Multi-factor transition to and from autonomy

Abstract

Methods and apparatus for a self-driving vehicle to safely control transitions into and out of autonomy mode. The techniques may be used in a single autonomous vehicle or adapted for cooperative control of vehicles traveling in a platoon. The transition may be based on two or more of a number of conditions being satisfied. The method includes detecting a number of conditions, including autonomy logic readiness, driver readiness, traffic conditions, road conditions, ambient weather conditions, ambient lighting conditions, and compliance with an operational driving domain for autonomy, and transitioning into or out of autonomy mode only when two or more of the conditions are satisfied.

Description

[Technical field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This patent application claims priority to co-pending U.S. Provisional Patent Application No. 63 / 297,349, filed January 7, 2022, the entire contents of which are incorporated herein by reference.

[0002] (Technical field) This patent application relates to methods and systems for controlling and managing transitions into and out of autonomy states. [Background technology]

[0003] (background) This patent application relates to methods and apparatus used by platooning vehicles to influence the behavior of other drivers who are not part of the platoon.

[0004] Researchers and vehicle manufacturers have been developing self-driving technologies for many years. Commercial trucking remains one of the areas where autonomous vehicles will eventually become widespread. In one scenario, the truck at the front of the convoy remains under human control, while one or more following vehicles autonomously follow the lead vehicle or each other. Sensors and / or wireless connections (such as vehicle-to-vehicle radio communication) keep the trucks aware of each other's location and conditions, and enable the autonomous following vehicles to respond to changes in direction and speed of the lead vehicle.

[0005] Prior art such as U.S. Pat. No. 9,690,292 B1 describes the use of "imaging sensors" (e.g., cameras, LiDAR, radar, or infrared) located within the vehicle cabin to detect driver position / posture and determine readiness to transition out of an autonomous mode. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] U.S. Patent No. 9,690,292 Summary of the Invention [Means for solving the problem]

[0007] (Summary of the Preferred Embodiment) A method and / or apparatus for operating an autonomous vehicle and controlling transitions into or out of an autonomy mode. The approach involves detecting a number of conditions relating to the state of vehicle control and / or indicia of driver readiness and / or traffic and road conditions and / or ambient weather and lighting conditions and / or compliance with an operational driving domain for autonomy. A transition into or out of the autonomy mode is made only when two or more conditions are satisfied.

[0008] In some aspects, the techniques described herein relate to methods for operating an autonomous vehicle and controlling transitions into or out of an autonomy mode, the methods including detecting a number of conditions including autonomy logic readiness, driver readiness, traffic conditions, road conditions, ambient weather conditions, ambient lighting conditions, and compliance with an operational driving domain for autonomy, and transitioning into or out of the autonomy mode only when two or more of the conditions are satisfied.

[0009] In some aspects, the techniques described herein relate to a method, in which a number of conditions persist for a determined period of time, and the driver readiness conditions include any two or more of the driver seat being in a proper position, weight being on the driver seat, the steering wheel being moved, the steering wheel being under force, the steering wheel being tilted, the steering wheel being gripped, a fingerprint being detected on the steering wheel, the brake pedal being moved, the accelerator pedal being moved, the armrest being moved, and a camera verifying that a driver is present or absent from the driver's seat.

[0010] In some aspects, the techniques described herein relate to a method, further comprising: disregarding input from the steering wheel in an autonomy mode when the driver's seat is not in a driving position or when the driver's seat does not have sufficient weight to indicate that a driver is present in the seat.

[0011] In some aspects, the techniques described herein relate to a method, wherein traffic conditions, road conditions, ambient weather conditions, lighting conditions, and operational driving domain limitations do not impede the transition.

[0012] In some aspects, the techniques described herein relate to a method, where the autonomous vehicle is part of a platoon with a second vehicle, and the plurality of conditions further includes approval from the second vehicle, such that transitioning into or out of the autonomy mode is a collaborative decision made between the autonomous vehicle and the second vehicle.

[0013] In some aspects, the techniques described herein relate to an apparatus for operating an autonomous vehicle and controlling transitions into or out of an autonomy mode, the apparatus including one or more data processors and one or more computer-readable media including instructions that, when executed by the one or more data processors, cause the one or more data processors to perform a process for detecting a plurality of conditions including autonomy logic readiness, driver readiness, traffic conditions, road conditions, ambient weather conditions, ambient lighting conditions, and compliance with an operational driving domain for autonomy, and transitioning into or out of the autonomy mode only when two or more of the conditions are satisfied.

[0014] In some aspects, the techniques described herein relate to an apparatus where a number of conditions persist for a determined period of time, and the driver readiness conditions include any two or more of the driver's seat being in the proper position, weight being on the driver's seat, the steering wheel moving, the steering wheel being under force, the steering wheel being tilted, the steering wheel being gripped, a fingerprint being detected on the steering wheel, the brake pedal being moved, the accelerator pedal being moved, the armrest being moved, and a camera verifying that a driver is present or absent from the driver's seat.

[0015] In some aspects, the techniques described herein relate to an apparatus whereby input from the steering wheel is ignored in an autonomy mode when the driver's seat is not in a driving position or when the driver's seat does not have sufficient weight to indicate that a driver is present in the seat.

[0016] In some aspects, the techniques described herein relate to an apparatus where traffic conditions, road conditions, ambient weather conditions, lighting conditions, and operational driving domain limitations are not interfering with the transition.

[0017] In some aspects, the techniques described herein relate to an apparatus, wherein the autonomous vehicle is part of a platoon with a second vehicle, and the plurality of conditions further includes approval arising from the second vehicle, such that transitioning into or out of the autonomy mode is a collaborative decision made between the autonomous vehicle and the second vehicle. [Brief description of the drawings]

[0018] Additional novel features and advantages of the approaches discussed herein will become apparent from the following text and accompanying drawings.

[0019] [Figure 1] FIG. 1 is an exemplary cargo truck and electronic subsystem.

[0020] [Diagram 2] FIG. 2 shows some typical sensors in a truck.

[0021] [Diagram 3] FIG. 3 is an exemplary autonomy state transition diagram.

[0022] [Figure 4] FIG. 4 is an example block diagram of components of a system for implementing the methods and apparatus described herein.

[0023] [Diagram 5] FIG. 5 illustrates the autonomy function.

[0024] [Figure 6] FIG. 6 illustrates the propagation of a shared world model.

[0025] [Figure 7] FIG. 7 is an example flow for a collaborative decision to transition to or from autonomy. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0026] DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS This patent application describes a method and apparatus for safely controlling transitions into or out of an autonomy mode. Making such a transition safely is ensured by first verifying that multiple states of the vehicle and / or human driver indicate readiness to make the transition, and thus such a transition does not occur blindly. Some of the examples described herein will relate to operating a single vehicle, where both the human and the autonomy logic may be in control. Other scenarios are described for a pair of vehicles traveling in a platoon, where the first vehicle is at least partially controllable by the human driver and the second vehicle is controllable by the autonomy logic. However, it should be understood that the principles discussed herein are also applicable to larger groups of vehicles.

[0027] Single vehicle example

[0028] 1 illustrates an example vehicle 110-1, such as a cargo truck, that includes a tractor and a fifth wheel onto which a kingpin of a trailer may be coupled. In some implementations, the vehicle may be other types of vehicles, such as a passenger car. The vehicle 110-1 may be controlled either by a human driver or by autonomous logic.

[0029] The electronics located within vehicle 110-1 may include sensors 112, actuators 114, a V2V radio transceiver 116, other I / O devices 118, and one or more processors 120 (also referred to herein as controllers 120). As discussed further herein, the one or more processors 120 may execute various logic, including autonomy logic 122 and decision logic 124. The electronics may also maintain a world model 126.

[0030] 2 is a view taken from inside the cabin of a vehicle 110-1. The sensors 112 may include a steering wheel 1102 sensor that detects steering wheel movement or force on the steering wheel or even the proximity of a human hand or finger near the steering wheel, a seat sensor that detects the weight and / or position of the driver's seat, an armrest position sensor 1106, a throttle position 1108, or a brake position 1109 sensor. Sensors 1112, such as video or infrared cameras, may detect whether a human (driver) is seated in the seat.

[0031] Other sensors 1110 located outside the vehicle may include cameras, LiDAR, radar, and the like that detect the presence of other vehicles, objects, obstacles, road conditions, and weather outside the vehicle 110-1. Such sensors 1110 may be used by the world model logic 126 to detect acceptable external conditions that lead to a transition into or out of autonomy.

[0032] For example, the sensors 1110 and logic 126 may determine whether (i) other traffic does not present undue risk to transitioning into or out of the autonomy mode (e.g., other vehicles are not engaged in maneuvers such as lane changing or overtaking), and / or (ii) other traffic conditions and actions are detectable and predictable with a sufficiently high degree of confidence. Other example obstruction conditions may include (iii) poor weather (e.g., heavy rain or snow or fog), or (iv) unacceptable road conditions (e.g., poor lane markings, uneven or slippery road surface), or (v) visual impairments (e.g., blinding sunlight). The sensors may also be used to determine whether appropriate operational driving domain conditions exist (e.g., the autonomy logic is designed to operate under typical conditions with reasonable certainty).

[0033] 3 is an example state transition diagram. In one state 310, the vehicle 110-1 is driven by a human. In another state 314, the vehicle is controlled by the autonomy logic 122. State 314 is referred to herein as autonomy control. It should be understood that autonomy may include any type or level of autonomy, such as a non-zero level of autonomy defined by the Society of Automotive Engineers (SAE).

[0034] In yet another state 312, control is in the process of transitioning between human control 310 and autonomous control 314, but control has not yet changed from its previous state. This state 312 is also referred to herein as the wait state.

[0035] Transitions between states include a transition 320 from human driving 310 to wait state 312, a transition 322 from wait state 312 to autonomous driving 314, a transition 332 from autonomy 314 to wait 312, and a transition 330 from wait 312 to human driving 310.

[0036] Each of these state transitions 320, 322, 330, and 332 (collectively, transitions 340) involves the confirmation that two or more conditions related to humans and / or vehicle components or systems or conditions external to the vehicle exist.

[0037] It should be understood that various sensors may be installed within the vehicle itself to sense these conditions, however, certain other conditions may be reported to the vehicle via the communications interface (such as weather conditions or the state of another vehicle).

[0038] By way of example, any two or more of the following conditions should persist for a sufficient period of time (such as at least a few seconds):

[0039] (Vehicle related)

[0040] The seat 1104 is in the appropriate "driving position" (rotated forward, or rotated to the side, or pushed / tilted forward / backward)

[0041] Weight is on seat 1104

[0042] Steering wheel 1102 is moving or experiencing a force

[0043] The steering wheel 1102 is tilted

[0044] The steering wheel 1102 is being gripped.

[0045] An authorized fingerprint is detected on the steering wheel 1102

[0046] Brake pedal 1109 is moving

[0047] Accelerator pedal 1108 is moving

[0048] Armrest 1106 is moved up or down

[0049] Camera 1112 verifies the presence or absence of the driver "in the seat"

[0050] (Exterior of vehicle 1110)

[0051] Traffic conditions are not impeding the transition

[0052] Road conditions are not impeding the transition

[0053] Ambient weather and lighting conditions do not impede the transition

[0054] (others)

[0055] Operational operating domain restrictions do not impede the transition

[0056] Thus, it should be understood that two or more of these conditions may be structured as prerequisites for entering the autonomous mode (e.g., transitions 320 and / or 322), for leaving the autonomous mode (e.g., transitions 332 and / or 330), or for all such cases.

[0057] Using such conditions, it may be prudent to verify, for example, that a driver is in place, aware of the situation, and ready to take over control (the seat 1104 detects sufficient weight, the camera 1112 detects that a human is in the seat with eyes open and hands on the steering wheel 1102 and brake 1109 or throttle 1108).

[0058] More generally, the presence of appropriate factors indicative of an ability to safely transition into or out of an autonomy mode may involve detection of on-board components such as seat position, seat weight, cameras, arm rests, dashboard push buttons, steering wheel and brake pedal movement, a fingerprint sensor (on the steering wheel), or a combination thereof. Detection may also involve determining conditions outside the vehicle, such as traffic or weather conditions, which may be sensed by the vehicle itself or reported to the vehicle via a communications link.

[0059] In some implementations, the transition 340 should be "smooth." Capable of both human and autonomous driving, a vehicle will likely have propulsion, braking, and steering actuators that can be overdriven by wired commands from a controller. Thus, any human input feeds the same control inputs as the autonomy logic. Thus, when a smooth transition 340 occurs from a human input signal to a computer input signal or vice versa, there will be no steps or edges in the signal.

[0060] To transition out of autonomy, the autonomy logic needs to ensure that the driver is engaged, present, and has access to all controls, regardless of their constraints.

[0061] Another scenario occurs when the autonomy is in control and does not expect human input, i.e. nothing should be touching the steering wheel, or the brake, or the throttle. Multi-element control flow can be used to provide safety mechanisms that prevent undesired loss of control. For example, if something should touch one of the control inputs (a cat jumps into the driver's seat, or a human touches the steering wheel when leaving the driver's seat, or perhaps a cell phone falls onto the brake because of a bump in the road), the transition out of autonomy will be prevented.

[0062] Different factors can also be evaluated in sequence over a predetermined period of time, such as a few seconds, and filtered, if necessary, to remove momentary noise or transients in the signal. For example, if a person simply tugs on the steering wheel or sits in the seat, a transition would not occur. For example, transition 340 may require multiple factors, such as a weight of more than 100 pounds on the seat, a tight grip on the steering wheel, a camera sensing a human body in the seat, and a fingerprint sensor determining that an authorized person is touching the steering wheel.

[0063] In another case, an armrest 1106 position sensor may be used in combination with the seat 1104 sensor. If the armrest is lifted up and the weight on the seat suddenly drops, the transition logic can determine that the driver has risen from the seat.

[0064] Another case occurs when the vehicle is in an autonomous mode and the driver is not in the seat, but is somewhere in the cab, perhaps resting. A pet or some other object may touch the steering wheel or fall onto the seat. The multi-element transition logic can thus prevent the human driver from inadvertently transitioning out of an autonomous mode when he is not ready and able to take over.

[0065] Multi-element transition logic can also reduce the risk of misinterpreting a signal from a single sensor. For example, the camera 1112 logic may conclude that a human is present in the seat when in fact it is a large dog.

[0066] Multi-component autonomy transitions as part of cooperative control of platooning vehicles

[0067] Briefly directing attention back to FIG. 1, the same multi-element control of autonomy transitions may be utilized when multiple vehicles cooperate to travel in a platoon.

[0068] When vehicles wish to travel in a platoon, each may have access to information that the others may not. Information available in any vehicle may originate in or near the vehicle and be sensed using sensors on that vehicle. The physical phenomenon being sensed may be too far away to be sensed (either well or at all) by other vehicles, or the phenomenon may be hidden by one vehicle that is able to sense it. Information may also originate from a human inside any vehicle whose presence is unknown or undetectable in other vehicles. When humans are the intended consumers of information, it is often best formatted in a manner consistent with human sensory capacities. Information may also be the result of an arbitrary amount of processing of any other information that was available as input to such processing.

[0069] When several vehicles wish to act as a unit, they often need to be considered as a unit, which can be difficult to achieve when all of the relevant information is distributed across space, i.e., among the vehicles themselves. One possible solution is to share the relevant information among the vehicles. The approach does not rely on specific signal processing, simulation, sensor data fusion, or optimal estimation schemes, but rather, the method interpolates, extrapolates, avoids interference, filters, processes, and shares such information as part of collaborative decision-making. A shared database produced using such techniques can be more complete, up-to-date, consistent, and accurate than would otherwise be obtainable, and the database can be available on all vehicles.

[0070] Methods for sharing information are presented herein to enable and / or improve the manner in which several vehicles may operate in a platoon as a unit. Individual vehicles may be operated by humans, by autonomy logic, or by a combination of both. For example, autonomy logic may be used to offload burdens, cognitively or otherwise, from humans, relieving them from needing to communicate with vehicles in any location or in a sufficiently quantitative or precise manner that allows the humans to direct their attention elsewhere.

[0071] Additionally, some methods may use information shared between all of the humans and all of the autonomy logic on all of the vehicles to enable the entire platoon to operate more effectively as a unit.

[0072] Returning attention to FIG. 1 , a situation is shown in which two vehicles are moving together in a platoon as a unit. An example platoon may be a convoy, or even a platoon with the vehicles following closely together. Both vehicles may incorporate hardware and software that allows them to implement autonomy logic, either when the vehicles are manufactured or subsequently modified. Such autonomy logic may include algorithms and enable the vehicles to drive themselves, interact with human drivers, and exchange information among themselves.

[0073] In this case, both example vehicles 110-1, 110-2 may include sensors 112, actuators 114, a V2V radio transceiver 116, other I / O devices 118, and one or more processors 120 (also referred to herein as controllers 120).

[0074] FIG. 4 illustrates these components in further detail. The self-driving algorithms and other aspects of the autonomy logic 122 are implemented in a controller (such as one or more processors 120) that receives sensor 112 data from the individual vehicles (110-1 or 110-2) and transmits actuator 114 signals to the individual vehicles 110-1 or 110-2. The controller 120 may further implement human interface algorithms that receive inputs (e.g., steering, throttle, touch screen, etc.) from a human driver via other I / O devices 118-D, while also transmitting data to other I / O devices 118, such as human-readable displays. The controller 120 may also transmit data to and receive data from a vehicle-to-vehicle (V2V) radio transceiver 116, enabling it to interact with humans and exchange information with controllers 120 located in other vehicles 110.

[0075] Collaboration through shared information

[0076] 5, the functions providing the decision logic 124 for each vehicle 110-A, 110-H may include perception and state estimation 220, situation awareness and assessment 222, decision making 224, and behavior execution 228. The world model 126 may include a state model 230, a situation model 232, and a decision model 234.

[0077] The controller 120 may implement algorithms that enable the driver and the vehicle to collaborate based on shared information. This information typically includes sensor data originating from outside the computer / human system components, as well as derived data (states, events, constraints, conclusions) originating from inside the computer / human system, and data indicative of physical phenomena generated by or for the purpose of being sensed by the human driver. Shared information may thus include data that (i) originates within or outside the convoy, (ii) represents physical phenomena (such as forces on a steering wheel that can be produced or sensed by a human), (iii) is received in its raw / sensed form from a sensor or other input device, or (iv) is derived data (examples include states, events, constraints, conclusions originating from inside the autonomy logic or human control components).

[0078] Each vehicle 110 will have its own local copy 126 of such shared information, referred to herein as a shared world model 240. At any given moment, each local copy 126 of the shared world model 240 may not be perfectly consistent with the local copies 126 on the other vehicles. Nevertheless, processes resident on all controllers 120 for all vehicles 110 attempt to keep the shared information in the shared world model 240 and local copies 126 sufficiently up-to-date and consistent to enable effective collaboration. Propagation of local copies 126 of the shared world model 240 between vehicles 110 is discussed in further detail below.

[0079] In Figure 5, the rectangular boxes on both the left and right sides show an example sequence, called the Perceive-Think-Act sequence. The dotted lines represent transitions between processing steps for information flow that supports decision making. As data originates inside the computer / human system, the world model 126 (and therefore also the shared world model 240) acts as another source of information for use by the autonomy algorithms implemented in the controller 120.

[0080] The perception and state estimation step 220 may process all of the incoming information from all sources to derive substantially new information that describes the arbitrary attributes of vehicles, humans, and external objects and traffic, etc. Such processing may comprise, for example, operations such as:

[0081] State estimation / data fusion - reducing redundant information to a non-redundant form or combining relevant quantities to produce other relevant quantities (e.g. measuring the space between vehicles)

[0082] Prediction - deriving future states from measurements (or predictions) of future states and times (e.g. predicting time to impact based on last known speed)

[0083] The situational awareness and assessment step 222 may process all of the incoming information from all sources to derive substantially new information that is less directly related to the information sensed and communicated. For example,

[0084] Detect events - watching and noticing when something important happens (e.g. a car in a blind spot)

[0085] Constraint Propagation - deriving constraints from other information (e.g., don't change lanes here)

[0086] The decision making step 224 may process all of the incoming information from all sources to derive substantially new information that is associated with or comprises the decision making. For example:

[0087] Logic - typically deriving a conclusion from other information by a process of logical inference, deduction, or resolution (e.g., a proposed lane change is denied due to an exercised veto)

[0088] Deliberation - considering multiple alternatives to choose one of them (e.g. the first vehicle cannot accelerate, so the second vehicle should slow down)

[0089] The behavior execution step 228 may process all of the incoming information from all sources to derive substantially new information that is associated with or causes an action in the real world. For example:

[0090] Notification - Generate an event (e.g., a message) for consumption in another part of the system (e.g., initiate a lane change maneuver here)

[0091] Action - Maintain or modify the vehicle's motion (e.g., perform an emergency braking maneuver)

[0092] Shared World Model

[0093] In FIG. 5, ovals 230, 232, 234 indicate some components of the shared world model 240. The shared world model 240 is used as a multi-data repository that is both a source of relevant information for some algorithms and a repository for results for other (or the same) algorithms. In general, any processing step may read information from or write information to any component. As mentioned above, each vehicle has its own local copy 126 of the shared world model 240, and processes attempt to keep them somewhat up-to-date and consistent. In this way, processes on any one vehicle effectively read information from and write information to the shared world models of all vehicles.

[0094] The shared world model 240 comprises all the information that is shared. In FIG. 5, this is depicted as being divided into three components 230, 232, 234 for ease of explanation, but there may be more or fewer components (such as state prediction 321 described below), and the distinction between them only serves to help detail the different ways in which vehicles may cooperate. In an exemplary embodiment, the shared information contains:

[0095] ● State Model 230 - Information about the properties, attributes, etc. of all objects of interest, both inside and outside the vehicle platoon. For example, this component comprises the aspect of "where everything is and how it is moving."

[0096] ● Situation Model 232 - Information relating to the description of the situation. For example, this component provides the aspect of "what is happening."

[0097] Decision Model 234 - Information relating to decisions to take or not take an action. For example, this component provides a "what to do" aspect.

[0098] As depicted in the example data flow diagram of FIG. 6, each vehicle 110 has a controller 120, a local model 126, perception and state estimation 220, state prediction 221, situation assessment 222, decision making 224, a shared world model 240, model propagation 280, model rendering 290, and vehicle-to-vehicle communication 295 components.

[0099] The sensors 112 feed the Perception and State Estimation 220 and State Prediction 221 components that make up the local model 126. The contents of the local model 126 are used to develop a local copy of the shared world model 240, which is then shared with other vehicles 110 via a model propagation function 280. The constraints, preconditions, and possible actions 260, along with the output from the situation assessment 222, are input to decision making 224, which in turn drives the controller 120. Model rendering 290 feeds the user interface.

[0100] Collaborative decisions to enter or leave autonomy

[0101] Information shared between vehicles, via vehicle-to-vehicle communication devices such as transceiver 116 or via shared world model 240, can be used to implement collaborative behaviors that may require approval from the companion vehicle before certain actions are taken.

[0102] For example, the transfer of control to or from an autonomy mode may be a collaborative behavior. To enable this collaborative behavior, the shared world model 240 may include relative distance and relative speed information for the vehicles, as well as information about a request from one vehicle (which may be the lead vehicle in the platoon) to another vehicle to join the platoon in an autonomy mode. The request is processed to assess compliance with preconditions for the transition of one or both vehicles to the autonomy mode. Some or all of the information needed to assess the preconditions may be provided within the shared world model 240 itself. For example, information related to the state of sensors in those individual vehicles may be stored within the world model 240. Preconditions may also be used to coordinate planned handshake maneuvers, where a request issued by a human in one of the vehicles is ultimately processed and possibly approved by a human in the other vehicle. As a result, the decision to enter autonomy is collaborative, involving a decision by an operator or autonomy logic in both of the vehicles, and based on the multi-component preconditions presented above.

[0103] 7 is an example flow for such a collaborative decision. In a first state 710, vehicle 110-1 is currently under human control and receives a request from another vehicle 110-2 to enter an autonomy mode. In state 712, logic within vehicle 110-1 determines whether two or more conditions exist that indicate an ability to safely transition.

[0104] If so, then in state 714, approval of the transition is communicated back to vehicle 110-2.

[0105] If not, then at state 716 a denial of the request to transition is communicated back to vehicle 110-2.

[0106] Implementation Options

[0107] The foregoing description of the exemplary embodiments illustrates and describes systems and methods for implementing novel arrangements and operations of sensors within a vehicle, but it is not intended to be exhaustive or limited to the precise forms disclosed.

[0108] The above described embodiments may be implemented in many different ways. In some cases, the various "computers" and / or "controllers" are "data processors" or "embedded systems" that may be implemented by one or more physical or virtual general-purpose computers having a central processor, memory, disks or other mass storage devices, communication interfaces, input / output (I / O) devices, and other peripherals. A general-purpose computer is transformed into a processor with improved functionality to execute program code, perform the processes described above, and provide improved operation. A processor may operate, for example, by loading software instructions and then executing the instructions to perform the functions described.

[0109] As known in the art, such a computer may contain a system bus, which is a set of hardware wired connections used for data transfer to components of a computer or processing system. The bus or buses are a shared conduit that connects different elements of a computer system (e.g., processor, disk storage, memory, input / output ports, network ports, etc.) and allows for the transfer of information. One or more central processing units are attached to the system bus and provide for the execution of computer instructions. Also attached to the system bus are typically I / O device interfaces for connecting various input and output devices (e.g., sensors, LiDAR, cameras, keyboards, touch displays, speakers, wireless radios, etc.) to the computer. A network interface allows the computer to connect to various other devices or systems attached to a network. The memory provides volatile storage for computer software instructions and data used to implement certain embodiments. A disk or other mass storage device provides non-volatile storage for computer software instructions and data used, for example, to implement various procedures described herein.

[0110] Certain portions may also be implemented as "logic" that performs one or more of the described functions. The logic may include hardware, such as hardwired logic circuitry, application specific integrated circuits, field programmable gate arrays, microprocessors, software, firmware, or combinations thereof. Some or all of the logic may include computer-executable instructions that may be stored in one or more tangible non-transitory computer-readable storage media and executed by a computer or data processing system. The computer-executable instructions may include instructions that implement one or more embodiments described herein. The tangible non-transitory computer-readable storage media may be volatile or non-volatile and may include, for example, flash memory, dynamic memory, removable disks, and non-removable disks.

[0111] Embodiments may therefore typically be implemented in hardware, firmware, software, or any combination thereof.

[0112] In some implementations, the computers or controllers performing the processes described above may be deployed, in whole or in part, within a cloud computing arrangement that makes available one or more physical and / or virtual data processing machines via on-demand access to a network of shared configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal administrative effort or service provider interaction.

[0113] Further, firmware, software, routines, or instructions may be described herein in terms of performing certain actions and / or functions. It should also be understood that the blocks and flow diagrams may contain more or fewer elements, be arranged differently, or be represented differently. Thus, it should be understood that such descriptions contained herein are merely for convenience, and that such actions actually result from a computing device, processor, controller, or other device that executes firmware, software, routines, instructions, etc.

[0114] Although a series of steps are described above with respect to a flow diagram, the order of the steps may be modified in other implementations. Additionally, steps, operations, and steps may be performed by additional or other modules or entities, which may be combined or separated to form other modules or entities. For example, although a series of steps may be described with respect to a certain figure, the order of the steps may be modified in other implementations consistent with the principles of the invention. Furthermore, non-dependent steps may be performed in parallel. Additionally, the disclosed implementations may not be limited to any specific combination of hardware.

[0115] No element, act, or instruction used herein should be construed as critical or essential to the present disclosure unless expressly described as such. Also, as used herein, the article "a" is intended to include one or more items. Where only one item is intended, the term "one" or similar language is used. Additionally, the phrase "based on" is intended to mean "based, at least in part, on," unless expressly stated otherwise.

[0116] The above description contains several exemplary embodiments. Although a particular feature may be disclosed above for only one of several embodiments, it should be understood that the particular feature may be combined with one or more other features of other embodiments as may be desired and advantageous for any given or particular application. Of course, for purposes of describing the innovations herein, it is not possible to describe every possible combination of components or methodologies, and one of ordinary skill in the art may now recognize that many further combinations and permutations are also possible in light of the above description. Also, the terms "includes" and "including" and variations thereof, to the extent that they are used in either the detailed description or the claims, are intended to be inclusive in a manner similar to the term "comprising."

[0117] Accordingly, the subject matter covered by this patent is intended to embrace all such alterations, modifications, equivalents, and variations that fall within the spirit and scope of the following claims.

Claims

1. 1. A method for operating an autonomous vehicle and controlling transitions into or out of an autonomy mode, comprising: Detecting a plurality of conditions, including autonomy logic readiness, driver readiness, traffic conditions, road conditions, ambient weather conditions, ambient lighting conditions, and compliance with an operational driving domain for autonomy; transitioning to or from the autonomous mode only when two or more of the conditions are satisfied; A method comprising:

2. Additionally, the plurality of conditions persist for a determined period of time, and the driver readiness condition comprises: The driver's seat is in the correct position, Weight is placed on the driver's seat, The steering wheel is moving, the steering wheel is subjected to a force; and The steering wheel is tilted; and The steering wheel is being gripped; and a fingerprint is detected on said steering wheel; The brake pedal is moving, The accelerator pedal is moving, The armrests are moving, a camera confirming that a driver is present or absent from said driver's seat; The method of claim 1 , comprising any two or more of:

3. 10. The method of claim 1, further comprising: ignoring input from the steering wheel in autonomy mode when the driver's seat is not in a driving position or when the driver's seat does not have sufficient weight to indicate that a driver is present in the seat.

4. The method of claim 1 , wherein the traffic conditions, the road conditions, the ambient weather conditions, the lighting conditions, and the operational driving domain restrictions are not impeding the transition.

5. the autonomous vehicle is part of a platoon with a second vehicle; the plurality of conditions further includes an approval originating from the second vehicle; 13. The method of claim 1, wherein transitioning into or out of the autonomy mode is thus a collaborative decision made between the autonomous vehicle and the second vehicle.

6. 1. An apparatus for operating an autonomous vehicle and controlling transitions into or out of an autonomy mode, comprising: one or more data processors; one or more computer readable media containing instructions; Equipped with The instructions, when executed by the one or more data processors, cause the one or more data processors to: Detecting a plurality of conditions, including autonomy logic readiness, driver readiness, traffic conditions, road conditions, ambient weather conditions, ambient lighting conditions, and compliance with an operational driving domain for autonomy; transitioning to or from the autonomous mode only when two or more of the conditions are satisfied; An apparatus for carrying out a process for

7. The plurality of conditions persists for a determined period of time, and the driver readiness condition is: The driver's seat is in the correct position, Weight is placed on the driver's seat, The steering wheel is moving, the steering wheel is subjected to a force; and The steering wheel is tilted; and The steering wheel is being gripped; and a fingerprint is detected on said steering wheel; The brake pedal is moving, The accelerator pedal is moving, The armrests are moving, a camera confirming that a driver is present or absent from said driver's seat; The apparatus of claim 6 , comprising any two or more of:

8. 7. The apparatus of claim 6, further comprising: a steering wheel input that is ignored in autonomy mode when the driver's seat is not in a driving position or when the driver's seat does not have sufficient weight to indicate that a driver is present in the seat.

9. The apparatus of claim 6 , wherein the traffic conditions, the road conditions, the ambient weather conditions, the lighting conditions, and the operational driving domain limitations are not impeding the transition.

10. the autonomous vehicle is part of a platoon with a second vehicle; the plurality of conditions further includes an approval originating from the second vehicle; 7. The apparatus of claim 6, wherein transitioning into or out of the autonomy mode is thus a collaborative decision made between the autonomous vehicle and the second vehicle.

Images