Passenger vehicle occupant conditioning system based on predictive and anticipatory control.

Abstract

An occupant conditioning system for a passenger vehicle is presented that operates to predict events that affect occupant condition (e.g., motion sickness) before they occur and to use the predictions to implement preemptive intervention in active vehicle subsystems.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Patent Application No. 17 / 072,802, filed October 16, 2020, and also claims the benefit of U.S. Provisional Application No. 62 / 916,406, filed October 17, 2019, the entire disclosures of which are incorporated herein by reference.

[0002] Technical Field The present disclosure relates to a passenger vehicle occupant conditioning system based on predictive and preemptive control. [Background technology]

[0003] Background technology Motion sickness in passengers while traveling in passenger vehicles is a common condition. Moreover, passengers not driving the vehicle experience such motion sickness more intensely compared to vehicle drivers. This is due to the driver's ability to make look-ahead corrections when initiating driving actions involving acceleration (e.g., speeding up, braking, or turning). These pre-emptive corrections by the driver (such as tightening the abdominal core muscles when braking or tilting the body / head in the direction of the turn when turning) help the driver prepare slightly in advance of the acceleration associated with the driving action, but the passenger ends up passively reacting to these driving actions. As a result, passengers in conventional (i.e., manually driven) vehicles typically suffer from motion sickness more than drivers of such vehicles. In autonomous vehicles (AVs), where all passengers are passive passengers, the negative impact of motion sickness on passenger comfort is expected to be greater.

[0004] Additionally, there is a desire for productive use of commute time by non-driving occupants of conventional vehicles as well as all occupants of AVs. However, the linear and turning motions of the vehicle, including accelerations in all directions (i.e., forward / longitudinal, lateral, vertical, roll, yaw, pitch) while traveling, adversely affect the intended productive tasks performed by the occupants (e.g., reading, writing, typing, drawing / sketching, exercising, listening to music, etc.).

[0005] The movement of the occupant's body (e.g., including the torso, head, limbs, etc.), the occupant's physiological state (e.g., heart rate, blood pressure, body temperature, etc.), the occupant's comfort state, the occupant's sensations of motion sickness and nausea, and the occupant's productivity (i.e., ability to productively perform intended tasks) are all examples of what is referred to in this disclosure as "occupant state."

[0006] This section provides background information related to the present disclosure that is not necessarily prior art. Summary of the Invention [Means for solving the problem]

[0007] Summary of the Invention This section provides a general overview of the disclosure, and is not an exhaustive disclosure of its entire scope or all of its features.

[0008] A system for occupant conditioning in a passenger vehicle is presented. In one aspect, the system includes an active seat along with a prediction algorithm and a command generation algorithm executed by a computer processor. The active seat supports a given occupant in the passenger vehicle. The prediction algorithm operates to predict a state of the given occupant and a movement of the passenger vehicle, preferably using machine learning methods, the predicted movement including an acceleration of the passenger vehicle. The command generation is configured to receive a predicted state of the given occupant and a predicted movement of the passenger vehicle from the prediction algorithm. The command generation algorithm operates to determine a preemptive command to tilt the active seat and issue the preemptive command to the active seat, the active seat being tilted in the same direction as the acceleration of the passenger vehicle.

[0009] In a second aspect, an occupant conditioning system includes an active restraint. The active restraint resides in a vehicle and is configured to restrain a given occupant in the vehicle. In this embodiment, a predictive algorithm predicts a state of the given occupant and a motion of the vehicle, preferably using machine learning methods. A command generation algorithm is configured to receive the predicted state of the given occupant and the predicted motion of the vehicle from the predictive algorithm. The command generation algorithm determines a preemption command for the active restraint and issues the preemption command to the active restraint.

[0010] In a third aspect, an occupant conditioning system includes an active occupant stimulation subsystem. The active occupant stimulation subsystem is present in a vehicle and configured to generate a stimulation to a given occupant in the vehicle. In this embodiment, a prediction algorithm predicts a state of the given occupant and a motion of the vehicle, preferably using a machine learning method, the predicted motion including an acceleration of the vehicle. A command generation algorithm is configured to receive the predicted state of the given occupant and the predicted motion of the vehicle from the prediction algorithm. The command generation algorithm is operative to determine a preemptive command to stimulate the given occupant to lean in the same direction as the acceleration of the vehicle and issue the preemptive command to the active occupant stimulation subsystem.

[0011] In a fourth aspect, an occupant condition adjustment system includes an active productivity interface. The active productivity interface is present in a passenger vehicle and configured to support tasks performed by a given occupant while the vehicle is moving. A predictive algorithm operates to predict a state of the given occupant, preferably using machine learning methods. A command generation algorithm is configured to receive a predicted state of the given occupant from the predictive algorithm. The command generation algorithm operates to determine a preemptive command for the active productivity interface and to issue the preemptive command to the active productivity interface.

[0012] Further areas of applicability will become apparent from the description provided herein.The description and specific examples in this summary are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure.

[0013] drawing The drawings described herein are only for the purpose of illustrating selected embodiments rather than all possible implementations and are not intended to limit the scope of the present disclosure. [Brief description of the drawings]

[0014] [Figure 1A] FIG. 1 illustrates a typical driving scenario for a vehicle making a right turn. [Figure 1B] FIG. 1 illustrates a typical driving scenario for a vehicle making a right turn. [Figure 1C] FIG. 1 illustrates a typical driving scenario for a vehicle making a right turn. [Figure 2A] FIG. 1 illustrates a typical driving scenario for vehicle braking. [Figure 2B] FIG. 1 illustrates a typical driving scenario for vehicle braking. [Figure 2C] FIG. 1 illustrates a typical driving scenario for vehicle braking. [Diagram 3] FIG. 1 is a block diagram of a computational architecture for a typical autonomous vehicle. [Figure 4]FIG. 1 is a block diagram of the computational architecture of an autonomous vehicle equipped with the PREACT system. [Diagram 5] FIG. 1 is a block diagram of the computational architecture of a conventional vehicle equipped with a PREACT system. [Figure 6] FIG. 6 is an expanded version of the block diagram shown in FIG. [Figure 7] FIG. 7 is a detailed exploded view of the PREACT mechatronics subsystem shown in FIG. [Figure 8] 1 illustrates an example active restraint subsystem. [Figure 9] 1 illustrates an exemplary active productivity interface. [Figure 10] As is commonly understood, longitudinal (ie, driving direction), lateral and vertical directions of a vehicle are indicated. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Corresponding reference numerals indicate corresponding parts throughout the several views of the drawings. Detailed Description Example embodiments will now be described more fully with reference to the accompanying drawings.

[0016] The key idea behind a proposed occupant condition adjustment system for a passenger vehicle (e.g., associated with all occupants of an autonomous vehicle or non-driving occupants of a conventional manually driven vehicle) (e.g., referred to as the PREACT system in various places in this disclosure) includes predicting events that will affect occupant condition before they actually occur, using this prediction to determine that certain preemptive interventions should be taken, and making these preemptive interventions via various active subsystems on board the vehicle. In the PREACT system, this prediction is made by one or more computers via one or more PREACT predictive algorithms (e.g., data-driven models, machine learning, artificial intelligence, etc.) that utilize, for example, real-time and aggregated data over time regarding route and traffic information, vehicle information, vehicle subsystem information, occupant information, etc., to predict route, vehicle navigation, vehicle conditions, vehicle subsystem conditions, and ultimately occupant conditions (including comfort, motion sickness, productivity). A second set of computer algorithms, called PREACT look-ahead algorithms (also called PREACT command generation algorithms), generate commands that are sent proactively to various vehicle subsystems (e.g., driving subsystem, steering subsystem, active seat subsystem, active restraint subsystem, active occupant stimulation subsystem, active productivity subsystem, cabin environment subsystem, vehicle audio-visual subsystem, cabin lighting subsystem, etc.). These look-ahead commands or corrections are implemented via vehicle subsystems (called PREACT mechatronics subsystems) prior to events experienced by the vehicle that are predicted to cause motion sickness in passive occupants based on the aforementioned predictions. Thus, occupants of a vehicle equipped with a PREACT system are no longer completely passive like non-driving occupants of a conventional manually driven vehicle, but instead are more like (or better than) drivers of a conventional vehicle.

[0017] To illustrate the operation of the PREACT system, two common driving scenarios are shown in Figures 1A-1C (vehicle turning right) and 2A-2C (vehicle braking to slow down or stop). The PREACT prediction algorithm uses real-time and aggregated data over time about the occupant, vehicle, vehicle subsystems, route, and traffic to predict occupant states (including body and limb movements, motion sickness, comfort, and productivity). Based on these predictions, the PREACT look-ahead algorithm generates and sends look-ahead commands to the PREACT mechatronic subsystem (in this case the active seat).

[0018] In FIG. 1A, the vehicle is shown traveling straight along the path. In a vehicle without the PREACT system (shown in FIG. 1B), when the vehicle turns right, the body of the vehicle sways (i.e., rotates slightly) away from the direction of the turn (towards the left in response to the vehicle turning right). Similarly, the non-driver's body, including the torso, head, or other limbs, etc., tends to move (e.g., sway, tilt, rotate) away from the direction of the turn. Such occupant movements and associated speeds, rotations, and accelerations lead to motion sickness in the occupant. Meanwhile, the driving occupant (not shown) is anticipating the vehicle turning and the consequences for his or her body (i.e., his or her body will swing outward in the opposite direction to the turning direction), and therefore intentionally tilts, twists, or stiffens (or a combination thereof) his or her body, or head, or neck, or limbs, or muscles, in the direction of the turn. The driver anticipates this because he or she is the one who initiated the vehicle turning in the first place. The driver performs preemptive corrections to adjust his or her body (including, for example, torso, head, neck, limbs, etc.) based on past experience of how such turns affect his or her body. Such preemptive corrections reduce the occupant's body movements (including speed, rotation, and / or acceleration), thereby reducing the occupant's motion sickness while driving.

[0019] This anticipatory awareness of the turn and preemptive action to the turn is replicated for all non-driving occupants via the PREACT system. In a vehicle equipped with a PREACT system (shown in FIG. 1C), a vehicle route and navigation prediction algorithm determines that the vehicle will make a right turn at some point in the future, and the PREACT prediction algorithm predicts the impact this will have on occupant state (including body movement, motion sickness, comfort, productivity, etc.). This PREACT prediction algorithm provides an anticipation or forecast or prediction that an occupant is likely to experience motion sickness due to the vehicle turning, before the vehicle actually begins to turn and the occupant actually experiences any body movement or motion sickness.

[0020] Based on this prediction, the PREACT look-ahead algorithm (also called the PREACT command generation algorithm) generates look-ahead commands and sends them to the on-board PREACT mechatronics subsystems, including the active seat subsystem and the active restraint subsystem. As a result of these look-ahead commands, before the vehicle actually turns, the active seat gradually starts to sway (i.e., tilt) in the direction of the expected turn (i.e., lateral to the vehicle's centripetal acceleration) and the active restraint gradually starts to increase tension in this direction. In this way, by the time the vehicle actually starts to turn, the occupant's body is in an orientation that minimizes or eliminates body movement, thus reducing motion sickness and increasing productivity. Because the active seat and active restraint gradually began to execute their actions before the turn, these changes are gradual and may be barely perceptible to the occupant.

[0021] Similarly, vehicle braking is illustrated in Figures 2A-2C. In Figure 2A, the vehicle is shown traveling straight down a path at a continuous speed. In a vehicle not equipped with the PREACT system (illustrated in Figure 2B), when the vehicle brakes the vehicle body and the occupant's body (including, for example, head, torso, limbs, etc.) leans forward, this can cause motion sickness, discomfort, and loss of productivity to the occupant. However, in a vehicle equipped with the PREACT system (illustrated in Figure 2C), the vehicle route and navigation prediction algorithm determines that the vehicle will brake at some point in the future, and the PREACT prediction algorithm predicts the effect this will have on occupant state (including body movement, motion sickness, comfort, productivity, etc.). This PREACT prediction algorithm provides an anticipation / prediction / forecast that the occupant is likely to experience motion sickness, discomfort, or loss of productivity due to vehicle braking before the vehicle actually begins to decelerate and the occupant actually experiences any body movement or motion sickness or discomfort.

[0022] Based on this prediction, the PREACT look-ahead algorithm (also referred to as the PREACT command generation algorithm) generates look-ahead commands and sends them to the active seat subsystem and the active restraint subsystem. As a result of these look-ahead commands, the active seat starts to gradually tilt (i.e., lean) backward (i.e., opposite to the deceleration direction, which is the same as the longitudinal acceleration direction) and the active restraint starts to gradually increase the tension in the backward direction before the vehicle actually starts to decelerate. In this way, by the time the vehicle actually starts to brake, the occupant's body is oriented and / or restrained in such a way that the body movement is minimized, thereby reducing motion sickness and increasing productivity.

[0023] The commands generated by the PREACT command generation algorithm, the resulting actions (and resulting states) of the PREACT mechatronic subsystem, and the resulting occupant states are all communicated to the data center, which uses them to inform the PREACT prediction algorithm and the PREACT command generation algorithm, further improving the effectiveness of the PREACT system going forward.

[0024] It should be noted that the PREACT mechatronic subsystem (e.g., active seat or active restraint) is different from other existing active seat or active restraint subsystems that are commanded / controlled / activated in response to an event once initiated or occurring. It is an example of reactive control. PREACT, on the other hand, is an example of preemptive control. Reactive control has several drawbacks. Often, with reactive control, the time that an event is detected to be occurring by sensors and computers is too late to make effective interventions / corrections. Or, if corrections / actions / interventions are made, they must be made in a very short time, which may be too bothersome to the occupants.

[0025] The occupant conditioning system is relevant for any type of passenger vehicle, including land vehicles that may be fully autonomous, i.e. self-driving vehicles, or partially autonomous vehicles, or vehicles with driver assistance functions, or traditional manually driven vehicles, or robotically driven vehicles. Land vehicles include road vehicles such as trucks, trailers, vans, cars of various sizes, motorcycles, tricycles, and off-road vehicles such as tanks, tractors, bulldozers, and the like. The invention is also relevant for other vehicles, including track-based (e.g., trains, monorails, cable cars, etc.), and water vehicles or watercraft (e.g., ships and boats, hovercraft), and air vehicles (e.g., airplanes of various sizes, gliders, etc.).

[0026] The computational architecture of a typical autonomous vehicle (AV) is captured via the block diagram shown in Figure 3, which shows three levels of computation (high, medium, and low). A similar computational architecture for an AV equipped with a PREACT system is shown in Figure 4. A similar computational architecture for a conventional vehicle equipped with a PREACT system is shown in Figure 5.

[0027] These diagrams represent block diagrams in the sense that each element of the diagram is either a system (including subsystems, components, modules, etc.) represented by a block or a signal (i.e., information, data, etc.) represented by a line. In the context of systems theory, a block diagram captures the flow of signals (information / data) between systems (either physical entities, e.g., mechatronic subsystems, actuators, sensors, vehicles, etc., or computations, e.g., controllers, algorithms, etc.). In contrast to a flowchart, a block diagram does not capture the chronological order of events, but rather the flow of information (represented by arrows) and processing (represented by blocks) that is always occurring. Flowcharts are often used in the context of capturing an algorithm or a series of logical steps where the chronological order (i.e., sequence in the time domain) is important. Figure 4 follows a block diagram representation (i.e., systems and signals) and is not necessarily a logical flowchart. Some of the individual blocks in the block diagram represent controller / logic / algorithm blocks, and there may be sequential / time-series logic captured within such controller / logic / algorithm blocks.

[0028] In the block diagrams of Figures 3-5, there is everything happening all the time. The low level computations and data flows are done in real time due to the physical systems and subsystems. Some of the mid-level and high level computations can happen in computer time (i.e. as fast as computation and communication can be). This can be faster or slower than real time, or synchronous with real time.

[0029] The block diagrams in Figures 3-5 represent a computational architecture, with each block representing a subsystem that is an algorithm or a physical system. This computational architecture does not necessarily represent the physical location of the computers or physical components. Computation is broadly defined as any calculation and analysis of information and control of hardware. Such computation may occur on-board various vehicles (i.e., vehicle computers, microcontrollers, microprocessors, integrated circuits, memory, etc.) or multiple vehicles, or on a remote server (e.g., cloud computing), etc.

[0030] In FIG. 3, at the low level (1000) of the computational architecture is a vehicle and its various subsystems. The vehicle subsystems include passive and active subsystems. Passive subsystems do not involve active control in real time, such as a conventional suspension system, a conventional seat, a conventional seat belt, etc. Although the parameters of these passive subsystems may be changed / updated from time to time (e.g., adjust the position or recline of the seat, or adjust the suspension), the dynamic variables associated with these subsystems are not actively controlled in real time to meet some desired objective. Passive subsystems may have sensors that measure the state of these subsystems, but these states are not actively controlled. An example of a passive vehicle subsystem is a suspension seat with springs and dampers, where the exact position of the seat can be measured by sensors, but the position and orientation of the seat are not controlled in real time, but are determined by the springs and dampers.

[0031] Active subsystems, on the other hand, are actively controlled via some computer (e.g., a microprocessor) to ensure that their state (which is a time variable) follows some desired objective over time. Examples of such active subsystems in a vehicle are active roll control, active suspension, active seats, active seat belts, active cabin environment, etc. For example, the movement and stiffness of an active suspension subsystem can be actively controlled in real time, independent of the fact that its movement is also measured using sensors.

[0032] In an AV, the vehicle subsystems may include a vehicle driving subsystem, a vehicle steering subsystem (206A), a vehicle seating subsystem (207), and a vehicle restraint subsystem (208). The vehicle driving subsystem (206A) may include vehicle drive system components such as an engine / motor, a drivetrain transmission, and ultimately the wheels. The vehicle steering subsystem (206A) may include a steering input (e.g., a motor or other actuator), a steering transmission, a steering linkage, and ultimately the wheels.

[0033] There may be other subsystems (206B), such as a vehicle suspension subsystem and a cabin subsystem. The vehicle suspension subsystem includes components such as the suspension, shock absorbers, and wheels. The cabin subsystem includes air conditioning, heating, and ambient lighting and sound within the vehicle. The vehicle driving (206A) subsystem is responsible for controlling the movement of the vehicle.

[0034] Upon receiving drive and steering commands (205), the vehicle drive and steering subsystem (206A) causes the vehicle to achieve a particular vehicle state (e.g., position, velocity, acceleration, roll, pitch, yaw, turn, etc.) controlled by vehicle dynamics. These subsystems affect the aforementioned states of the vehicle body and chassis. These states affect the vehicle seat (207) when the vehicle seat is attached to the vehicle chassis. The vehicle seat (207) and vehicle restraints (208) affect occupant states (e.g., body movement, physiological state, motion sickness, comfort, productivity, etc.) when an occupant (209) is seated in the vehicle seat (207) and restrained by the vehicle restraints (208).

[0035] The mid-level (2000) of the computational architecture of Figure 3 contains vehicle algorithms used to plan, predict, and generate commands sent to the lower-level vehicle subsystems. Vehicle route and navigation prediction algorithms (204A) perform route planning and predict optimal vehicle navigation based on aggregated over time and real-time measurement data (203) received from the higher level (3000) representing the data center. Based on these predictions and data (203), command generation algorithms (204B) generate driving and steering commands (205) and send them to the vehicle driving and steering subsystems (206A).

[0036] At a high level (3000), data may be aggregated over multiple trips made by multiple people, from multiple vehicles, between multiple destinations, and over time, thus acting as a transportation system level data center. This data aggregated over time is collectively known as aggregated data over time (201). Additionally, real-time data (202) from the vehicles and their subsystems and occupants may be measured via various sensors and sent to the data center, collectively known as real-time measured data (200). Here the data is compiled and processed to remove spikes and noise so that the most reliable data can be made available to the vehicle algorithms at the mid-level (2000). The vehicle route and navigation prediction algorithm (204A) may, for example, predict well in advance when and where the vehicle should turn, and the command generation algorithm (204B) generates commands (205) at the appropriate time to effect this turn. These commands (205) are sent to the vehicle driving and steering subsystem (206A).

[0037] Up to this point, we have described a representative computational architecture of an existing autonomous vehicle (AV). Next, Figure 4 shows the computational architecture of an AV equipped with a PREACT system, captured through a block diagram. Again, there are three levels of computational strategies that seamlessly integrate data aggregation and analysis, predictive algorithms, look-ahead algorithms, and mechatronics subsystems, all of which work together to adjust occupant status. In Figure 4, blocks (3), (5), (6), (7), (10A), (10B), and parts of (14) and (15), specifically the PREACT system and occupant information, represent unique additional modules associated with the PREACT system that extend the existing autonomous vehicle (AV) architecture shown in Figure 3.

[0038] At the low level (1000) of the computational architecture of FIG. 4, there are various vehicle subsystems. As mentioned before, the vehicle subsystems can be passive or active. Of all the active subsystems, some or all are preemptively commanded by the PREACT look-ahead algorithm (10B) with the purpose of modifying the occupant state, such as reducing body movement, including reducing motion sickness and / or increasing productivity. The subset of active vehicle subsystems preemptively commanded / controlled by the PREACT look-ahead algorithm (10B) is called the PREACT mechatronics subsystem. Examples of this include the PREACT active seat (3), the PREACT active restraint (5), the PREACT active occupant stimulation (6), and the PREACT productivity interface (7).

[0039] In one embodiment, other vehicle subsystems (1B), such as vehicle suspension subsystems, cabin subsystems, etc., may not be commanded by the PREACT look-ahead algorithm (10B). In yet another embodiment, these subsystems, as well as others not shown in FIG. 4 (e.g., active roll control, anti-lock braking, active chassis, etc.), may be controlled and commanded by the PREACT look-ahead algorithm (10B) to affect occupant (4) movement / movement, motion sickness, comfort, and productivity. All such subsystems are then included in the PREACT mechatronics subsystem.

[0040] The driving and steering commands (2) in FIG. 4 generated by the vehicle driving command generation algorithm (8B) are sent to the vehicle driving and steering subsystem (1A). In response to these driving and steering commands (2), the vehicle driving and steering subsystem (1A) causes the body / chassis to achieve a specific vehicle state (e.g., position, velocity, acceleration, roll, pitch, yaw, turn, etc.) controlled by the vehicle dynamics. In an AV equipped with a PREACT system, there is at least one possible additional PREACT mechatronics subsystem. FIG. 4 features a PREACT active seat (3) that can be actuated in a specific motion (e.g., pitch, tilt, lift, yaw, etc.) relative to the body / cabin / chassis. Additionally, the occupant (4) is restrained to this seat via a PREACT active restraint (5) that comprises a harness with multiple anchor points that can be selectively tightened when commanded. Additionally, the occupant (4) is presented with PREACT active occupant stimuli (6) that can include visual, audio, or vibrotactile input. Additionally, the occupant (4) can perform productive tasks (e.g., reading a book, typing and reading information on a display, etc.) in the vehicle by interacting with the PREACT active productivity interface (7). This can help reduce motion sickness and increase productivity, for example by tracking the occupant's gaze and moving the display to move in sync with the occupant.

[0041] Occupant state (body movements, physiological state, motion sickness, comfort, productivity) is affected by the vehicle driving and steering subsystem (1A), the active seat (3), the active restraints (5), and the occupant's (4) responses to the active occupant stimuli (6), and the active productivity interface (7). In particular, the occupant has a bidirectional (two-way) interaction with the active productivity interface (7), represented by the arrows moving in both directions between the occupant (4) and the active productivity interface (7). This means that the occupant provides input to the active productivity interface (7), for example, via typing on a keyboard, and the active productivity interface (7) provides input to the occupant (4), for example, by tilting or adjusting the surface on which the keyboard rests.

[0042] The intermediate level (2000) of this system architecture includes vehicle algorithms whose calculations are used to plan, predict, and generate commands that are sent to the lower level vehicle subsystems. A vehicle route and navigation prediction algorithm (8A) performs route planning and predicts optimal vehicle navigation based on historical aggregated and real-time measurement data (9) received from the higher level (3000) representing the data center. Based on these predictions and data (9), a command generation algorithm (8B) generates driving and steering commands (2) and sends them to the vehicle driving and steering subsystem (1A). However, in this case, there are additional PREACT prediction algorithms (10A) and PREACT look-ahead algorithms (10B) that work in conjunction with the vehicle route and navigation prediction algorithm (8A) and the vehicle driving command generation algorithm (8B). The PREACT algorithms (10A) and (10B) also receive and utilize historical and real-time data (11) from the higher level (3000) data center. The PREACT predictive algorithm (10A) functions in two ways (short-term look-ahead and long-term look-ahead) to provide look-ahead corrections / commands (12) to the PREACT mechatronic subsystems such as the active seats (3), active restraints (5), active occupant stimuli (6), and active productivity interfaces (7), as described below.

[0043] First, we will discuss short-term look-ahead. In this case, at the moment when the vehicle driving command generation algorithm (8B) sends a driving and steering command (2) to the vehicle driving and steering subsystem (1A), at the same moment this command is also shared (13) with the PREACT algorithms (10A and 10B). As a result, the PREACT look-ahead algorithm (10B) sends look-ahead corrections (12) to the PREACT mechatronics subsystems. These look-ahead corrections are possible because the response time / dynamics of these mechatronics subsystems are much faster (due to their more compact size) than the response time / dynamics of the vehicle driving and steering subsystem (1A). In other words, by the time the effect of the driving command (2) has caused the vehicle to reach the intended state (e.g., accelerating, braking, or turning), the driving command (13) and the associated corrections (12) have already been "feed-forwarded" to the PREACT mechatronics subsystems. Due to this faster response, they begin to favorably change occupant conditions slightly ahead of inertial events related to vehicle conditions (eg, acceleration, deceleration, turning, etc.).

[0044] Secondly, long-term look-ahead is described. In this case, another component of the look-ahead correction (12) generated by the PREACT look-ahead algorithm (10B), also called the PREACT command generation algorithm, is based on historical and real-time data (11) from a high-level (3000) data center. At the high-level (3000), data is collected from real-time measurements (14) and aggregated over time from multiple sources (15). This includes historical traffic pattern data as well as real-time traffic patterns (e.g., accidents causing traffic jams) as the AV is traveling. This data includes information about static road infrastructure (e.g., stop signs, traffic light locations and schedules, speed bumps, medians, exit ramp curvature, etc.), as well as any temporary potholes or traffic cones. Additionally, this data includes vehicle information (make, model, year, vehicle dynamics model) and real-time measurements of vehicle conditions (position, speed, acceleration, turns, vertical bumps, etc.). All of this data is typically already used in existing AV architectures. However, for AVs equipped with the PREACT system, additional data types include PREACT mechatronics subsystem information and occupant information (including parameters and states such as height, weight, etc.). This data is collected over time (i.e., multiple trips) as well as measured in real time. Examples of PREACT mechatronics subsystem states include active seat reclination / tilt angle, seat belt tension, response time, productivity interface interactions, etc. Occupant states include mechanical variables such as body tilt angle, head tilt angle, head acceleration and angular velocity, and physiological states such as electrodermal activity, heart rate, skin temperature, and respiration.

[0045] At a high level (3000), data is aggregated over multiple trips made by multiple people, from multiple vehicles, between multiple destinations and over time, thus acting as a transportation system level data center. Here, the data is compiled and processed to remove spikes and noise so that the most reliable data can be made available to the vehicle route and navigation prediction algorithm (8A), the vehicle driving command generation algorithm (8B), the PREACT prediction algorithm (10A), and the PREACT look-ahead algorithm (10B). Based on this data, the vehicle route and navigation prediction algorithm (8A) can predict / anticipate, for example, well in advance that the vehicle is approaching a turn and a turn command (2) will be sent to the vehicle driving and steering subsystem (1A). As a result of this prediction, the PREACT prediction algorithm (10A) can predict and anticipate inertial events (i.e. events related to acceleration) and their impact on occupant status. Thus, the PERACT look-ahead algorithm (10B) determines / generates the look-ahead corrections (12) even before the current turn command (2) is sent to the vehicle driving and steering subsystem (1). As a result, the PREACT look-ahead algorithm (10B) can command the active seat (3) to start (gently and gradually) tilting in the intended direction of the turn (see FIG. 1) even before the turn is initiated or made. Similarly, the PREACT look-ahead algorithm (10B) can command the active restraints (5) to selectively tighten to gently pull the torso of the occupant (4) in the direction of the turn, starting shortly before the turn is initiated. Thus, the PREACT system architecture is based on a combination of feedback (16) that reacts to real-time information and provides either no anticipation or short-range anticipation (depending on the spatial measurement range of the real-time sensors) and a feedforward (12) that is based on short-term or long-term anticipation / prediction by the PREACT prediction algorithm (10A) and implemented by the PREACT look-ahead algorithm (10B).

[0046] The PREACT system can also be used in conventional (i.e., manually driven) vehicles that are only partially autonomous (e.g., driver-assisted) or not autonomous at all. The system architecture of such a vehicle equipped with a PREACT system is shown in FIG. 5. Blocks (3), (5), (6), (7), (14), (15), (16), (9), (11), (12), (10A), (10B), and (13) of FIG. 4 are the same as blocks (312), (313), (314), (315), (300), (301), (302), (303), (304), (309), (307A), (307B), and (306) of FIG. 5. The driving occupant (310) is the occupant in the vehicle who provides driving and steering commands to the vehicle driving and steering subsystem (311A). The driving occupant (310), as shown in the figure, is different from the non-driving occupant (316). As previously mentioned, because the driving occupant commands the driving and steering actions of the vehicle, the driving occupant anticipates the outcome of these actions and has the ability to preemptively adjust his or her body. However, the non-driving occupant does not have the benefit of such anticipation and therefore does not make any preemptive corrections himself or herself. In conventional vehicles without the PREACT system, this lack of anticipation and preemptive corrections can lead to undesirable occupant states (high body movement, high motion sickness, low productivity).

[0047] However, in a conventional vehicle equipped with a PREACT system, the PREACT prediction algorithm (307A) predicts future events and the PREACT look-ahead algorithm (307A) provides look-ahead commands (309) to the non-driving occupant to better regulate the occupant condition (e.g., reduce motion sickness and increase productivity). The driving occupant (310) has his own anticipatory and look-ahead corrections, but the PREACT system can augment this and benefit the driving occupant as well. In this case, the vehicle route and navigation prediction algorithm (305) does not send driving and steering commands to the vehicle driving and steering subsystem (311A). However, the vehicle route and navigation prediction algorithm (305) provides inputs (306) to the PREACT prediction algorithm (307A).

[0048] The PREACT prediction algorithm (307A) receives real-time and historical aggregate data (304) from a high-level (3000) data center, predicted driving and steering commands (306) from a vehicle driving and navigation prediction algorithm (305), and / or real-time driving and steering commands (317) from a driving occupant (310). The latter is available to the PREACT prediction algorithm (307A) via real-time data feedback (302) that goes to the real-time measurement data (300) of the high-level (3000) data center and flows to (307A) via data inputs (304). The real-time and historical aggregate data (304) relates to route and traffic information, vehicle information, vehicle subsystems (including the PREACT mechatronics subsystem), and occupant information (including driving and non-driving occupants). The PREACT prediction algorithm (307A) uses these inputs to predict the timing and occurrence of occupant states, and based on these predictions, the PREACT look-ahead algorithm (307B) generates and sends look-ahead corrections / commands (309) to various PREACT mechatronic subsystems, including the PREACT active seat (312), the PREACT active restraints (313), the PREACT active occupant stimuli (314), and the PREACT active productivity interface (315).

[0049] Detailed description of the PREACT system FIG. 6 shows an expanded version of FIG. 4. The blocks in FIG. 4 and FIG. 6 are similar to each other. The architecture levels (e.g., high, mid, low level calculations) are the same throughout both FIG. 4 and FIG. 6. The PREACT mechatronics subsystem (32) in FIG. 6 includes the PREACT active seat (3), the PREACT active restraint (5), the PREACT active occupant stimuli (6), and the PREACT active productivity interface (7) in FIG. 4. The occupant (4) in FIG. 4 corresponds to the occupant (33) in FIG. 6. The vehicle driving and steering subsystem (1A) in FIG. 4 is identical to the vehicle driving and steering subsystem (31A) in FIG. 6. The prediction algorithm (8A) in FIG. 4 includes the vehicle model (27) and the route and navigation command generation (25) in FIG. 6. The command generation algorithm (8B) in FIG. 4 includes the driving behavior command generation (26) in FIG. 6. The PREACT prediction algorithm (10A) of FIG. 4 includes the PREACT mechatronics subsystem model (29) and the occupant model (30) of FIG. 6. The PREACT look-ahead algorithm (10B) of FIG. 4 includes the "Generate PREACT mechatronics subsystem commands" (28) of FIG. 6. The real-time measurement data (14) and the aggregated data over time (15) of FIG. 4 are a combination of the route and traffic information (17, 18), the vehicle information (19, 20), the PREACT system information (21, 22), and the occupant information (23, 24) of FIG. 6. The driving and steering commands (2) and other information sent from the mid-level to the low-level vehicle driving and steering subsystem (1A) are similar to the information flow of FIG. 6, indicated by (42). The look-ahead corrections (12) of FIG. 4 are represented by (50). The real-time feedback (16) in Figure 4 is similar to the information flow in Figure 6, shown by (39, 41, 45-46, 49, 53-55, 60). The information flow (9) from the data center (3000) in Figure 4 to the vehicle route and navigation prediction algorithm (8a) and the vehicle driving command generation algorithm (8b) is similar to the information flow in Figure 6, shown by (37, 40, 43). The information flow (11) from the data center in Figure 4 to the PREACT algorithms (10a and 10b) is similar to the information flow in Figure 6, shown by (47, 51, 64).In the following sections, the overall system shown in FIG. 6 is described in detail, with the block reference numbers relating to the block numbers in FIG.

[0050] FIG. 7 shows a more detailed exploded view of the PREACT mechatronics subsystem (32) block shown in FIG. 6. However, FIG. 7 is not a block diagram; rather, it is a chart of various possible PREACT mechatronics subsystems (32). FIG. 7 shows further details of the interaction between the inputs (50) of FIG. 6 and the PREACT mechatronics subsystem (32). Specifically, how the PREACT mechatronics subsystem (32) uses commands and other information (50) from the mid-level calculations (2000) to determine the operation of the active seats (68), active restraints (69), active occupant stimuli (70), active cabin environment (71), and active productivity interface (72). The current and look-ahead commands (50) of FIG. 6 and (12) of FIG. 4 are similar to (66-67) of FIG. 7. In Figure 7, the PREACT mechatronic subsystems (68-70, 72) are similar to those in Figure 4 (3, 5-7), respectively. Additionally, other additional possible PREACT mechatronic subsystems, such as an active cabin environment (71), are also shown in Figure 7.

[0051] Data Center - High Level Computing (3000) The data center (3000) provides for data compilation, integration, and storage. This represents the highest level of computation within the PREACT system architecture shown in FIG. 6. Data is always collected in real time and stored over time. The stored data becomes part of the historical data in the data center. The entire data stream (a combination of real time and historical data of the same type) is available to the rest of the PREACT system, and this data is constantly updated. The terms "data" and "information" are used interchangeably herein. The collected data may be aggregated. Data aggregation refers to the integration or synthesis of multiple data streams from various sources compiled together in an appropriate format. In addition to synthesizing multiple data streams, the same or similar data from multiple sources is compiled and reconciled. Historical or past data can be analyzed for multiple purposes, such as, but not limited to, to determine patterns and trends, which helps predict future events, and such predictions can be used to take preemptive action. This prediction can be achieved by online machine learning, offline machine learning, or some combination thereof. The data center collects data from various sources, including other databases (34, 61), and sends data to them. It collects measurement data (54) from sensors in the PREACT mechatronics subsystem (32). It collects measurement data (46) from sensors in the various vehicle subsystems (31A and 31B). It collects measurement data (54) from sensors in the various PREACT mechatronics subsystems (32). It collects data (60) from on-board sensors, personal electronic devices such as wearable electronic devices, tablets and computers that measure the conditions and parameters of the occupants (33). It collects data (62) from other PREACT and non-PREACT vehicles (35) and other occupants in other vehicles. It collects data (63) from infrastructure and environmental sensors (36).In this context, a non-PREACT vehicle refers to any vehicle that is not equipped with the PREACT system but is capable of providing relevant information to the PREACT computing system via direct (e.g. V2V communication) or indirect communication (e.g. via an intermediate database).

[0052] Data communications may be accomplished by wired communications, wireless communications such as WiFi, Bluetooth, NFC, or any combination thereof. Data communications may include any desired combination of wired (e.g., cable and fiber) and / or wireless (e.g., cellular, radio, satellite, microwave, and radio frequency) communications mechanisms and any desired network topology (or multiple topologies if multiple communications mechanisms are utilized). Communications networks include wireless communications networks (e.g., using Bluetooth, IEEE 802.11, etc.), local area networks (LANs), and / or wide area networks (WANs), including the Internet, that provide data communications services.

[0053] Some of the collected data may be corrupted, noisy, or otherwise damaged and may be unusable or harmful. To ensure that good quality data is stored and used in the calculations, the data center processes and evaluates all received information and assigns a confidence value. Information with an appropriate confidence value is stored by the data center and used in all further calculations. Some of the data collected by the data center comes from environmental sensors and other estimators mounted on the vehicles, occupants, and infrastructure sensors. Data from such sensors may be noisy. The data center may use filters and other techniques that can "clean" the data and remove noise, making the data usable by the data center for storage and processing, and available to various algorithms at an intermediate level (2000).

[0054] Data classification describes classes of data (e.g., parameters and dynamic variables). Furthermore, these data classes span the different types of data collected by the data center (3000) and used by the vehicle algorithms (2000). Data types describe the different kinds of data collected and used by the system (e.g., route and traffic information, vehicle information, occupant information, etc.). Parameters are information that defines the system and do not necessarily always require time domain information. For example, the width of a road or the length of a vehicle are parameters that are not expected to change over time, especially in real time. Although parameters do not usually change dynamically over time, they may change periodically and therefore may require monitoring. These changes to parameters may be intentional or unintentional. For example, intentional changes to parameters include construction activities along a route that restrict the route, and unintentional changes to parameters include changes in tire diameter due to worn or flat tires, or component failure. Dynamic variables are information that constantly change over time and are affected by various factors and inputs. For example, vehicle speed, traffic density, etc. are dynamic variables that constantly change over time. Dynamic variables of a certain type of data are also referred to as states. For example, the speed of a vehicle is a dynamic variable and may be referred to as a vehicle state. Similarly, the heart rate and / or motion sickness of a passenger are dynamic variables and may be referred to as a passenger state.

[0055] The various types of data (ie, information) collected by the data center (3000) are described below.

[0056] a. Route and Traffic Information (17, 18): This information captures parameters and dynamic variables that describe the route and the associated traffic conditions along the route. It includes traffic pattern data (e.g., historical information about possible traffic jams at a given time of day, real-time traffic conditions caused by accidents or changes in road conditions, etc.), road parameters (e.g., turning curvature, road roughness, road width, number of lanes, etc.), as well as infrastructure parameters (e.g., stop signal locations, signal errors or failures, etc.) and infrastructure conditions (e.g., timing of stop signal switching). Information can be collected from a variety of sources, including, but not limited to, other vehicles (35), infrastructure sensors (36). This data can be collected (46, 54, 60) from on-board sensors, as well as databases (34) using satellite imagery and real-time measurements (36).

[0057] b. Vehicle Information (19, 20): This information captures parameters and dynamic variables that describe the vehicle and its associated operating conditions. This includes parameters that define the make, model, and physical attributes of the vehicle. This includes size, weight, inertia, wheelspan, engine horsepower or battery capacity, suspension stiffness and damping, etc. This also includes dynamic variables including vehicle motion states (position, speed, acceleration, rotation, roll, pitch, yaw, etc.), and cabin conditions (temperature, light, sound volume, etc.). Information can be collected from a variety of sources, which can include, but are not limited to, on-board sensors, infrastructure sensors (e.g., exterior cameras mounted on poles / buildings / overpasses that capture the vehicle's position, speed, acceleration), sensors on other vehicles, and user-reported data.

[0058] c. PREACT Mechatronics Subsystem Information (21, 22): This information describes the parameters and dynamic variables that describe the vehicle subsystems, specifically the PREACT mechatronics subsystem, including hardware and software. The PREACT mechatronics subsystems include active seats (3), active restraints (5), active occupant stimuli (6), active productivity systems (7), etc. The parameters can include the physical attributes of the PREACT mechatronics subsystem (e.g., size, weight, response time, etc.), and the dynamic variables (or states) can include acceleration, speed, and position. This data can be collected for every trip, and data can also be compared across multiple trips for the same occupant in the same vehicle.

[0059] d. Occupant Information (23, 24): This information captures parameters and dynamic variables that describe the occupant state. Occupant state refers to the occupant's physiological information, the occupant's body movements, comfort level, and productivity level. Parameters include occupant preferences, the occupant's weight, height, susceptibility to motion sickness, and other biometrics. Other examples of parameters include occupant preferences, for example indicating via an interface whether the occupant is experiencing motion sickness or reduced productivity state (e.g., productivity level) at some point during the trip. Body-worn sensors worn by the occupant or sensors in the vehicle cabin (e.g., imaging cameras, motion detectors) can determine various occupant data. Dynamic variables include the occupant's physiological state (heart rate, sweating, blood pressure, etc.) and the occupant's movements (e.g., the kinematics and dynamics of the occupant's body / torso / limbs / head).

[0060] The above data types are described in more detail in the following sections. The aggregated data can be used for long-term calculations and aggregate analysis. This analysis can leverage any combination of machine learning, artificial intelligence, data science, or predictive algorithms and techniques to generate insights from this collective data that could not otherwise be determined. Such insights can be used to inform the design of algorithms at mid-level calculations and the algorithms that control the operation of the PREACT mechatronic subsystems in the vehicle.

[0061] Route and traffic information (17 and 18 in Fig. 6) The scope of route and traffic information can include traffic related information, traffic patterns, navigation routes, and driving related information such as past route choices collected in real time from still active / ongoing trips, driving profiles (acceleration, braking, turning, etc.). A route is defined as a path connecting the origin and destination of a vehicle trip and any stops or events on the way to the destination. Associated with the vehicle's route is traffic information, defined as an extensive set of parameters and variables that define the trip, such as traffic congestion, traffic light status, road conditions along the route, etc. The data center (3000) that serves the PREACT system collects this information from multiple sources, such as other vehicles (32), user reported data (60), infrastructure sensors (63), a database of existing applications (such as Google Maps) (61), and satellite imagery (63). Data across multiple sources is reconciled to increase the reliability and fidelity of the data used by the PREACT algorithm. For example, if a particular road section is known to have a higher lateral acceleration magnitude based on historical aggregate data, but the acceleration experienced during a particular real-time journey is less than expected, analysis to determine the causes of such discrepancies can be performed in the future so that prediction accuracy can be improved.

[0062] Driving related information includes driving actions (65, 41), which refer to any and all planned (queued) for future and current decisions made by the "driving action command generation" algorithm (26) related to controlling and steering (e.g., accelerating, braking, cruising, turning, etc.) of the autonomous vehicle. This data is constantly updated as the trip progresses, and some or all of this data can be used to affect the still active / ongoing trip and associated PREACT look-ahead commands (50). Historical traffic information is an ever-growing data stream that collects traffic information from various sources and stores it to give insight into future trips of vehicles that may adopt similar routes. This information is collected via vehicle sensors such as mid-range / long-range sensors (e.g., LiDAR), IMU sensors, GPS, etc. This information is also collected from various infrastructure sensors (e.g., traffic cameras). Additionally, vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and infrastructure-to-vehicle (I2V) communications allow for the collection of data not only within the vicinity of a given vehicle, but also of the overall traffic and other physical environment around the vehicle, including static road structures (e.g., lanes, medians) as well as dynamic road conditions (e.g., temporary traffic cones).

[0063] Vehicle information (19 and 20 in Fig. 6) Vehicle information (i.e., vehicle data) includes parameters and dynamic variables that can be used to define vehicle attributes and states. This information can come from vehicle sensors (46), user reported data (60), data reported by other vehicles (62), and the like. Real-time vehicle sensor information includes all information and data collected in real-time from the vehicle. Vehicle sensors can be of two types: internal and external. External vehicle sensor information includes detected objects, road conditions, traffic conditions, traffic / driving information, and the like, providing the route and traffic information mentioned above. External vehicle sensors such as LiDAR, radar, cameras (i.e., imagers) can be used to detect and identify objects such as obstacles on the road, other vehicles, pedestrians, and cyclists. Internal vehicle sensors measure vehicle states such as vehicle acceleration, speed, chassis roll, engine power, braking, steering, and the like. Vehicle state refers to dynamic variables that capture changes in vehicle state, including the kinematics, motion, and dynamics of the vehicle (specifically, vehicle chassis, drivetrain, and cabin) subsystems. Sensors such as IMUs, accelerometers, encoders, potentiometers, etc. can be used to detect various vehicle conditions. This information can be used to generate driving behavior commands (26), as well as PREACT mechatronic subsystem commands (28). For example, if it is determined that a pedestrian is detected in the path of the vehicle and the vehicle is braking in response, the PREACT algorithms can use this information to determine an appropriate response using its various PREACT mechatronic subsystems to maximize occupant comfort and minimize motion sickness.

[0064] Historical vehicle sensor information includes historical / past data collected from a given vehicle and can include such data from other vehicles (either PREACT-equipped or not) from previous trips. This is data collected prior to the current vehicle trip or operation. Unlike current information specific to the present time, aggregated vehicle sensor information over time is sourced simultaneously from multiple vehicles and shared with other vehicles via vehicle-to-vehicle communication and network communication with the data center. While not all aggregated data over time is relevant, for example because a pedestrian detected by a vehicle in the past is unlikely to be in the exact same location, large-scale trends such as traffic volume and pedestrian patterns can be extracted. Additionally, multiple vehicles may be on the same route or path at different times. For example, a vehicle may detect traffic volume on a section of the route and slow down. This traffic volume information detected in real time is stored in the data center. If more vehicles continue to detect this traffic and slow down, this information is aggregated by the data center (35, 62) and informs the behavior of another PREACT vehicle approaching that section of the route but not yet reaching that traffic. In this way, the aggregate information over time is a combination of raw data, filtered / processed data, and potential data analytics / machine learning trends and insights. Machine learning and other computations may be on-board the vehicle or off-vehicle as part of a data center.

[0065] PREACT system information (21 and 22 in Figure 6) The PREACT system information includes information about the PREACT algorithms (28-30), their outputs, and the PREACT mechatronics subsystem (32), which is a collection of subsystems that work independently or in concert to mitigate and / or eliminate the causes and symptoms of motion sickness (also known as acceleration sickness) or improve productivity in any and all occupants (33) of a vehicle (currently a typical automobile and autonomous vehicles with various levels of autonomy). The PREACT algorithms (28-30) incorporate multiple sources of real-time information, as well as aggregated information over time from data centers (47, 51, 64), and use information about occupant preferences and an understanding of the causes of motion sickness to devise optimal PREACT mechatronics actions / commands (50) that minimize motion sickness, improve comfort, and increase productivity. These command signals (50) are sent to the PREACT mechatronics subsystem, where these preemptive commands are a combination of current and future commands based on the PREACT system's current understanding and predictions of occupant and vehicle conditions. These command signals (49) are also sent to the data center to become part of the aggregated PREACT system command / intervention data over time. These commands (50) are received by the PREACT mechatronics subsystem (32). This mechatronics subsystem includes multiple subsystems such as active seat, active restraint, active occupant stimulation, active productivity system, etc. The PREACT system information also includes sensor and performance data from the sensors of the mechatronics subsystem. For example, if it is found that for a particular occupant, active seat interventions produce more favorable results than active occupant stimulation, the PREACT command generation algorithm (28) will favor those interventions. Also, by combining information across multiple rides and multiple occupants, the system can learn optimal commands for the system by analyzing the aggregated data over time. PREACT system information includes any parameters and dynamic variables that define the operational state of the PREACT mechatronic subsystem.This includes sensor information from all hardware, and all input and output signals of these subsystems.

[0066] Although the commands (50) are described here as being proactive, i.e., based on predictions made by various algorithms (25, 26, 27, 28), in some cases these commands can also include a reactive component (e.g., commands or decisions that are purely based on predictions, but also responsive to what is measured in real time).

[0067] Occupant information (23 and 24 in Figure 6) The occupant information captures occupant states as well as occupant parameters (including attributes, preferences, etc.). Occupant states refer to occupant physiological information, occupant body movements, motion sickness level, comfort level, productivity level. Parameters include occupant preferences, occupant weight, height, motion sickness susceptibility, productivity tasks [Figure 7 (67)], etc. Other examples of parameters include the occupant indicating, via an interface (e.g., user input or user interface), whether he / she is motion sick, and if so, to what extent, or the change in productivity state (e.g., productivity level) at a point during the trip. Occupant states are dynamic variables including occupant physiological state, bio-indicators (heart rate, sweating, etc.), and occupant movements (occupant body / torso movements, locomotion, kinematics, and dynamics, etc.).

[0068] Real-time occupant information (60) is collected during the journey reflecting the occupant's state as a function of time measured in real time. Sensor information can provide information on the occupant's motion, kinematics, and dynamics, as well as physiological state. The motion state of the occupant dynamics refers to the kinematics and dynamics of the occupant's body within the autonomous vehicle. Physiological sensor information includes heart rate, respiration rate, sweating, etc. In-vehicle cameras (i.e., imaging devices) can provide tracking of body segments through computer vision algorithms. Additionally, the cameras can provide information on the tasks being performed by the occupant through human activity recognition software consisting of computer vision and machine learning algorithms. Wearable devices such as wristbands can also be included to provide physiological and motion tracking data. Active displays with occupant inputs can be used to allow the occupant to report preferences and provide direct feedback on the level of comfort they are experiencing. IMUs can be attached to the seats and occupants to provide tracking of the occupant's motion, supplementing the camera image data processed by computer vision algorithms. The real-time occupant preference information includes real-time data regarding occupant preferences regarding PREACT mechatronic subsystem behavior that impacts motion sickness and productivity.

[0069] This above information can also be used to assess the occupant's productivity state. Productivity assessment refers to a qualitative or quantitative assessment of the occupant's productivity state made by the occupant model (30) (i.e., the PREACT predictive algorithm) using real-time and historical information from the data center (3000, 64), directly from the occupants (33, 60), and from the PREACT mechatronics subsystem (32, 54). To accomplish this assessment, the system can use productivity interface hardware and software, occupant sensors, cabin sensors, or some combination thereof. Examples include cameras that can identify tasks, measure typing speed, measure pages read per minute, etc. The assessment data (which is part of the occupant information data type) can be used to determine appropriate productivity enhancement and motion sickness mitigation strategies. Productivity is inversely correlated with motion sickness, but also includes other factors such as improved ability to perform tasks. Examples include the ability to rearrange in-car seats, VR systems, interactive displays, etc. Different productive tasks may require different types and intensities of intervention. Productive tasks may include writing, reading, typing, and any combination thereof. Additionally, productive tasks may include peaceful activities such as sleeping, meditating, etc. Such productive tasks include not only personal tasks, but also interactive tasks with other vehicle occupants such as business meetings, interactive game playing, among others. The task ID (67) is a unique identifier assigned to a unique productive task, and this determination of which productive task is being performed may be made by a subsystem sensor or user input. Through analysis of aggregate data of all past trips across multiple vehicles and trips, it is possible to infer trends in occupant profiles and classify them based on preferences and sensor information. This allows the system to not only track specific occupant information, but also collect data trends across occupants who share the same demographics with respect to susceptibility to motion sickness. This allows the creation of personalized occupant profiles and trends among other occupants who share similar characteristics. Thus, motion sickness mitigation measures may be tailored to optimize occupant comfort.

[0070] Since the vehicle may be a conventional driver-driven vehicle, additional components of the occupant information (occupant state) may include the driving style and preferences of one or more occupants when the one or more occupants are the drivers (driving occupants) of a conventionally driven PREACT vehicle. The driving occupants may have their own style of steering the vehicle, which may include the specific timing, speed, and steering amount of the vehicle for a given route. For example, when making a right turn, one driver may want to start turning the wheels slowly and early, as opposed to another driver who starts turning the wheels later and faster. The drivers may have their own style of accelerating and braking the vehicle when navigating a route, which may include the timing, speed, and amount of acceleration and braking. For example, a driver may accelerate at the end of a turn or come to a complete stop at a faster speed than another driver. Additionally, the driving occupant may brake earlier and at a slower speed than a driving occupant who brakes harder (i.e., for a shorter period of time, with a higher amount of braking, and brakes later). Driving style may also include vehicle settings such as preferences for vehicle stability management, vehicle traction control, vehicle suspension stiffness, etc. For example, a driving occupant's driving style may include a preference for a stiffer vehicle suspension and / or more aggressive traction control.

[0071] Vehicle Algorithms - Mid-Level Calculations (2000) Vehicle algorithms form the mid-level of the computational architecture of a vehicle equipped with a PREACT system. The mid-level computation includes prediction algorithms such as route and navigation prediction (25) and vehicle model (27). It also includes command generation algorithms such as driving behavior command generation (26). The mid-level computation includes PREACT prediction algorithms such as PREACT mechatronic subsystem model (29) and occupant model (30). It also includes PREACT look-ahead algorithms (or equivalent PREACT command generation algorithms) such as the PREACT mechatronic subsystem command generation (28) algorithm. Command generation (including PREACT look-ahead) algorithms are decision-making algorithms that generate optimal commands (42, 50) that are sent to the low-level computation / control of the various vehicle subsystems. The decision-making and command generation functions are similar in that decisions lead to command generation. For example, the driving behavior command generation (26) algorithm can make a decision to turn the car and generate a corresponding command to turn the car. These commands include both immediate / current and future commands (or predicted commands or simply predictions), and these commands are constantly updated in real time with new information and new predictions. In addition to decision-making algorithms, the mid-level computations also include prediction algorithms that represent models of physical systems, such as a traffic and navigation model (25) for predicting routes and navigation, a vehicle model (27), a PREACT mechatronic system model (29), and an occupant model (30). These prediction algorithms or models predict the behavior of the physical systems when executing the commands generated by the decision-making algorithms (26, 28), and these commands include immediate or current and future predicted commands. For example, based on the commands generated by the driving behavior command generation algorithm (26), the vehicle model (27) can predict the state and behavior of the vehicle that will result from the commands generated by the algorithm (26).

[0072] Forecasting is defined as predicting in advance (probabilistic or deterministic) what will happen in the future, and forecasting includes estimation or forecasting, which are predictions made in the time domain. Predictive algorithms try to make their predictions as close to reality as possible and use all available data to improve their prediction and command generation capabilities. Estimation is defined as using historical data and new information to estimate algorithm or model parameters, settings, etc. Estimation is generally associated with past estimates. Parameters are constantly updated (37, 40, 43, 47, 51, 64), and with each new data collected, decision algorithms and model parameters are iteratively improved and modified to make the predictions of these algorithms and models as close to reality as possible.

[0073] These algorithms and calculations can be performed on-board the PREACT vehicle or off-vehicle, such as on computation servers, computers, and other PREACT vehicles, and can communicate information to the PREACT vehicle. The mid-level calculations are in constant communication with other levels of the system architecture (data centers and / or vehicle subsystems) to ensure that model estimates and predictions are as accurate and precise as possible. The physics model of the mid-level calculations (i.e., predictions and the PREACT prediction algorithms) is described as follows:

[0074] a. Vehicle model (27): This is a model of the vehicle in which the PREACT system is installed. The model is used to estimate the vehicle states for the expected driving behavior on the predicted route. By estimating the vehicle states, a prediction of the vehicle motion and its effect on the occupant states can be estimated. For a specific car with a set of model parameters, the system can simulate how the car interacts with the environmental conditions, taking into account the expected driving behavior of the vehicle. The dynamic variables related to this model are received from the data center (43) and / or from sensors installed on the vehicle (46) and / or directly from user input (60).

[0075] b. PREACT Mechatronics Subsystem Model (29): This is a model of the PREACT mechatronics subsystem (32) installed in the vehicle (31). This model is used to simulate the operation of PREACT mechatronics subsystems such as active seats, active restraints, active occupant stimuli, and active productivity interfaces (mechatronics subsystems including hardware and software) and their effects on the occupants and the vehicle, which are also modeled. This model includes relevant model parameters and dynamic variables received from a data center, from sensors installed in the vehicle, or directly from user input.

[0076] c. Occupant Model (30): This is a model of an occupant (33) seated in a PREACT equipped vehicle (31). The model is used to estimate the occupant's biomechanics and movements (e.g., torso, limbs, head movements, eye tracking, etc.) as well as physiological states (e.g., heart rate, emotional state, motion sickness state, sweating, comfort, etc.). Model parameters are obtained from user input (60), sensors (46) in the vehicle, and any occupant profile information that may be stored in a data center (64).

[0077] d. Route and Navigation Prediction (25): This algorithm predicts a route (or a set of potential routes) connecting the trip origin and the trip destination. Occupant preferences for motion sickness and productivity, as well as vehicle fuel / energy consumption, are estimated for each route and used to determine if a given route is acceptable. Additionally, using information available from the data center, the algorithm can predict traffic conditions, as well as route and road conditions (e.g., construction, bad roads, safety hazards, etc.).

[0078] The decision-making / command generation algorithm of the mid-level computation is described as follows: Vehicle Driving Behavior Command Generation (26): This algorithm is used to determine the actions the vehicle will take to navigate a given route, traffic conditions, and road conditions (if it is an autonomous vehicle or predicted based on past actions by the driver). Additionally, the algorithm can take into account occupant preferences (e.g., acceleration and / or turning aggression) and vehicle conditions (e.g., fuel / energy status, number of occupants, etc.) to determine and refine the driving behavior.

[0079] b. Command Generation for PREACT Mechatronics Subsystem (28): This algorithm uses information from the data center, user input, and predicted states by the models and controllers described above to determine the optimal actions or interventions that can be immediately executed by the PREACT Mechatronics Subsystem (50) in a proactive (or feedforward) manner during the current operation. These actions are performed on a daily basis.

[0080] The above algorithms are explained in detail in the following sections. Route and Navigation Prediction (25) Route and navigation prediction refers to the selection of a path connecting the start and end of a trip. The system uses the input start / end points and any available information about the vehicle environment (37) to generate multiple potential routes for the vehicle. The occupant (33) can communicate the relevant information to the PREACT system (60) using their personal electronic device and / or any interface in the vehicle. The data center records this information (17, 18) and sends it (37) to the route and navigation command generation (25) in addition to other information that may include vehicle and occupant information. The algorithm generates multiple route options connecting the start and end of the trip, and if no explicit end point is defined, the algorithm can try to predict the destination based on aggregated data over time (17, 19, 21, 23) from the data center. Once a set of possible paths is identified, they are evaluated using multiple factors including, but not limited to, the time to reach the destination, fuel / energy consumption, and expected vehicle and occupant conditions. Based on the evaluation, the most optimal route is predicted and sent (38) to the driving behavior command generation (26) which sends the route and driving behavior (42) to the vehicle driving and steering subsystem (31A). Other examples of route information include distance, travel time, road / path type, location of traffic lights and stop signs, etc. In addition to the route connecting the start and end points of the trip, the algorithm also determines navigation information based on information from the data center (37) that allows the algorithm to predict traffic conditions. Other navigation information includes road closures, road conditions, traffic density, traffic light conditions, etc. If the route is changed at any point during the trip, this sequence is repeated for the new start and end points. All updated information is sent (38) to the driving behavior command generation (26) algorithm and to the data center (39). The predictions by this algorithm are reactive and proactive, and include real-time predicted routes and future predicted routes.

[0081] Driving action command generation (26 in Figure 6) Driving behavior commands refer to actions that the autonomous vehicle takes while navigating the route identified by (25). There are multiple ways that the vehicle can steer a given route. For example, based on the occupant's preferences, the vehicle can choose to brake more gently or hard and turn faster or slower. The driving behavior depends on the occupant's preferences, the vehicle, and the PREACT system information (40), and any driving behavior commands generated by the algorithm are sent to the data center (41) and transmitted to the vehicle driving subsystem (42). The driving behavior is optimized by the algorithm to take into account the energy consumption and available energy, the route and navigation, and the occupant's motion sickness and productivity state (i.e., productivity information). If the occupant (33) is engaged in a productive task, the occupant (33) can communicate this information to the data center (60) or can update the data center with the occupant's productivity information as determined by the PREACT mechatronics subsystem (54). The data center sends this information (40) to the driving behavior command generation (26) to influence the generated commands that do not reduce the productivity of the occupants (33) and reduce motion sickness. For example, if changing lanes before turning is expected to reduce motion sickness caused by the turn, a lane change driving behavior can be generated and sent to the vehicle. This algorithm runs constantly and its commands are constantly updated with new information. The commands generated by this algorithm are reactive and proactive (or predicted route and navigation commands).

[0082] Vehicle model (27 in Figure 6) A model of the vehicle is used to predict vehicle states for a given driving behavior command (65) for a specific route (38). The model is used to predict vehicle states including the dynamic behavior of the vehicle, its energy consumption, and its effect on the occupants sitting in the vehicle (and thereby the occupant state). The model may be deterministic and / or probabilistic and includes a set of model parameters for a specific car. The goal of the model is to accurately predict the vehicle state of a given vehicle, and the model parameters are continuously estimated and improved (43) using new information from the data center. Examples of vehicle parameters include suspension stiffness, motor power, vehicle weight, real-time vehicle state, and historical vehicle information, among others. The model predicted vehicle state is sent to the data center (45) and compared with actual sensor information from the vehicle driving subsystem (46), and based on this comparison, updated model parameters are estimated and sent to the vehicle model algorithm (43). This algorithm is constantly performing calculations continuously and its predictions are updated with new information.

[0083] Command generation for the PREACT mechatronics subsystem (28 in Figure 6) The algorithm is a PREACT mechatronics subsystem command, which is an action that the PREACT mechatronics subsystem can act upon to reduce motion sickness and increase occupant productivity. Multiple factors affect the performance of this algorithm, including the expected movement of the vehicle (i.e., predicted vehicle state) (44), all real-time and historical information from the data center (47), the real-time movement of the vehicle and vehicle driving subsystem (56), and the occupant preferences, inputs, and profile (60). For example, tilting the seat to counteract inertial forces caused by turning is known a priori to reduce motion sickness, so this information can be used to command an active seat when motion sickness is expected. However, the exact nature of the tilt, timing, and other factors can be predicted and customized to the individual requirements of a particular occupant. The algorithm generates commands that are future predictions (preemptive actions for the future) in real time. The commands generated by the algorithm are modeled by the PREACT mechatronic subsystem model (29) and their predicted impact on the occupants is modeled by the occupant model (30). The commands are optimized based on multiple factors including the amount of energy needed and available, as well as occupant profile and preferences. Any information regarding the PREACT mechatronic subsystem commands is sent to a data center (49) and combined with information from the PREACT mechatronic subsystem (32) sent to the data center (54) and occupant input (60) to improve the algorithm and its predictions. All updated information is sent (48) to the PREACT mechatronic subsystem model (29), the data center (49), and then sent (50) to the PREACT mechatronic subsystem (32). The commands generated by the algorithm are reactive and preemptive (or predicted route and navigation commands), both in real time and future predicted commands.

[0084] PREACT mechatronics subsystem model (29 in Figure 6) PREACT mechatronic subsystem models are algorithms that model the physical PREACT mechatronic subsystems, including active seats, active restraints, active occupant stimuli, and active productivity interfaces. By creating dynamic models of each of these systems and how they interact, it is possible to predict the state of the PREACT hardware at any point during a journey given a set of driving behaviors. The models can be deterministic and / or probabilistic and contain a set of model parameters for a specific PREACT mechatronic subsystem implementation. The goal of the models is to accurately predict the PREACT mechatronic subsystem states for a given vehicle, and the model parameters are continually estimated and improved (47) using new information from the data center and from the actual PREACT mechatronic subsystems (54). These models are informed by mechatronic subsystem parameters such as active seat suspension stiffness, cabin lighting arrangement, and active restraint configuration, among others. PREACT mechatronic subsystem actions can be targeted to modify occupant dynamics (active seats and restraints), cabin conditions (temperature, lighting and displays), and active occupant dynamics (haptics and displays). This process is constantly ongoing to find the optimal PREACT mechatronic subsystem actions for every anticipated driving behavior. The algorithm is constantly running calculations and its predictions are updated with new information.

[0085] Occupant model (30 in Figure 6) The occupant model is used to predict the occupant state for a given PREACT mechatronics subsystem command (52) using information from the data center (64). The model can be deterministic and / or probabilistic and includes a set of model parameters for a specific occupant. The occupant parameters include gender, age, weight, height, motion sickness susceptibility, productivity preferences, etc. The occupant dynamic variables include the occupant's motion state (head position and orientation), the task being performed, the occupant's motion sickness state, etc. The occupant motion dynamics are calculated using a biomechanical model. The estimated occupant movements can be used as input to a motion sickness estimation model and a productivity assessment model. This process is performed continuously to find the occupant state for all expected driving behaviors. The real-time information of the PREACT mechatronics subsystem (57) and the occupant (60), in addition to data from the data center (64) and other algorithms in the mid-level calculation (52), is used to optimize the model and ensure that its predictions are as close to reality as possible. The algorithm is constantly running calculations and its predictions are updated with new information. Estimated occupant states and model inputs are continuously sent to a data center (55).

[0086] Low Level Calculations (1000) At the low level (1000) of the computational architecture of FIG. 6, there are several vehicle subsystems. These vehicle subsystems include the vehicle driving subsystem (31A), other vehicle subsystems (31B), and the PREACT mechatronics subsystem (32). The computations that take place within these vehicle subsystems and the levels of these vehicle subsystems represent the low level (1000) computations in the computational architecture of FIG. 6. As part of the vehicle subsystems, including the PREACT mechatronics subsystem, there are various sensors that measure vehicle subsystem data (including status). These measurements are used for the low level control / computation of the PREACT mechatronics subsystem. This data / information is also sent to the mid (56, 57) and high (46, 54, 60) levels of computation for decision making and data storage. Data regarding the occupants is collected by wearable sensors or other sensors in the vehicle (e.g., cameras, motion detectors, proximity sensors, non-contact thermometers) that track the occupant's status. Real-time data from the low level computations is also used to improve algorithms in the mid level computations to ensure prediction accuracy. The PREACT mechatronics subsystem is described in more detail below.

[0087] a. Active Restraints (5, Figure 4): Active restraints are mechatronic subsystems that restrain the occupant from moving relative to the vehicle seat (active seat). This function requires changing the length of the restraint or some other means of varying the restraining force applied to the occupant. Active restraints are equipped with sensors that measure the state of motion of the active restraint.

[0088] b. Active Seat (3, FIG. 4): An active seat is a mechatronic subsystem that allows the movement of a vehicle seat relative to the vehicle chassis. This movement can include rotation, translation, or any combination of the above. The movement of an active seat is controlled by mid-level computational algorithms and user input. An active seat is equipped with sensors (e.g., IMU, encoders) that measure the motion state of the active seat (e.g., rotation angle, angular velocity, acceleration, position).

[0089] c. Active Occupant Stimuli (6, FIG. 4): Occupants can be given specific stimuli that trigger a predetermined action or movement of the occupant; these stimuli that trigger active behavior of the occupant are active occupant stimuli. Stimuli can be in the form of sound, light, and haptics (e.g., touch, vibration, puff of air, etc.). These can be customized to suit the preferences of a particular occupant.

[0090] d. Active Productivity Interfaces (7, FIG. 4): Productivity interfaces include a display screen, a touch screen, a keyboard or interactive buttons, an active table or work surface, or any combination thereof. Based on the task ID, the system makes a decision to activate all or some combination of the productivity interfaces to increase the crew's productivity and assist in the execution of the task.

[0091] In addition to the PREACT mechatronics subsystem, the PREACT look-ahead algorithm (10B in FIG. 4, 28 in FIG. 6) may also affect any controllable vehicle subsystem, and is not limited to any vehicle operation (31A) and PREACT mechatronics subsystem (32) previously identified. For example, the mid-level computation may command and control (reactively and proactively) the cabin environment (71, FIG. 7). The cabin environment (71, FIG. 7) includes the climate control, lighting, and audio components of the vehicle. Temperature, airflow, amount and direction of lighting, and type of sound and music may affect occupant comfort and productivity. The cabin environment (71, FIG. 7) may be controlled in coordination with all other vehicle subsystems within the low-level computation of the architecture. It is conceivable that the PREACT look-ahead algorithm (10B) or the PREACT mechatronics subsystem command generation algorithm (28) may control (reactively and proactively) any vehicle subsystem that is currently present in the vehicle or that may be added later. For example, if a new vehicle subsystem (73, FIG. 7) is invented or added to the vehicle (e.g., as an aftermarket add-on) after the vehicle is manufactured, this vehicle subsystem can be controlled by the PREACT algorithms. The PREACT mechatronics subsystem is described in more detail below.

[0092] Active restraint (5 in Figure 4) The active restraint subsystem is a mechatronic subsystem that restrains an occupant to a vehicle seat (e.g., an active seat). The type of restraint can vary and can be a multi-point, three-point, lap restraint, or some combination thereof. The restraint straps are attached to actuators that can be controlled by varying the length of the straps to adjust the tension of the restraint (i.e., restraining force). By adjusting the restraining force, the occupant can be tilted in the direction of a turn or towards the seat when the vehicle is braking. The tilt of the occupant includes the tilt of the occupant's torso, head, neck, or other limbs. The active restraint may use sensors that track the position and tension of the straps (i.e., restraining force). Additionally, occupant preferences and inputs can control the behavior of the active restraint to meet individual comfort, productivity, and motion sickness needs. Data from the occupant inputs and active restraint sensors is transmitted to a data center (54) and used by mid-level control algorithms. Active restraint parameters include number and location of anchor points, actuator power, restraint (e.g. strap) width and stiffness, etc. Active restraint dynamic variables include restraint length, restraint tension, restraint latch state, etc.

[0093] The active restraints can include a variety of hard or soft or hybrid braces, restraints, harnesses, and seat belts. An example of a multi-anchor point harness (i.e., seat belt) for a forward facing occupant is shown in FIG. 8. Ends A1, A2, B1, B2 are all active, i.e., retracted into the seat via appropriate actuators, thereby selectively tightening certain portions of the seat belt. In one example, when the vehicle brakes (i.e., slows down), sections A1 and A2 are pre-activated / activated / retracted, thereby supporting the occupant by holding sections A1 and A2 down in anticipation of the forward lunge that will occur when the vehicle actually slows down. Alternatively, if the vehicle is predicted to turn right, seat belt sections A2 and B2 of the active restraint system are pre-activated / activated / retracted, anticipating or restraining the occupant in the direction of the turn in anticipation of the centrifugal effect pushing the occupant out of the turn, thus mitigating the effects.

[0094] Additional elements of the active restraint subsystem may include a neck support or head restraint with active features that can preemptively bias the occupant's head / neck in one direction or the other in anticipation of an acceleration or deceleration event.

[0095] Active seat (3 in Figure 4) An active seat is a vehicle seat in which a vehicle occupant (33) sits or is supported. An active seat provides relative motion between the seat and the vehicle chassis. This motion can include rotation (e.g., pitch, roll, yaw), translation (e.g., pitch, sway, surge), or some combination thereof. The active seat and active restraints fit together such that an occupant sits comfortably restrained in the active seat and does not have significant relative motion between themselves and the seat. The active seat motion can be controlled by actuators (e.g., motors, pneumatics, hydraulics, etc.) and measured by sensors (e.g., encoders, IMUs, force and torque sensors, etc.). The active seat motion can be initiated by commands from mid-level computational algorithms and controlled (i.e., subsequent commands) by low-level computation. As part of the occupant information, specifically occupant preferences, the occupant can select the intensity of the active seat motion. Depending on their preferences, the PREACT look-ahead algorithm can reduce or increase the range of movement, speed, acceleration, etc. of the look-ahead commands (50) sent to the active seats. Data from the active seats' sensors is sent to a data center via some network communication. The active seats can also move to allow occupants in the vehicle to face each other for meetings, discussions, and / or other productive activities. The active seats can include embedded sensors that measure occupant status, including any physiological and motion information. Active seat parameters include seat length, height, width, range of active seat movement, actuator type and power, etc. Active seat dynamic variables (i.e., state) include the amount of reclining, tilting, or any other movement, the speed and acceleration of the movement, and any information measured by the sensors.

[0096] Active occupant stimulation (6 in Figure 4) Occupants can be given specific stimuli that trigger desired occupant actions or movements; these stimuli that trigger active occupant actions are active occupant stimuli. The stimuli can be in the form of sound, light, and haptics (e.g., touch, vibration, puff of air, etc.). The stimuli can be a single type or a combination of stimulus options. The specific combination of active occupant stimuli may be customized by the "PREACT Mechatronics Subsystem Command Generation" algorithm (28) for each occupant based on occupant information (e.g., occupant sensitivity, sensitivity, or preferences).

[0097] Audio stimuli can be provided by audio components in the vehicle cabin (e.g., dedicated speakers and / or speakers of the vehicle entertainment system) and occupant personal devices (e.g., laptop, smartphone, smartwatch, tablet, etc.). Audio stimuli can be different types of sounds (e.g., beeps or chirps, etc.) and / or melodies and music. The purpose of the audio stimuli is to trigger a desired response from the occupant. For example, if the vehicle is about to turn right, a speaker on the right side of the cabin can beep, so that the occupant can turn his head in the direction of the sound. In another example, if the vehicle is about to turn left, the occupant can tilt (e.g., his head, torso, body, or other limbs) in the direction of the turn. Light stimuli can be provided by light and display components in the vehicle cabin as well as occupant personal devices. The purpose of the light stimuli is to trigger a predictable / desired response from the occupant. For example, if the vehicle is about to stop, a light in the vehicle can flash red, which the occupant can interpret as the vehicle slowing down, and can use that information to brace himself. Haptic stimuli can be provided by active seats, active restraints, the occupant's personal devices, devices embedded in the occupant's clothing / outfit (e.g., neck collar, headband, wristband, etc.), or by dedicated haptic devices in the vehicle cabin. For example, if the vehicle is about to turn left, the haptic device in the active seat can trigger a vibration that can be felt by the occupant's left leg, which can be interpreted by the occupant to prepare for the vehicle turning left. In addition to haptic devices, sensory stimuli can be provided by the air conditioning by sending a directional puff of air. The operation of the active occupant stimuli, the occupant's responses and preferences, and any associated sensor information are transmitted to mid-level control algorithms and data centers to affect future behavior.

[0098] Active Productivity Interface (7 in Figure 4) The active productivity interface works in conjunction with other active subsystem parts of the PREACT system. When the system determines or the occupant indicates that they are performing a task with a task ID (67, FIG. 7) triggers the active productivity interface. For example, if the occupant is reading a book, the system or the occupant themselves can indicate that they are performing this activity, and the system recognizes the task via its task ID (67, FIG. 7) and triggers the appropriate action in the active productivity interface. For a particular task ID (67, FIG. 7), only active seat, active restraint, active cabin environment, and active occupant stimulation interventions are triggered, but for other task IDs corresponding to occupants performing productive tasks, the active productivity interface may also be triggered. In one embodiment, the productivity interface may be composed of the following components: (1) an active display, (2) an active work surface, and (3) an active user input / keyboard (FIG. 9). The active display is the display that the occupant uses to perform a productive activity. The display position (and movement) can be controlled (33) by the occupant (60) and / or the PREACT mechatronics subsystem command generation (28). The display can serve multiple roles, such as being a touch screen that can be used for both user input and information display. The display can actively move (i.e., be commanded / controlled) so that the occupant can remain engaged in productive activities despite the movement of the vehicle. Also, as the occupant moves around the cabin, the active display can reorient itself for easy occupant access. Sensors (including cameras) within the cabin can determine the occupant's orientation and line of sight and use that to reposition the active display. An active work surface is a table-like device that the occupant can use when they are writing, sketching, or performing any activity that requires the occupant to rest their hands on a table while seated inside the vehicle. The work surface is compatible with the user input and active display components. It may be physically attached to one or both of those components.The work surface can be actively moved (i.e., commanded / controlled / adjusted) so that the occupant can remain engaged in productive activities despite the vehicle's motion. User input is a keyboard type device with buttons, touch screen, sketch pad, or any other type of user input device that allows the occupant to communicate some intent or action to the computer. Any sensor data related to the operation and components of the active productivity interface is sent to mid-level control algorithms and data centers to affect future operation. Parameters of the active productivity interface include physical dimensions of the display, work surface, user interface / keyboard, display, range of work surface motion, etc. Dynamic variables of the active productivity interface include actual movement (position, speed) of the display, work surface, and keyboard, display state (brightness, color), keyboard / user interface state, etc.

[0099] Vehicle interior environment (71 in Figure 7) The active cabin environment refers to the environment in the vehicle cabin where the occupants are seated. The cabin environment includes multiple factors that make up the cabin atmosphere, including heating and air conditioning, lighting and visual displays, and the audio components of the vehicle. By actively controlling and regulating the above, the comfort, productivity, and motion sickness of the occupants can be influenced.

[0100] The heating and air conditioning system helps to control the temperature in the vehicle cabin by varying the temperature of the air, the direction of the airflow, and the speed of the airflow. Additionally, the air conditioning system can also introduce scents into the airflow to create a pleasant aroma. The air can also be filtered to reduce and purify particles and other foreign matter from the air. The lighting and visual display system helps to display information for the occupants and control ambient lighting. The amount of lighting can be controlled by varying which lights are turned on and by controlling the intensity of the lights. Displays can be used to provide relevant information to the occupants. The amount of light and information that may be available to the occupants can affect their comfort and productivity. The audio system controls the sound and auditory environment of the vehicle cabin. This can include the type and volume of sound. This also includes entertainment systems that play music and other sounds as well as the occupants' personal devices (e.g., laptops, smartphones, smart watches, tablets, etc.). The system can leverage the lights, displays, and audio devices within the vehicle, as well as personal electronic devices belonging to the occupants (e.g., laptops, tablets, smartphones, etc.) by connecting and communicating with the personal devices via wireless network communication (e.g., WiFi, Bluetooth, NFC, etc.) or wired connections. The operating conditions of the active cabin environment can be transmitted to a data center and stored for future use.

[0101] PREACT system description in action Here we describe the PREACT system (at all computational levels) while operating in a vehicle. This description combines the operation and functionality of the various levels of computation in the PREACT architecture and how they come together to mitigate motion sickness and increase occupant productivity. The detailed description is presented chronologically and divided into three phases: (1) before the trip begins and before the vehicle moves, (2) during the trip, any time after the trip begins and before its end, and (3) after the trip ends and the vehicle has stopped moving. Although this description is presented in the context of an autonomous vehicle (AV), it is relevant to any passenger ground vehicle that may be manually driven or may have any of various levels of autonomy.

[0102] Before moving - before operation begins Before the trip begins, the AV is likely to be stationary and the vehicle driving subsystem (31A) is likely to be partially powered off. For example, the engine of an autonomous vehicle is unlikely to be powered. Other vehicle subsystems, such as the PREACT mechatronics subsystem (32), can continue to operate and perform computations, exchange information (42, 50, 56, 57) with mid-level computations, and transmit information (46, 54, 60) to higher-level computations. To maintain communication with all computation levels, any of the data communication methods previously mentioned can be used (wired communications such as cable and fiber, and wireless communications such as cellular, wireless, satellite, microwave, radio frequency, LAN, Bluetooth, WAN, etc.). In addition, the occupant's electronic devices (e.g., smartphones, smart watches, or other mobile devices, or other wearable devices) can also be used to collect and transmit information (60). The occupant (33) can use these devices to provide information about the upcoming trip, which can include information about any data type (e.g., vehicle, occupant, route and traffic, and PREACT system information).

[0103] If the occupant (33) does not have an occupant profile that is part of the occupant information (23, 24) in the data center, electronic devices in the vehicle and / or electronic devices can be used and / or the necessary information can be extracted from the occupant social media or other accounts (61) to build the occupant profile. For example, occupant parameters such as gender, age, height, and weight can be extracted (with appropriate permission) from their social media or fitness tracking applications. Also, if the occupant has traveled in other vehicles (35) or shares characteristics (e.g., motion sickness susceptibility, gender, age, productivity preferences, etc.) with other occupants of other vehicles (35), that information can also be used by the data center (62) to build the occupant profile (23, 24). Information such as motion sickness susceptibility and occupant (33) preferences for PREACT mechatronic subsystem (29, 32) operation can be determined via surveys and subsequent ongoing occupant feedback (60) accumulated over multiple trips in the PREACT vehicle. For example, the occupant (33) can use their personal electronic device and / or any interface in the vehicle to indicate their motion sickness susceptibility, their preferences for PREACT mechatronic subsystem operation. These preferences can include the intensity, timing, and amount of subsystem operation (e.g., active seat subsystem movement). Information regarding additional occupants and / or any other cargo the PREACT vehicle may be carrying can also be communicated to the data center.

[0104] Even before the trip begins, calculations can be performed at all levels of the system architecture. For example, in the mid-level calculations, the algorithms for determining the route and navigation (25) can constantly update their outputs based on new information (37) from the data center. Using information about the PREACT vehicle (43, 46), the mid-level calculations can optimize the command generation algorithms (25, 26, 28). Based on the route and traffic information (37), such as distance and duration, as well as the vehicle, such as the maximum available power / energy (40, 43, 47, 51, 64) of the PREACT mechatronics subsystem of the mid-level calculation algorithms, they can appropriately modify their output commands (48) to maximize effectiveness while minimizing power consumption. The calculations can also be used to inform the occupants of relevant information. For example, if the vehicle does not have enough energy / power to complete the trip, the data center can inform the occupants (33) (60) via their personal electronic devices or interfaces in the vehicle (33) that the vehicle needs more energy / power. While the occupant (33) may or may not explicitly provide the data center and / or vehicle algorithms with the origin and destination for the trip, the route and navigation prediction (25) algorithms may determine this information using various sensors and other accessible sources of information (37). For example, the data center may use information from a GPS sensor from the vehicle driving subsystem (31) to detect the current location of the PREACT vehicle, which is likely the starting location of the trip. The algorithms for predicting route and navigation (25) may also use historical information (17, 19, 23) to determine likely destinations based on the occupant's past trips given dates, times, and other factors. The algorithms may also use up-to-date information about routes and traffic (18, 37) in combination with historical trends (17) to predict traffic and optimal routes (38) for the next trip.

[0105] Even as a trip is initiated and the vehicle is moving, calculations may occur at all computational levels within the system architecture. These calculations can be used to inform the behavior of not only the PREACT vehicle (primary vehicle), but also other PREACT vehicles that may be on the roadway near the primary vehicle. For example, if a PREACT vehicle (primary vehicle) is parked on the side of the road, its on-board sensors (31A, 31B) and computer can still provide information to the mid-level (56) and high-level (46) calculations, and this information and calculations can be used to inform the behavior (42, 50) of other PREACT vehicles. The vehicle subsystems (low level calculations) of the primary vehicle can be used to assist other PREACT vehicles nearby. For example, if a PREACT vehicle (primary vehicle) is moving but has lost communication with the data center or vehicle algorithms, the vehicle can use V2V or V2I communication to communicate with another PREACT vehicle nearby and maintain a communication link with the data center and vehicle algorithms. Once the occupants enter the vehicle and the vehicle begins to move, the trip begins, and this phase of the trip is described in the next section.

[0106] On the move - driving Here, one or more occupants are seated in the PREACT vehicle and a journey has begun. The vehicle driving subsystem (31A) implements the driving behavior commands (42) generated by the driving behavior command generation (26) for a given route (38) predicted by the route and navigation algorithm (25). The algorithms (25, 26) receive the latest real-time and historical information (37, 40) from the data center. This information includes route and traffic information (17, 18), vehicle information (19, 20), PREACT system information (21, 22), and occupant information (23, 24). In addition to being sent (42) to the vehicle driving subsystem (31) and the data center (41), the driving behavior commands are also sent (65) to the vehicle model (27). The vehicle model is updated and kept up to date with new information from the data center (43) and this model is used to predict the vehicle state. These model predicted vehicle states are sent to a data center (45) along with real-time vehicle states (46) from the vehicle driving subsystem (31). Both of these data are used to ensure that the vehicle model predictions are close to reality by estimating improved vehicle model parameters. The predicted vehicle states are sent to a PREACT mechatronics subsystem command generation algorithm (28) (44). The PREACT mechatronics subsystem command generation algorithm (28) uses information from the data center (47) including the model predicted vehicle states (44), the real-time vehicle states (56), as well as historical and real-time information on occupant preferences (23, 24), PREACT system information (21, 22), etc. The algorithm predicted PREACT mechatronics subsystem commands are sent to a PREACT mechatronics subsystem model (29) that predicts the mechatronics subsystem states (48). The mechatronic subsystem model (29) is continually improved with new information from the data center (51) as it continually estimates and refines model parameters for more accurate predictions. The predicted state of the mechatronic subsystem model (29) is transmitted to the data center (53) for addition to the information collected by the data centers (21, 22).The predicted states of the mechatronics subsystem model (29) are sent (52) to an occupant model (30). The occupant model (30) represents the physical and physiological characteristics of an occupant (33) in an autonomous vehicle. The occupant model (30) predicts the occupant states (e.g., motion sickness, comfort, productivity, dynamics, movement, etc.) of the occupant for a given route and navigation (38), driving behavior (65), and PREACT mechatronics subsystem behavior (48). The occupant model (30) is continuously improved with new information from the data center (64), real-time information from the occupants (60, 64), and real-time sensor information from the vehicle subsystems (57). The predicted occupant states of the model (30) are sent to the data center (55) to become part of the data center's occupant information (23, 24). Information from the vehicle algorithms (39, 41, 45, 49, 53, 55) and vehicle subsystems (46, 54, 60) becomes part of the data center information (17-24).

[0107] Once the vehicle algorithms have optimized those commands, those commands are sent to the vehicle subsystems (42, 50). The optimized real-time and predicted commands generated by the route and navigation (25, 38) and driving behavior algorithms (26, 65) are sent (42) to the vehicle driving subsystem (31A). The state of the vehicle driving and steering subsystem (31A) is sent (58) to the PREACT mechatronics subsystem (32). The PREACT mechatronics subsystem (32) implements the commands using information from the vehicle driving subsystem (58) and commands from the PREACT look ahead algorithms (50). The mechatronics subsystem (32) performs actions (59) that affect the occupants (33). For example, the active seat subsystem (which is part of the PREACT mechatronics subsystem (32)) can sway and tilt based on commands from the PREACT preemptive algorithms (50) and information from the vehicle driving subsystem (58), which affects the position, comfort, and other occupant conditions of the occupant (33) within the vehicle. The occupant (33) can communicate their preferences and / or adjust the operation of the vehicle algorithms using interfaces within the vehicle and their own personal electronic devices to communicate their preferences and / or adjust the operation of the vehicle algorithms.

[0108] The route and traffic information (17, 18) is constantly updated as new information is collected from sensors (46, 54, 60) in the vehicle subsystem, other PREACT and non-PREACT vehicles (35, 62), infrastructure sensors (36, 63), and other databases (34, 61). At any given moment during the trip, the vehicle may be moving or may be temporarily stationary at a stop sign, traffic light, etc. Using the best possible information (37, 40, 43, 47, 51, 56, 57, 64), a mid-level calculation can predict the optimal route and traffic conditions for the trip (25, 38). From time to time, as new information is found, the route may be changed. For example, if new information from other vehicles (62) or infrastructure sensors (63) indicates that traffic conditions have changed along the route, the vehicle may change its route (38) to avoid increased traffic. Multiple data streams may influence route decisions at mid-level calculations, such as, but not limited to, occupant preferences (23, 24) for travel time and route (e.g., avoiding highways or side streets), motion sickness mitigation preferences (21, 22) (e.g., routes with more curves and / or starts and stops cause more motion sickness), and productivity preferences (e.g., bumpy roads make it difficult to perform productive tasks such as reading or typing on a keyboard). Similarly, vehicle operation (26, 40) decisions may also be influenced by the above data streams. For example, if an occupant is highly susceptible to motion sickness and therefore prefers strong motion sickness mitigation interventions, the vehicle operation (26, 40) may reduce the severity of vehicle acceleration, braking, and steering for a given route. The PREACT operation (28, 48) decisions for a given route (38) and occupant (33) are optimized and predicted for the entire duration of the trip.

[0109] At every moment, new and improved information improves the determination of future PREACT mechatronic subsystem actions (28, 48). By combining real-time actions with predicted future actions, the PREACT mechatronic subsystem (32) can blend and combine actions to smoothly transition from one command to the other. For example, if the vehicle algorithms (25, 26, 28) know that a left turn is coming, the active seat subsystem (which is part of the PREACT mechatronic subsystem (32)) can begin to gradually tilt into the turn before the turn arrives, and the movement can be slow and smooth to minimize disturbance to the occupant (33) and allow the occupant (33) to adjust to the tilt / movement of the active seat (32). Similarly, if the productivity interface subsystem (32) knows that an occupant (33) is on a video conference and the active seat (32) is tilting / moving to account for a vehicle turn, the camera and display of the productivity interface subsystem (32) can move in unison, thereby reducing disruption to the occupant's (33) productive tasks while still mitigating motion sickness.

[0110] The various PREACT mechatronics subsystems (32) can also work together to achieve optimal motion sickness and productivity occupant states. For example, while driving over rough roads, instead of the active seat (32) continuously tilting, while the vehicle is rocking back and forth intermittently, the optimal action may be to simply tighten the active restraints (32) to hold the occupant's (33) body more snugly in the seat, which can help the occupant (33) be more comfortable than the active seat alone. Similarly, if the vehicle is changing lanes, the PREACT active occupant stimulation subsystem (32) can notify the occupant (33) of the lane change and, together with the active seat and active restraints, reduce motion sickness. The PREACT system must be robust to sudden and unexpected changes to the route and traffic (17, 18), the vehicle (19, 20), the PREACT mechatronics subsystems (21, 22), and the occupant states and information (23, 24). This is why data flows between all computational levels, and even in the absence of real-time data, historical data and trends can be used to make best guesses and predictions to ensure optimal or near-optimal system performance. For example, if real-time information is not available on routes and traffic (18) for some reason (e.g., communication failure, lack of sensors, etc.), the mid-level computation can call up all relevant historical data (17, 19, 21, 23) from the data center and use this to make predictions and estimates of real-time conditions. Not only can this prediction and estimation be used to determine future commands / actions, but prediction and look-ahead algorithms (25-30) can also try to predict current and future conditions and take look-ahead actions when no real-time information or only partial real-time information is available. Since all levels of computation rely on large amounts of data, an additional challenge can be dealing with erroneous or outdated data that is not supported by any historical data or past trends.For example, while a PREACT vehicle is moving on its journey, an accident may occur very suddenly, which does not directly involve the PREACT vehicle, but affects the driving behavior (65), the route (38), and the occupant response (60). The accident may very suddenly change the traffic situation along the route (38), and may also require a change of route due to road closures. In the case of such a sudden event, the PREACT vehicle may not have prior knowledge and must respond in real time. However, other PREACT vehicles (which may be several seconds, minutes, or hours behind the PREACT vehicle that first witnessed the accident, thereby recording the data related to the accident (46) and sharing it at all computation levels, including with the data center), may be notified of the change of route (38) and navigation by the data center. Another example of a sudden event is when a PREACT vehicle experiences a tire blowout or a sudden loss of pressure in one or two of its tires; this sudden change cannot be predicted or recognized a priori, but affects driving behavior (65, 42) and PREACT subsystem behavior (48, 50).

[0111] In some cases, the sensor-collected information (46, 54, 56, 57) may be limited and the occupant (33) may have to self-report new information or data to all computational levels. For example, even if the PREACT mechatronics subsystem (32, 59) uses various sensors and cameras (i.e., imaging devices) to monitor the occupant (33)'s condition, the data captured by the sensors may not fully and accurately reflect the actual occupant's condition. In this scenario, the occupant (33) may self-report any information (60), such as the current comfort level (i.e., comfort state), updated preferences for motion sickness mitigation and / or productive interventions. At any time during the trip, the occupant (33) may control and adjust the PREACT mechatronics subsystem (32, 50) behavior using his / her electronic device or any interface in the vehicle. These on-the-fly changes and indications of preferences represent the individual customized requirements of the crew member (33), and these changes augment the crew member profile that is stored in the data center as part of the crew member information data streams (23, 24). In particular, in the case of the productivity interface (32), the crew member (33) can customize the productivity interface to suit their individual work style, for example, if the crew member (33) is more likely to read during their morning commute, the productivity interface (part of 32, the PREACT mechatronics subsystem) can prioritize reading tasks for that particular crew member (33).

[0112] The above system behavior applies to all types of driving, including city, highway, and off-road driving. A trip ends when the vehicle reaches its destination.

[0113] After moving - After driving Once the trip is complete, the vehicle reaches its destination. Data collected on the trip is transmitted to and stored in the data centers (46, 54, 60) and becomes part of the data center's historical data (17, 19, 21, 23). A stationary PREACT vehicle can continue to provide computational assistance to other vehicles nearby, as well as any sensor information it may be able to gather from its surroundings. With every trip, intermediate levels of computation improve its prediction and estimation capabilities.

[0114] Detailed explanation of the PREACT algorithm The PREACT look-ahead algorithm (FIG. 4, block 10B) consists of the PREACT mechatronic subsystem command generation algorithm (FIG. 6, 28). The PREACT predictive algorithm (FIG. 4, block 10A) consists of the PREACT mechatronic subsystem model (FIG. 6, 29) and the occupant model (FIG. 6, 30). These algorithms are predictive or look-ahead control algorithms, embodiments of which are described in detail below. More specifically, the PREACT mechatronic subsystem command generation algorithm (28) is a look-ahead control or look-ahead algorithm, whereas the occupant model (30) and the PREACT mechatronic subsystem model (29) are predictive algorithms.

[0115] Occupant Model Algorithm (30) The following algorithms are predictive in nature in that they use a model of the occupant to predict future occupant states. There are five predictions made by the occupant model: (1) occupant motion sickness susceptibility, (2) occupant motion sickness, (3) occupant comfort, (4) occupant productivity assessment, and (5) occupant task identification. These predictions and their mechanisms are described below.

[0116] Passenger susceptibility to motion sickness The algorithm predicts the susceptibility of a passenger to motion sickness. Motion sickness susceptibility is defined as the likelihood that a passenger will experience motion sickness for a particular motion of the vehicle and the type of activity being performed by the passenger. In one possible embodiment, three classes of motion sickness susceptibility are defined: Class 1 is a passenger with a high probability of motion sickness, Class 2 is a passenger with an average probability of motion sickness, and Class 3 is a passenger with a low (lower than average) probability of motion sickness. Passengers with a motion sickness susceptibility of Class 1 mean that they are more sensitive to motion sickness-inducing stimuli (i.e., vehicle motion, performing productive tasks, etc.) and are more likely to experience motion sickness faster and / or more intensely than the average passenger. Passengers with a motion sickness susceptibility of Class 3 mean that they are less sensitive to motion sickness-inducing stimuli and are more likely to experience motion sickness slower and / or less intensely than the average passenger. Occupants with class 2 susceptibility to motion sickness are occupants with average susceptibility to motion sickness. Average susceptibility to motion sickness can be determined by experimentation and user surveys. In other embodiments, there may be more classes or different classes defined to capture susceptibility to motion sickness.

[0117] In one possible embodiment, a classification machine learning algorithm can be used to predict the occupant's susceptibility to motion sickness. Furthermore, supervised or semi-supervised algorithm training can be utilized. Certain types of classification algorithms can be used, such as neural networks and / or Bayesian classifiers. For example, when using a Bayesian classifier for a given set of inputs to the algorithm (i.e., the occupant's gender, age, height, weight, self-reported susceptibility to motion sickness, physiological information such as heart rate and sweating), the algorithm attempts to predict the probability that the occupant falls into one of the defined classes of susceptibility to motion sickness. In another embodiment, if the occupants share the same attributes, such as gender, age, height, and weight, cluster analysis can be used to group the occupants into a particular class of susceptibility to motion sickness. In one embodiment, in addition to the algorithm being trained on experimental input data, the algorithm can also be trained on data collected during daily operation of the PREACT system and data collected from the occupants.

[0118] The algorithm can accept quantitative inputs. Inputs such as age, weight, height, and quantitative user-reported survey information can be used as is without modification. Inputs that are not quantitative in nature, such as gender, qualitative responses to self-reported surveys, can first be converted to quantitative values, e.g., gender can be coded using one-hot coding or other equivalent quantitative coding methods. In one embodiment, the algorithm obtains occupant parameters such as height, age, weight, average heart rate, gender, and the occupant's self-reported survey responses to questions about the occupant's past experiences with motion sickness. The algorithm should have been trained on similar inputs.

[0119] Passenger motion sickness The motion sickness state of a passenger is quantified and a motion sickness score is used to quantitatively represent the motion sickness of the passenger. The algorithm predicts the motion sickness score based on a set of passenger parameters and dynamic variables. The inputs to the model are the passenger's physiological state, motion dynamics, visual-vestibular impingement level and profile. In one embodiment, the output is a motion sickness intensity (MSI) on a scale of 0 to 100. MSI is defined in the literature as the percentage of people who vomit under a given motion input frequency and magnitude applied in a given time interval. The algorithm is trained using a previous dataset that includes measurements of the aforementioned inputs along with self-reported or calculated MSI. This allows for correlation between the inputs and the predicted motion sickness score. To predict the output motion sickness score, supervised / semi-supervised regression machine learning algorithms such as linear regression, polynomial regression, ridge regression, principal component analysis, among others, can be used.

[0120] For example, an increase in heart rate is known to be positively correlated with motion sickness. Thus, the higher the heart rate value, the higher the motion sickness score is expected to be. To understand the nature and strength of such correlation, a predictive algorithm can be used. Given the previously recorded heart rate and corresponding motion sickness score data, the algorithm can determine what is the best-fit curve that allows the determination of the motion sickness score given the heart rate value. This best fit can be achieved using the regression algorithm described above. Obviously, motion sickness is not only a function of heart rate. Other parameters that correlate with motion sickness include the experienced vestibular acceleration, the occupant's susceptibility to motion sickness, and cold sweating, among others. Thus, the predictive algorithm must take these other variables into account, which can be done using multiple regression analysis.

[0121] Occupant comfort The algorithm predicts an occupant comfort score based on a set of occupant variables. It is similar to motion sickness prediction algorithms in the sense that the output is a quantifiable continuous variable determined based on multiple input variables. In one embodiment, the occupant comfort score is a continuous variable proportional to a baseline comfort score of 100. The baseline comfort score corresponds to the comfort experienced by an occupant in a stationary vehicle without an active system. For example, a comfort score of 200 means that the occupant is twice as comfortable as an occupant in a stationary vehicle without an active system.

[0122] Inputs to the algorithm include occupant self-reported comfort, occupant kinematics, occupant physiological state, occupant profile, and cabin conditions. The algorithm is trained using a previous data set that includes measurements of the aforementioned inputs along with self-reported or calculated occupant comfort scores. This allows for correlation between the inputs and predicted occupant comfort scores. Supervised / semi-supervised regression machine learning algorithms such as linear regression, polynomial regression, ridge regression, principal component analysis, among others, can be used to predict the output comfort score.

[0123] For example, occupant comfort as a function of vehicle interior temperature is known to have an inclusive maximum that depends on the occupant's preference for temperature. Thus, temperature values ​​higher or lower than the occupant optimum temperature point are expected to result in a lower occupant comfort score. To understand the nature and strength of such correlation, a predictive algorithm can be used. Given previously recorded vehicle interior temperature and corresponding comfort score data, the algorithm can determine what is the best-fit curve that allows for the determination of the occupant comfort score given the vehicle interior temperature value. This best fit can be achieved using the regression algorithm described above. Clearly, occupant comfort is not the only function of vehicle interior temperature. Other parameters that correlate to occupant comfort include experienced head acceleration, heart rate, visual-vestibular impingement level, among others. Thus, the predictive algorithm needs to take these other variables into account, which can be done using multiple regression analysis.

[0124] Crew Productivity Assessment The algorithm predicts an occupant productivity score based on a set of occupant variables. This is similar to the motion sickness prediction algorithm in the sense that the output is a quantifiable continuous variable determined based on multiple input variables. In one embodiment, the productivity score is a continuous variable proportional to a baseline productivity score of 100. The baseline productivity score is equivalent to the productivity that an occupant would have in a stationary vehicle without an active productivity system. For example, if an occupant takes twice as long to accomplish the same task compared to an occupant in a stationary vehicle without a productive performance active system, the productivity score would be 50. Note that a score above 100 is acceptable because active systems can increase productivity.

[0125] Inputs to the algorithm include the occupant's self-reported productivity, the occupant's physiological state, the occupant's kinematics, the occupant profile, the identification of the task being performed, and a quantifiable assessment of the task being performed. Examples of quantifiable assessments of the task being performed include, among others, words per minute for a reading task, and minutes spent in deep sleep for a sleep task. The algorithm is trained using a previous data set that includes measurements of the aforementioned inputs along with self-reported or calculated occupant productivity scores. This allows for correlation between the inputs and the predicted occupant productivity scores. Supervised / semi-supervised regression machine learning algorithms such as linear regression, polynomial regression, ridge regression, principal component analysis, among others, can be used to predict the output productivity score.

[0126] For example, it is known that an increase in the number of minutes spent in deep sleep is positively correlated with sleep productivity score (or sleep quality). Thus, the higher the value of minutes spent in deep sleep, the higher the sleep productivity score is expected to be. To understand the nature and strength of such correlation, a predictive algorithm can be used. Given the previously recorded minutes spent in deep sleep and the corresponding sleep productivity data, the algorithm can determine what is the best-fit curve that allows the determination of the productivity score given the value of the number of minutes spent in deep sleep. This best fit can be achieved using the regression algorithm mentioned above. Obviously, sleep productivity is not only a function of minutes spent in deep sleep. Other parameters that correlate with sleep productivity score include, among others, the total minutes spent sleeping, the frequency of movement during sleep. Therefore, the sleep productivity prediction algorithm needs to take these other variables into account, which can be done using multiple regression analysis. It is important to note that the productivity score depends on the nature of the task being performed. The given example provides an insight into sleep productivity assessment. However, other tasks will have different productivity scores associated with different input variables.

[0127] Crew Task Identification The algorithm predicts the productive tasks being performed by the occupants in the vehicle. A productive task is defined as any activity that the occupant is involved in, such as reading, writing, typing, watching videos, video conferencing, or any combination thereof. In one possible embodiment, we define four classes that capture the productive tasks of the occupants: class 1 corresponds to reading newspapers / paper documents, class 2 corresponds to writing on paper / tablet, class 3 corresponds to typing on a keyboard / touch screen, and class 4 corresponds to watching videos on a screen (i.e., mobile phone, laptop, productivity display). These classes can be quantitatively organized using one hot coding or an equivalent quantitative coding method. These outputs are also called task IDs.

[0128] The algorithm receives input from various sensors in the vehicle, such as video cameras, LiDAR, motion sensors, and may also receive direct input from the occupants. In one embodiment, the algorithm may receive input from one or more RGB color video cameras in the vehicle and from the user's self-reported tasks that the user is performing. The information from the RGB color video cameras is converted into a vast matrix with numerical values ​​that correspond to the information in each pixel of the video / image. This matrix is ​​the quantitative input to the algorithm. The user's self-reported tasks may be reported by pressing a button on a user interface and / or touch screen in the vehicle. Once the user self-reports the task, the algorithm may use the video information to validate this and may also label the video information for the purpose of training the algorithm for continuous improvement.

[0129] In one possible embodiment, machine vision and classification machine learning algorithms can be used to predict the productive tasks being performed by the occupants in the vehicle. Furthermore, supervised or semi-supervised algorithm training can be utilized. The algorithm can utilize space-time methods, where the activity is represented by a set of spatio-temporal features or trajectories that can be extracted from the video information. For example, using the video information, the algorithm can determine the trajectory of the occupant's hands in space and time, and use that to determine whether the occupant is typing or writing. In one embodiment, in addition to the algorithm being trained on experimental input data, the algorithm can also be trained on data collected during the daily operation of the PREACT system and data collected from the occupants.

[0130] Command generation algorithm for the PREACT mechatronics subsystem (28 in Figure 6) The PREACT mechatronic subsystem command generation algorithms are further divided into three algorithms. All of these algorithms are for pre-emptive control in that they use real-time and predicted states of the route and traffic, vehicle, PREACT mechatronic subsystem, and occupants as inputs to generate pre-emptive commands and decisions. In addition to pre-emptive commands, they also use real-time information to generate immediate current commands. In summary, commands are generated over a period ranging from the immediate future. The three pre-emptive control algorithms are: (1) vehicle subsystem commands for motion sickness mitigation, (2) vehicle subsystem commands for comfort enhancement, and (3) vehicle subsystem commands for productivity enhancement.

[0131] Vehicle Subsystem Commands for Motion Sickness Reduction The algorithm generates vehicle subsystem commands that help reduce occupant motion sickness. These commands are proactive because they use predictions of the future state of the occupant and the vehicle. These commands also include current, immediate commands to the vehicle subsystems. When combined, the commands generated at every moment include both current and anticipated future commands. Each vehicle subsystem affects the occupant in a unique way. In one possible embodiment, the algorithm can command and control the operation of the active seat, active restraints, active occupant stimuli, and active productivity interface. Each vehicle subsystem operation can be defined as an output of the algorithm: active seat sway and tilt, active restraint tension, active display (active productivity interface) movement, and active occupant stimulus light flashing. Each of these operations is quantified, with active seat sway and tilt defined by angular position and velocity, active restraint tension defined by restraint position, and active display movement defined by angular position. In one embodiment, the quantified outputs are captured in a matrix, with rows corresponding to actions defined above and columns corresponding to commands, with the first column corresponding to an immediate / current action and successive columns corresponding to future preempted commands. In other embodiments, the outputs may be organized in other ways. In other embodiments, other active / mechatronic vehicle subsystems may be commanded to mitigate motion sickness.

[0132] In one possible embodiment, the commands can be generated using an enhanced machine learning algorithm. Enhanced machine learning leverages exploration of various outcomes, then measuring their impact as either positive or negative, and then leveraging the outcome with the most positive impact. For example, if the algorithm determines a 20 degree bank considering the vehicle making a hard turn and the occupant responds to this in the affirmative, the algorithm will continue to recommend this action over another when the vehicle makes the same or similar turn again. In other embodiments, other algorithms and methods can be used to generate the commands.

[0133] In one possible embodiment, the predicted route and traffic (predicted based on historical data from the data center), predicted vehicle chassis roll and pitch (vehicle state predicted by the vehicle model algorithm), predicted occupant motion sickness susceptibility (predicted by the occupant model and historical information from the data center), real-time and predicted PREACT mechatronic subsystem states, such as active seat sway and tilt and active restraint tension (predicted by the PREACT mechatronic subsystem model), and occupant self-reported preferences for vehicle subsystem commands as inputs to the algorithm. Most of these inputs, such as vehicle chassis roll and pitch, occupant motion sickness susceptibility, and mechatronic subsystem states, are quantifiable. The occupant self-reported preferences may or may not be quantitative, but they can be quantitatively organized. For example, in one possible embodiment, the occupant may indicate that he or she would prefer a "high" active seat intervention, which corresponds to a 20 degree tilt, rather than a "low" active seat intervention, which corresponds to a 5 degree tilt. A lookup table may be used to quantify the occupant's self-reported preferences. In other embodiments, other inputs and methods for organizing and quantifying the inputs and outputs may be used.

[0134] Vehicle Subsystem Command for Increased Productivity The algorithm generates vehicle subsystem commands that help increase occupant productivity. These commands are proactive because they use predictions of the future states of the occupant and the vehicle. These commands also include real-time immediate commands to the vehicle subsystems. When combined, the commands generated at every moment include both real-time and proactive future commands. Each vehicle subsystem impacts occupant productivity in a unique way. In one possible embodiment, the algorithm can command and control the operation of the active seats, active productivity interfaces, and active cabin environment. Each vehicle subsystem operation can be defined as an output of the algorithm: active seat sway and tilt, active display (active productivity interface) movement, and active cabin environment light brightness. Each of these operations is quantified, with active seat sway and tilt defined by angular position and velocity, and active display movement defined by angular position and cabin light brightness. In one embodiment, the quantified output is captured in a matrix, with rows corresponding to actions defined above and columns corresponding to commands, with the first column corresponding to an immediate / real-time action and successive columns corresponding to future preempted commands. In other embodiments, the output may be organized in other ways. In other embodiments, other active / mechatronic vehicle subsystems may be commanded to increase crew productivity.

[0135] In one possible embodiment, the command can be generated using an enhanced machine learning algorithm. Enhanced machine learning utilizes the exploration of various outcomes, then measures their impact as either positive or negative, and then utilizes the outcome with the most positive impact. For example, if the occupant is reading a book, the algorithm determines that the active seat should be tilted 10 degrees and the interior lighting should be increased in brightness to increase productivity. The occupant can report their productivity themselves, or this determination can be made using a camera in the interior. In other embodiments, other algorithms and methods can be used to generate the command.

[0136] In one possible embodiment, predicted route and traffic (predicted based on historical data from a data center), predicted vehicle chassis roll and pitch (vehicle state predicted by vehicle model algorithm), predicted occupant productivity rating (predicted by occupant model and historical information from a data center), predicted task ID, real-time and predicted PREACT mechatronic subsystem states, such as active seat sway and tilt (predicted by PREACT mechatronic subsystem model), and occupant self-reported preferences for vehicle subsystem commands as inputs to the algorithm. Most of these inputs, such as vehicle chassis roll and pitch, and mechatronic subsystem states, are quantifiable. The occupant self-reported task ID and productivity rating can be quantified as described above. The occupant self-reported productivity preference may or may not be quantitative, but it can be quantitatively organized. For example, in one possible embodiment, the occupant may indicate that they would prefer a "high" active productivity interface intervention, which corresponds to a 10 degree tilt of the display, rather than a "low" active productivity interface intervention, which corresponds to a 3 degree tilt. A look-up table may be used to quantify the occupant's self-reported productivity preferences. In other embodiments, other inputs and methods for organizing and quantifying the inputs and outputs may be used.

[0137] Vehicle Subsystem Commands for Comfort Improvement The algorithm generates vehicle subsystem commands that help to enhance occupant comfort. These commands are proactive because they use predictions of the future states of the occupant and the vehicle. These commands also include current immediate commands to the vehicle subsystems. When combined, the commands generated at every moment include both current and future commands that are preempted. Each vehicle subsystem impacts occupant comfort in a unique way. In one possible embodiment, the algorithm can command and control the operation of the active seat and active cabin environment. Each operation of the vehicle subsystem can be defined as an output of the algorithm, namely, active seat sway and tilt, active cabin environment light brightness, and active cabin environment air conditioning. Each of these operations is quantified, where active seat sway and tilt are defined by angular position and velocity, cabin light brightness, air conditioning air flow temperature, direction, and velocity. In one embodiment, the quantified outputs are captured in a matrix, where the rows correspond to the operations defined above, and the columns correspond to commands, with the first column corresponding to the immediate / current operation and successive columns corresponding to future preempted commands. In other embodiments, the outputs may be organized in other ways. In other embodiments, other active / mechatronic vehicle subsystems may be commanded to enhance passenger comfort.

[0138] In one possible embodiment, the command can be generated using an enhanced machine learning algorithm. Enhanced machine learning utilizes the exploration of various results, then measures their impact as either positive or negative, and then utilizes the result with the most positive impact. For example, if the algorithm determines that the lighting in the cabin should be reduced in brightness to increase comfort when the occupant is sleeping / resting, and the air temperature should be reduced (when the outside temperature is high, otherwise it increases when the outside temperature is low) to increase comfort. The occupant can report the comfort themselves, or this determination can be made using a camera in the cabin. In other embodiments, other algorithms and methods can be used to generate the command.

[0139] In one possible embodiment, the predicted route and traffic (predicted based on historical data from a data center), predicted vehicle chassis roll and pitch (vehicle state predicted by vehicle model algorithm), predicted occupant comfort rating (predicted by occupant model and historical information from a data center), real-time and predicted PREACT mechatronic subsystem states, such as active seat sway and tilt (predicted by PREACT mechatronic subsystem model), and occupant self-reported preferences for vehicle subsystem commands as inputs to the algorithm. Most of these inputs are quantifiable, such as vehicle chassis roll and pitch, and mechatronic subsystem states. The occupant self-reported comfort state and comfort rating can be quantified as described above. The occupant self-reported comfort preference may or may not be quantitative, but it can be quantitatively organized. For example, in one possible embodiment, the occupant may indicate that they would like "more" comfort, which corresponds to a lower cabin temperature and dimmer lights. A look-up table can be used to quantify the occupant's self-reported comfort preference. In other embodiments, other inputs and methods for organizing and quantifying the inputs and outputs may be used.

[0140] Vehicle Algorithm The vehicle driving algorithms (Fig. 1, block 8) consist of route generation and navigation (Fig. 2, block 25), driving behavior command generation (26), and vehicle model (27). These algorithms are predictive or preemptive control algorithms, and their embodiments are described in detail below. More specifically, the route prediction and navigation algorithm (25) is a predictive algorithm, the driving behavior command generation (26) is a preemptive control algorithm, and the vehicle model (27) is a predictive algorithm. Although similar algorithms are used in the literature, the above algorithms use different inputs.

[0141] Driving behavior generation to improve passenger condition The generation of driving behavior is performed with the goal of minimizing passenger motion sickness while maximizing passenger comfort and productivity. The algorithm also takes into account the fuel and energy consumption of the vehicle. The inputs to the algorithm are aggregate driving behavior data over time, passenger motion sickness, passenger comfort, passenger productivity, passenger kinematics, passenger physiological state and passenger profile, as well as real-time route information, passenger status and passenger preferences. For example, if the system generates a route with similar characteristics to a route that caused motion sickness for a passenger with a similar profile to the current passenger, the algorithm can choose to select a different route to minimize motion sickness. In another example, if the generated route has high traffic volume during the trip, the system can choose to select a different route to avoid multiple acceleration / braking events and thus minimize motion sickness.

[0142] Optimal route prediction to improve passenger condition The route prediction is performed with the goal of minimizing passenger motion sickness while maximizing passenger comfort and productivity. The algorithm also takes into account the fuel and energy consumption of the vehicle. The inputs to the algorithm are aggregate route information over time, passenger motion sickness, passenger comfort, passenger productivity, passenger kinematics, passenger physiological state and passenger profile, as well as real-time route information, passenger state and passenger preferences. For example, if a set of driving behaviors has a high acceleration value and the passenger profile indicates a tendency to motion sickness, the system can choose to adopt a set of driving behaviors with a lower acceleration value. In another example, if a set of driving behaviors includes multiple lane changes and the passenger is experiencing motion sickness, the algorithm can select an alternative set of driving behaviors with fewer lane changes to minimize motion sickness at the expense of increased time to reach the destination.

[0143] The techniques, including algorithms, calculations, etc. described herein may be implemented by one or more computer programs executed by one or more computer processors. These one or more computer processors may be physically co-located (e.g., in an on-board vehicle, or a remote data server) or distributed across multiple vehicles, remote data centers, remote servers, cloud servers, mobile computing devices, wearable computing devices, etc. A computer program includes processor-executable instructions stored on a non-transitory tangible computer-readable medium. A computer program may also include stored data. Non-limiting examples of non-transitory tangible computer-readable media are non-volatile memory, magnetic storage, and optical storage. The algorithms, models, and calculations described herein may be implemented in an integrated or distributed manner. In the latter case, certain parts of an algorithm or calculation may be executed via a first computer program, and different parts may be executed by a second computer program. However, two computer programs, possibly executing on separate computer processors, may communicate and operate in conjunction to implement said algorithms or calculations.

[0144] Some portions of the above description are presented in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. These operations, while described in functional or logical terms, will be understood to be implemented by computer programs. Further, it has proven convenient at times to refer to arrangements of these operations as modules or by functional names, without loss of generality.

[0145] As will be apparent from the above description, unless otherwise stated, throughout the description, descriptions utilizing terms such as "processing" or "computing" or "calculating" or "determining" or "displaying" are understood to refer to the operations and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (electronic) quantities in the computer system's memory or registers or other such information storage, transmission or display devices.

[0146] Certain aspects of the described technology include process steps and instructions described herein in the form of an algorithm, it being noted that the described process steps and instructions may be embodied in software, firmware, or hardware, and if embodied in software, may be downloaded to reside and operate on different platforms used by a real-time network operating system.

[0147] The present disclosure also relates to an apparatus for performing the operations herein. The apparatus may be specially constructed for the required purposes, or may comprise a computer selectively activated or reconfigured by a computer program stored in a computer-readable medium accessible by the computer. Such computer programs may be stored on any type of tangible computer-readable storage medium, including, but not limited to, a floppy disk, an optical disk, a CD-ROM, a magneto-optical disk, a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic or optical card, an application specific integrated circuit (ASIC), or any type of medium suitable for storing electronic instructions, each coupled to a computer system bus. Furthermore, the computers referred to herein may include a single processor, or may be architectures employing multiple processor designs to increase computing power.

[0148] The algorithms and operations presented herein are not inherently related to any particular computer or other apparatus. Various systems may also be used with programs in accordance with the teachings herein, or it may prove convenient to construct a more specialized apparatus to perform the required method steps. The required structure for a variety of these systems, along with equivalent variations, will be apparent to those skilled in the art. Further, the present disclosure is not described with reference to any particular programming language. It will be understood that a variety of programming languages ​​may be used to implement the teachings of the present disclosure as described herein.

[0149] The foregoing description of the embodiments is provided for purposes of illustration and description. It is not intended to be exhaustive or to limit the present disclosure. Individual elements or features of a particular embodiment are generally not limited to that particular embodiment, are interchangeable where applicable, and can be used in selected embodiments even if not specifically shown or described. It may also be modified in many ways. Such variations should not be considered as departures from the present disclosure, and all such modifications are intended to be included within the scope of the present disclosure.

Claims

1. An occupant conditioning system for a passenger vehicle, comprising: an active seat for supporting a particular occupant within said vehicle; a prediction algorithm executed by a computer processor and operable to predict a state of the particular occupant and a motion of the vehicle, the predicted motion including an acceleration of the vehicle; and a command generation algorithm executed by the computer processor and configured to receive the predicted state of the particular occupant and the predicted movement of the vehicle from the prediction algorithm, the command generation algorithm determining a look-ahead command to tilt the active seat and issuing the look-ahead command to the active seat, the active seat being tilted in the same direction as the acceleration of the vehicle; The look-ahead commands are received by the predictive algorithm and used in predicting the state of the particular occupant.

2. The occupant condition conditioning system of claim 1 , wherein the predictive algorithm uses machine learning methods to predict the state of the particular occupant and the behavior of the vehicle.

3. The passenger condition adjustment system of claim 1 , wherein the predictive algorithm predicts the state of the particular occupant and the movement of the passenger vehicle using data collected prior to current operation of the passenger vehicle and data collected in real time.

4. 2. The passenger condition adjustment system of claim 1, wherein the predictive algorithm predicts movement of the vehicle using data describing the vehicle, data describing a route of the vehicle, and data describing traffic along the route of the vehicle.

5. The occupant condition adjustment system of claim 1 , wherein the predictive algorithm uses occupant information to predict the state of the particular occupant.

6. The occupant conditioning system of claim 1 , wherein the condition of the particular occupant is selected from the group consisting of motion sickness, comfort level, productivity level, physical movement, and physiological condition.

7. The occupant conditioning system of claim 1 , wherein the command generation algorithm uses vehicle and occupant information to determine a look-ahead command for tilting the active seat.

8. An occupant conditioning system for a passenger vehicle, comprising: an active restraint present within the vehicle and configured to restrain a particular occupant within the vehicle; a predictive algorithm executed by a computer processor and operable to predict the state of the particular occupant and the movement of the vehicle; a command generation algorithm executed by the computer processor and configured to receive the predicted state of the particular occupant and the predicted movement of the vehicle from the prediction algorithm, the command generation algorithm determining a preemption command for the active restraint and issuing the preemption command to the active restraint; The command generation algorithm uses the active restraint information aggregated over time and occupant information aggregated over time to determine optimized preemptive commands for the active restraints.

9. The occupant condition conditioning system of claim 8 , wherein the predictive algorithm uses machine learning methods to predict the state of the particular occupant and the behavior of the vehicle.

10. The passenger condition adjustment system of claim 8, wherein the predictive algorithm predicts the state of the particular occupant and the movement of the vehicle using data collected prior to current operation of the vehicle and data collected in real time.

11. 9. The passenger condition adjustment system of claim 8, wherein the predictive algorithm predicts movement of the vehicle using data describing the vehicle, data describing a route of the vehicle, and data describing traffic along the route of the vehicle.

12. The occupant condition regulation system of claim 8 , wherein the predictive algorithm uses occupant information to predict the state of the particular occupant.

13. The occupant conditioning system of claim 8 , wherein the condition of the particular occupant is selected from the group consisting of motion sickness, comfort level, productivity level, physical movement, and physiological condition.

14. The occupant conditioning system of claim 8 , wherein the command generation algorithm uses vehicle and occupant information to determine preemptive commands for the active restraints.

15. The occupant conditioning system of claim 8 , wherein the command generation algorithm determines preemptive commands for the active restraints using states and parameters of the active restraints.

16. 9. The occupant conditioning system of claim 8, wherein the active restraint is further defined as a strap attached to an actuator, the actuator being controllable to vary the restraining force applied by the strap to a particular occupant.

17. An occupant conditioning system for a passenger vehicle, comprising: an active occupant stimulation subsystem present within the vehicle and configured to generate stimulation for a particular occupant within the vehicle; a prediction algorithm executed by a computer processor and operable to predict a state of the particular occupant and a motion of the vehicle, the predicted motion including an acceleration of the vehicle; and a command generation algorithm executed by the computer processor and configured to receive the predicted state of the particular occupant and the predicted movement of the vehicle from the prediction algorithm, the command generation algorithm determining a preemptive command to stimulate the particular occupant to lean in the same direction as the acceleration of the vehicle, and issuing the preemptive command to the active occupant stimulation subsystem; The look-ahead commands are received by the predictive algorithm and used in predicting the state of the particular occupant.

18. The occupant condition conditioning system of claim 17 , wherein the predictive algorithm uses machine learning methods to predict the state of the particular occupant and the behavior of the vehicle.

19. The occupant condition adjustment system of claim 17, wherein the predictive algorithm predicts the state of the particular occupant and the movement of the vehicle using data collected prior to current operation of the vehicle and data collected in real time.

20. 18. The passenger condition adjustment system of claim 17, wherein the predictive algorithm predicts movement of the vehicle using data describing the vehicle, data describing a route of the vehicle, and data describing traffic along the route of the vehicle.

21. The occupant condition regulation system of claim 17 , wherein the predictive algorithm uses occupant information to predict the state of the particular occupant.

22. 20. The occupant conditioning system of claim 17, wherein the condition of the particular occupant is selected from the group consisting of motion sickness, comfort level, productivity level, physical movement, and physiological condition.

23. The occupant conditioning system of claim 17 , wherein the command generation algorithm uses vehicle information and occupant information to determine the preemptive commands.

24. The occupant conditioning system of claim 17 , wherein the command generation algorithm determines the preemptive commands using states and parameters of the active occupant stimulation subsystem.

25. An occupant conditioning system for a passenger vehicle, comprising: an active productivity interface present in the vehicle and configured to support tasks performed by a particular occupant while the vehicle is moving; a predictive algorithm executed by a computer processor and operable to predict the particular occupant state; a command generation algorithm executed by the computer processor and configured to receive the predicted state of the particular occupant from the prediction algorithm, the command generation algorithm determining a look-ahead command for the active productivity interface and issuing the look-ahead command to the active productivity interface; An occupant state adjustment system, wherein the command generation algorithm uses information of the active productivity interface aggregated over time and occupant information aggregated over time to determine optimized preemptive commands for the active productivity interface.

26. 26. The occupant condition conditioning system of claim 25, wherein the predictive algorithm uses machine learning methods to predict the particular occupant condition.

27. 26. The occupant condition adjustment system of claim 25, wherein the predictive algorithm predicts the state of the particular occupant using data collected prior to current operation of the vehicle and data collected in real time.

28. 26. The occupant condition regulation system of claim 25, wherein the predictive algorithm uses occupant information to predict the state of the particular occupant.

29. 26. The occupant condition adjustment system of claim 25, further comprising an imaging device disposed in the vehicle and configured to capture image data of the particular occupant, and wherein the predictive algorithm determines the state of the particular occupant based in part on the image data.

30. 26. The occupant condition adjustment system of claim 25, further comprising a user input device configured to receive input from a person within the vehicle, the input indicating a productivity state of the particular occupant, and the predictive algorithm determining the productivity state of the particular occupant based in part on the input.

31. 26. The occupant conditioning system of claim 25, wherein the active productivity interface is further defined as one of an active display, an active keyboard, or an active work surface.

32. 2. The occupant condition adjustment system of claim 1, wherein the prediction algorithm is operable to predict a state of the active seat, the prediction algorithm uses the look-ahead command in the prediction of the state of the active seat, the prediction algorithm uses the predicted state of the active seat in the prediction of the state of the particular occupant, and the command generation algorithm is configured to receive the predicted state of the active seat.

33. 2. The occupant conditioning system of claim 1, wherein the command generation algorithm uses aggregated information of the active seat over time and aggregated occupant information over time to determine an optimized look-ahead command for tilting the active seat.

34. The occupant condition regulation system of claim 8 , wherein the look-ahead commands are received by the predictive algorithm for use in predicting the state of the particular occupant.

35. 35. The occupant condition adjustment system of claim 34, wherein the prediction algorithm is operable to predict a state of the active restraint, the prediction algorithm uses the look-ahead command in the prediction of the state of the active restraint, the prediction algorithm uses the predicted state of the active restraint in the prediction of the state of the particular occupant, and the command generation algorithm is configured to receive the predicted state of the active restraint.

36. 18. The occupant state adjustment system of claim 17, wherein the prediction algorithm is operable to predict a state of the active occupant stimulation subsystem, the prediction algorithm uses the look-ahead command in the prediction of the state of the active occupant stimulation subsystem, the prediction algorithm uses the predicted state of the active occupant stimulation subsystem in the prediction of the state of the particular occupant, and the command generation algorithm is configured to receive the predicted state of the active occupant stimulation subsystem.

37. 20. The occupant conditioning system of claim 17, wherein the command generation algorithm uses information of the active occupant stimulation subsystem aggregated over time and occupant information aggregated over time to determine optimized preemptive commands for stimulating the particular occupant.

38. 26. The occupant condition regulation system of claim 25, wherein the look-ahead commands are received by the predictive algorithm and used in the prediction of the state of the particular occupant.

39. 39. The occupant state adjustment system of claim 38, wherein the prediction algorithm is operable to predict a state of the active productivity interface, the prediction algorithm uses the look-ahead commands in the prediction of the state of the active productivity interface, the prediction algorithm uses the predicted state of the active productivity interface in the prediction of the state of the particular occupant, and the command generation algorithm is configured to receive the predicted state of the active productivity interface.

Images