System and method for operating autonomous vehicle

Abstract

An autonomous vehicle (AV) includes features that allow the AV to comply with application regulations and regulations to perform safe driving operations. Exemplary embodiments disclosed herein provide for enhanced high precision operation of AV in low speed environments such as toll station facilities or busy traffic. An example method disclosed herein includes controlling a computer to identify a starting point of a toll station facility on a road and a plurality of toll lanes associated with the toll station facility; selecting a specific toll lane; determining the track of the AV extending through the specific toll lane; and in response to the autonomous vehicle reaching the starting point of the toll station facility, transmitting instructions to one or more driving subsystems of the AV through the subsystem interface, the instructions configured to cause the driving subsystems to operate together to cause the AV to travel in the trajectory.

Description

Technical Field

[0001] This patent document claims priority to and the benefit of U.S. Provisional Application No. 63 / 221,740, filed on July 14, 2021, entitled “SYSTEM AND METHOD FOR ANAUTONOMOUS VEHICLE,” U.S. Provisional Application No. 63 / 226,378, filed on July 28, 2021, entitled “SYSTEM AND METHOD FOR AN AUTONOMOUS VEHICLE,” U.S. Provisional Application No. 63 / 255,839, filed on October 14, 2021, entitled “SYSTEM AND METHOD FOR AN AUTONOMOUS VEHICLE,” and U.S. Provisional Application No. 63 / 273,868, filed on October 29, 2021, entitled “SYSTEM AND METHOD FOR ANAUTONOMOUS VEHICLE.” The entire disclosures of the foregoing applications are incorporated herein by reference as part of the disclosure of this application. Technical Field

[0003] The present disclosure relates generally to autonomous vehicles. More particularly, the present disclosure relates to properly operating an autonomous vehicle (AV) on public roads, highways, and locations with other vehicles or pedestrians. Background Art

[0004] Autonomous vehicle technology may provide a vehicle that is capable of safely navigating to a destination with limited or no driver assistance. Safe navigation of an autonomous vehicle (AV) from one point to another may include the ability to signal other vehicles, navigate around other vehicles on the shoulder or emergency lane, change lanes, properly steer within a lane, and navigate all sections or types of highway lanes. Autonomous vehicle technology may enable an AV to operate without requiring extensive learning or training from surrounding drivers by operating safely in a manner that is obvious, logical, or familiar to surrounding drivers and pedestrians. Summary of the invention

[0005] The systems and methods described herein can allow an autonomous vehicle (AV) to navigate from a first point to a second point. In some embodiments, the AV can navigate from the first point to the second point without the presence of a human driver in the AV and comply with instructions for safe and legal operation.

[0006] In one exemplary aspect, a method for operating an autonomous vehicle is described. The method includes: detecting, by a control computer located on the autonomous vehicle, a toll booth facility located along a road through which a route of the autonomous vehicle extends based on sensor data acquired through a subsystem interface between the control computer and one or more sensor subsystems of the autonomous vehicle. Detecting the toll booth facility includes: identifying a starting point of the toll booth facility on the road and a plurality of toll lanes associated with the toll booth facility. The method also includes: selecting, by the control computer, a particular toll lane from among the plurality of toll lanes associated with the toll booth facility. The method also includes: determining, by the control computer, a trajectory of the autonomous vehicle extending through the particular toll lane. The method also includes: in response to the autonomous vehicle reaching the starting point of the toll booth facility, transmitting, by the control computer through the subsystem interface, a plurality of instructions to one or more driving subsystems of the autonomous vehicle, the instructions being configured to cause the one or more driving subsystems of the autonomous vehicle to operate together to cause the autonomous vehicle to travel according to the trajectory until the autonomous vehicle is located at a toll booth associated with the particular toll lane.

[0007] In another exemplary aspect, another method for operating an autonomous vehicle is described. The method includes: collecting sensor data from one or more sensor subsystems of the autonomous vehicle through a subsystem interface by a control computer located on the autonomous vehicle, the sensor data capturing a plurality of vehicles located within a portion of a road on which the autonomous vehicle is operating. The method also includes: determining a classification of the plurality of vehicles representing a degree of vehicle traffic present within the plurality of vehicles. The classification is determined from the sensor data based on the number of the plurality of vehicles, the relative distances between the vehicles, and the average vehicle speed. The method also includes: when the autonomous vehicle is within a threshold distance of at least one of the plurality of vehicles, transmitting an instruction by the control computer through the subsystem interface to one or more driving subsystems of the autonomous vehicle, the instruction being configured to cause the one or more driving subsystems of the autonomous vehicle to operate to cause the autonomous vehicle to travel at a speed corresponding to the classification of the plurality of vehicles.

[0008] In yet another exemplary aspect, a system for operating an autonomous vehicle includes a computer including a processor configured to execute the methods described above and in this patent document.

[0009] In yet another exemplary aspect, the above method and the method described in this patent document are embodied in a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium includes code that, when executed by a processor, causes the processor to perform the method described above and in this patent document.

[0010] In another exemplary embodiment, a device configured or operable to perform the above method is disclosed. In yet another exemplary embodiment, a system is disclosed, which includes a computer located in a vehicle, the computer including a processor configured to implement the above disclosed method.

[0011] The above and other aspects and implementations thereof are described in more detail in the drawings, the description and the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For a more complete understanding of the present disclosure, reference is now made to the following brief description, taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals represent like parts.

[0013] Figure 1 A block diagram of an example vehicle ecosystem for an autonomous vehicle is illustrated.

[0014] Figure 2 A flow chart is shown for safely operating an autonomous vehicle given its health and / or surrounding environment.

[0015] Figure 3 A system is illustrated that includes one or more autonomous vehicles, a control center or supervisory system with a human operator (e.g., a remote center operator (RCO)), and an interface for third-party interaction.

[0016] Figure 4 An exemplary block diagram of a remote computer associated with a supervisory system is shown.

[0017] Figure 5 An example flow chart of example operations for operating an autonomous vehicle is shown.

[0018] Figure 6 An example flow chart of example operations for operating an autonomous vehicle is shown.

[0019] Figure 7A-7C A diagram illustrating example toll booth facilities located along a roadway navigable by an autonomous vehicle is illustrated.

[0020] Figure 8 A diagram illustrating different portions of an example toll booth facility is shown.

[0021] Figure 9A-9E An example road sign indicating the presence of a toll booth facility is illustrated.

[0022] Fig.10 A diagram illustrating an autonomous vehicle at a certain distance in front of a leading vehicle.

[0023] Fig.11 A diagram illustrating different portions of an example toll booth facility is shown. DETAILED DESCRIPTION

[0024] Vehicles traversing highways and roads are required by law to comply with laws and regulations during the safe operation of the vehicle. For autonomous vehicles (AVs), particularly autonomous tractor trailers, the ability to identify system failures and safely stop the vehicle can enable legal and safe operation of the vehicle. AVs such as commercial trucks and trucks with trailers often face road conditions and situations that private car passengers do not typically face, and may be subject to different vehicle regulations in such situations. For example, a highway sign indicating that commercial traffic needs to slow down on a winding road or enter an inspection area or weigh station may not apply to passenger cars. However, commercial autonomous vehicles should be aware of such signs and take appropriate actions based on the signs. Described below are systems and methods for the safe and legal operation of autonomous vehicles on roads, including performing maneuvers that cause the autonomous vehicle to comply with the law while signaling surrounding vehicles about its condition.

[0025] As will be appreciated, different operating environments for an autonomous vehicle may correspond to different levels of autonomous control and operation of the autonomous vehicle. Specifically, in some examples, an autonomous vehicle may operate in a high-density and crowded environment where a higher level of precision, control, and perception of surrounding objects may be required to safely navigate the autonomous vehicle. For example, in a toll booth facility, the navigation of an autonomous vehicle is challenged by many neighboring vehicles and many environmental obstacles located in a relatively small area that is more complex than other road segments. This navigation challenge is particularly amplified in examples where the autonomous vehicle is a large vehicle such as a truck. As another example, a heavy traffic environment along a road includes a large number of high-density vehicles, and with the limited operating space of the road, there are technical challenges for the autonomous vehicle to navigate between and among the vehicles. Therefore, the embodiments described herein address the technical challenges by enabling high-precision perception and operation of autonomous vehicles in low-speed, high-density environments.

[0026] This patent document describes an example vehicle ecosystem for an autonomous vehicle and driving-related operations of an autonomous vehicle in Part I below. Part II describes a control center or supervisory system for one or more autonomous vehicles, and various example features thereof and operations / processes performed thereby. Parts III to VI describe operations performed by autonomous vehicles in various scenarios. The example titles for the various sections below are used to facilitate understanding of the disclosed subject matter and do not limit the scope of the claimed subject matter in any way. Therefore, one or more features of one example section may be combined with one or more features of another example section.

[0027] The patent document uses many abbreviations and unusual terms. For example, "GNSS" or "GPS" can refer to a satellite navigation system (Global Navigation Satellite System and Global Positioning System, respectively); the abbreviation "EV" can be used when referring to emergency vehicles such as police cars, ambulances, fire trucks, tow trucks, etc.; the abbreviation "TTC" indicates "time to collision"; "NPC" refers to non-player characters and can include characters other than Figure 1 Any other vehicle other than the autonomous vehicle in the NPC. For example, any surrounding vehicles, motorcycles, bicycles, etc. that are manually driven or autonomously driven and may not communicate with the autonomous vehicle can be considered NPCs; "k-ramp" indicates a highway entrance / exit ramp with a specific configuration; "STV" indicates a stopped vehicle; "ELV" can indicate an abandoned or scrapped vehicle, such as an abandoned vehicle on the side of the road; "OBO" can refer to the on-board operator of the autonomous vehicle or a human operator who temporarily takes over control to assist during the inspection, start and / or end of the journey or mission of the autonomous vehicle; and "LC" can be an abbreviation for lane change.

[0028] I. Example Ecosystem for Autonomous Vehicles

[0029] Figure 1 A system 100 including an autonomous vehicle 105 is shown. The autonomous vehicle 105 may include a tractor for a semi-trailer truck. The autonomous vehicle 105 includes a plurality of vehicle subsystems 140 and an onboard control computer 150. The plurality of vehicle subsystems 140 include a vehicle driving subsystem 142, a vehicle sensor subsystem 144, and a vehicle control subsystem 146. The vehicle driving subsystem may include an engine or motor, wheels and tires, a transmission, an electrical subsystem, and a power subsystem. The engine of the autonomous truck may be an internal combustion engine, a fuel cell powered electric engine, a battery powered electric engine, a hybrid engine, or any other type of engine capable of moving the wheels on which the autonomous vehicle 105 moves. The autonomous vehicle 105 has a plurality of motors or actuators to drive the wheels of the vehicle, so that the vehicle driving subsystem 142 includes two or more electric drive motors. The transmission may include a continuously variable transmission or a set number of gears that converts the power generated by the engine into a force that drives the wheels of the vehicle. The vehicle driving subsystem may include an electrical system that monitors and controls the distribution of current to components within the system, including pumps, fans, and actuators. The power subsystem of the vehicle driving subsystem may include components that regulate the vehicle power supply. The vehicle driving subsystem 142 may operate precisely based on instructions (such as commands) transmitted from the onboard control computer 150. For example, the onboard control computer 150 controls the operation of the vehicle driving subsystem 142 via commands and instructions transmitted to the vehicle driving subsystem 142.

[0030] The vehicle sensor subsystem 144 may include sensors for general operation of the autonomous vehicle 105, including sensors that would indicate a malfunction in the autonomous vehicle or another reason that caused the autonomous vehicle to perform a limited or minimal risk condition (MRC) maneuver or an emergency driving maneuver. Figure 1 The MRC maneuver can be performed by sending a command that causes the autonomous vehicle to turn to the roadside along the trajectory and apply the brakes so that the autonomous vehicle can safely stop at the roadside. Sensors used for general operation of autonomous vehicles may include cameras, temperature sensors, inertial sensors (IMU), global positioning systems, light sensors, LIDAR systems, radar systems, and wireless communications.

[0031] A sound detection array, such as a microphone or microphone array, may be included in the vehicle sensor subsystem 144. The microphones of the sound detection array are configured to receive audio indications of the presence of authorities or instructions from authorities, including sirens and commands such as "pull over". These microphones are mounted or located on the exterior of the vehicle, particularly on the exterior of the towing vehicle portion of the autonomous vehicle 105. The microphones used may be of any suitable type, mounted so that they are effective both when the autonomous vehicle 105 is stationary and when traveling at normal driving speeds.

[0032] Cameras included in the vehicle sensor subsystem 144 may be rear-facing so that flashing lights from emergency vehicles may be observed from around the self-driving truck 105. These cameras may include video cameras, cameras with filters for specific wavelengths, and any other cameras suitable for detecting emergency vehicle lights based on color, flash, or both color and flash.

[0033] The vehicle control subsystem 146 may be configured to control the operation of the autonomous vehicle or truck 105 and its components. Thus, the vehicle control subsystem 146 may include various elements, such as an engine power output subsystem, a braking unit, a navigation unit, a steering system, and an autonomous control unit. The engine power output may control the operation of the engine, including the torque produced or the horsepower provided, and provide control over the gear selection of the transmission. The braking unit may include any combination of mechanisms configured to cause the autonomous vehicle 105 to decelerate. The braking unit may use friction to slow the wheels in a standard manner. The braking unit may include an anti-lock braking system (ABS) that may prevent the brakes from locking when the brakes are applied. The navigation unit may be any system configured to determine the driving path or route of the autonomous vehicle 105. The navigation unit may also be configured to dynamically update the driving path while the autonomous vehicle 105 is in operation. In some embodiments, the navigation unit may be configured to merge data from a GPS device and one or more predetermined maps in order to determine the driving path of the autonomous vehicle 105. The steering system may represent any combination of mechanisms operable to adjust the heading of the autonomous vehicle 105 in an autonomous driving mode or a driver-controlled mode.

[0034] The autonomous control unit may represent a control system configured to identify, evaluate, and avoid or otherwise negotiate potential obstacles in the environment of the autonomous vehicle 105. In general, the autonomous control unit may be configured to control the autonomous vehicle 105 for operation without a driver or to provide driver assistance in controlling the autonomous vehicle 105. In some embodiments, the autonomous control unit may be configured to incorporate data from a GPS device, RADAR, LiDAR (e.g., LIDAR), camera, and / or other vehicle subsystems to determine a driving path or trajectory for the autonomous vehicle 105. Autonomous control may activate systems that the autonomous vehicle 105 has that are not present in traditional vehicles, including those systems that may allow the autonomous vehicle to communicate with surrounding drivers or send signals to surrounding vehicles or drivers to ensure safe operation of the autonomous vehicle.

[0035] The onboard control computer 150 may be referred to as a VCU, which includes a vehicle subsystem interface 160, a driving operation module 168, one or more processors 170, a compliance module 166, a memory 175, and a network communication subsystem 178. This onboard control computer 150 controls many (if not all) operations of the autonomous vehicle 105 in response to information from various vehicle subsystems 140 that can be received through the vehicle subsystem interface 160. One or more processors 170 perform operations that allow the system to determine the health of the autonomous vehicle, such as whether the autonomous vehicle has failed or encountered a situation that requires maintenance or deviates from normal operation and issue instructions. Data from the vehicle sensor subsystem 144 is provided to the VCU 150 (e.g., via the vehicle subsystem interface 160) so that the state of the autonomous vehicle can be determined. The compliance module 166 determines what actions the autonomous vehicle 105 should take to operate in accordance with applicable (e.g., local) regulations. Data from other vehicle sensor subsystems 144 can be provided to the compliance module 166 so that the best course of action can be appropriately determined and executed given the state of the autonomous vehicle. Alternatively or additionally, the compliance module 166 may determine a course of action in conjunction with another operation or control module, such as a driving operation module 168. The onboard control computer 150 may then determine instructions and transmit the instructions (e.g., via the vehicle subsystem interface 160) to the vehicle driving subsystem 142 to cause the vehicle driving subsystem 142 to operate to cause certain operations of the autonomous vehicle.

[0036] The memory 175 may also contain additional instructions, including instructions for transmitting data to, receiving data from, interacting with, or controlling information of one or more of the vehicle driving subsystem 142, the vehicle sensor subsystem 144, and the vehicle control subsystem 146, including the autonomous control system. The vehicle control computer (VCU) 150 may control the functions of the autonomous vehicle 105 based on inputs received from various vehicle subsystems (e.g., the vehicle driving subsystem 142, the vehicle sensor subsystem 144, and the vehicle control subsystem 146). In addition, the VCU 150 may send information to the vehicle control subsystem 146 to guide the trajectory, speed, signaling behavior, etc. of the autonomous vehicle 105. For example, the compliance module 166 and / or the driving operation module 168 in the VCU 150 may send instructions to one or more devices of the autonomous vehicle 105. The one or more devices may include one or more devices in the vehicle driving subsystem 142, the vehicle sensor subsystem 144, or the vehicle control subsystem 146. These instructions sent by the VCU 150 to one or more devices in the autonomous vehicle 105 are configured to implement and cause certain operations and actions to be performed by the one or more devices in accordance with the instructions. The operations generated by the instructions sent to one or more devices can together form driving-related operations performed by the autonomous vehicle 105. For example, the VCU 150 can send instructions to the motor in the steering system, to the actuator in the brake unit, and / or to the engine to cause one or more devices to operate according to the instructions, so that the autonomous vehicle 105 performs a maneuver, or turns to follow the trajectory and / or accelerate / decelerate at a speed specified (e.g., via the instructions). Therefore, the instructions provided by the VCU 150 can allow the autonomous vehicle 105 to follow the trajectory to turn from the current lane in which the autonomous vehicle 105 is operating to an adjacent lane on the road or to a shoulder area (e.g., an emergency stop lane or area on the side of the road). The autonomous vehicle control subsystem can receive the action plan to be taken from the compliance module 166 of the VCU 150, and thus relay the instructions to other subsystems to execute the action plan. In the following Sections III to VI, this patent document describes an autonomous vehicle or system performing certain functions or operations. These functions and / or operations described may be performed by the compliance module 166 and / or the driving operation module 168.

[0037] Figure 2 A flow chart for safely operating an autonomous vehicle (AV) in view of the health of the autonomous vehicle and / or the surrounding environment is shown. Although the figure depicts functional steps in a particular order for illustrative purposes, the process is not limited to any particular order or arrangement of steps. Those skilled in the relevant art will appreciate that the various steps depicted in the figure may be omitted, rearranged, combined, and / or adapted in various ways.

[0038] like Figure 2 As shown in , at step 205, the vehicle sensor subsystem 144 receives visual, auditory, or visual and auditory signals indicating the environmental conditions of the autonomous vehicle, as well as vehicle health or sensor activity data. As in step 210, these visual and / or auditory signal data are transmitted from the vehicle sensor subsystem 144 to the vehicle control computer system (VCU) 150. In step 215, any one of the driving operation module and the compliance module receives the data transmitted from the vehicle sensor subsystem. Then, in step 220, one or both of these modules determine whether the current state of the autonomous vehicle allows it to proceed in the usual manner, or whether the autonomous vehicle needs to change its plan to prevent damage or injury or allow for repairs. Information indicating the need to change the autonomous vehicle's course of action may include an indicator of a sensor failure; an indicator of a failure in the engine, brakes, or other components that may be necessary for the operation of the autonomous vehicle; a determination of visual indications from authorities, such as flares, cones, or signs; a determination of the presence of authority personnel on the road; a determination that a law enforcement vehicle is approaching the autonomous vehicle on the road, including from which direction; and a determination that a law enforcement vehicle or emergency vehicle is moving away from the autonomous vehicle or traveling on a different road from the autonomous vehicle. In step 225, this information indicating the need to change the autonomous vehicle's course of action or driving-related operation may be used by the compliance module to formulate a new course of action to be taken, which takes into account the health and surrounding environment of the autonomous vehicle. The course of action to be taken may include slowing down, stopping, moving into the shoulder of the road, changing route, changing lanes while staying on the same regular route, etc. The course of action to be taken may include initiating communication with any supervisory or human-machine interaction system present on the autonomous vehicle. Then, in step 230, the course of action to be taken may be transmitted from the VCU 150 to the autonomous control system. Then, in step 235 , the vehicle control subsystem 146 causes the autonomous vehicle 105 to operate according to the action plan to be taken received from the VCU 150 .

[0039] It should be understood that the specific order or hierarchy of steps in the processes disclosed herein is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in these processes can be rearranged while still remaining within the scope of the present disclosure. The attached method claims present the elements of the various steps in an example order, but are not meant to be limited to the specific order or hierarchy presented.

[0040] II. Autonomous Vehicle Supervision System

[0041] Figure 3A system 300 is illustrated that includes one or more autonomous vehicles 105, a control center or supervisory system 350 with a human operator 355, and an interface 362 for third party 360 interactions. The human operator 355 may also be referred to as a remote center operator (RCO). Communications between the autonomous vehicles 105, the supervisory system 350, and the user interface 362 occur over a network 370. In some instances, where not all autonomous vehicles 105 in a fleet are able to communicate with the supervisory system 350, the autonomous vehicles 105 may communicate with each other over the network 370 or directly. As described with respect to FIG. Figure 1 As described, the VCU 150 of each autonomous vehicle 105 may include a module 178 for network communications.

[0042] The self-driving trucks may communicate with the supervisory system. The supervisory system may be used for a variety of purposes, including: tracking the progress of one or more self-driving vehicles (e.g., self-driving trucks); tracking the progress of a fleet of self-driving vehicles; sending maneuver instructions to one or more self-driving vehicles; monitoring the health of the self-driving vehicle(s); monitoring the status of the cargo of each self-driving vehicle in contact with the supervisory system; facilitating communications between third parties (e.g., law enforcement, customers who are transporting cargo) and each or specific self-driving vehicle; allowing tracking of specific self-driving trucks in communication with the supervisory system (e.g., third-party tracking of a portion of vehicles in a fleet); scheduling maintenance services for self-driving vehicles (e.g., oil changes, refueling, maintaining levels of other fluids); alerting affected self-driving vehicles of traffic or weather changes that may adversely affect routes or delivery plans; pushing updates to self-driving trucks wirelessly to keep all components up to date; and other purposes or functions that improve the safety of self-driving vehicles, their cargo, and their surroundings. The supervision system may also determine performance parameters of the autonomous vehicle or autonomous truck, including any of the following: data logging frequency, compression rate, location, data type; communication priority; maintenance frequency of the autonomous vehicle (e.g., number of miles between maintenance); when to perform a minimum risk condition (MRC) maneuver while monitoring the vehicle's progress during the maneuver; when to hand over control of the autonomous vehicle to a human driver (e.g., at a destination yard, in a rescue situation); ensuring that the autonomous vehicle passes pre-trip inspection; ensuring that the autonomous vehicle performs or complies with legal requirements at checkpoints and weigh stations; ensuring that the autonomous vehicle performs or follows instructions from humans at roadblocks, crosswalks, intersections, construction, or accident sites; and so on.

[0043] Among some of the functions performed by the monitoring system or command center is the ability to relay wireless real-time weather updates to autonomous vehicles in a monitored fleet. Wireless weather updates may be pushed to all autonomous vehicles in the fleet, or may be pushed only to autonomous vehicles currently on a mission to deliver cargo. Alternatively or additionally, fleet vehicles currently on a trajectory or route within or within a predetermined radius leading to a severe weather event may be given priority to push or transmit wireless weather reports.

[0044] Another function that may be included in the functions performed by the supervisory system or command center is the transmission of trailer metadata to the autonomous vehicle's computing unit (VCU) before the cargo transport mission begins. The trailer metadata may include the type of cargo being transported, the cargo weight, temperature thresholds for the cargo (e.g., the temperature inside the trailer should not be below or above a predetermined temperature), time sensitivity, acceleration / deceleration sensitivity (e.g., due to the fragility of the cargo, violent movements may be undesirable), the weight distribution of the trailer along the length of the trailer, the packaging or stacking of the cargo within the trailer, and so on.

[0045] The supervisory system or command center may be operated by one or more persons, also referred to as operators or remote center operators (RCOs). The operator may set thresholds for autonomous vehicle health parameters so that when the autonomous vehicle reaches or exceeds the threshold, preventive measures may be taken. Examples of vehicle health parameters for which the operator may establish thresholds may include any of the following: fuel level; oil level; mileage driven since the last maintenance; low tire pressure detected; washer fluid level; brake fluid level; responsiveness of the steering and braking subsystems; diesel exhaust fluid (DEF) level; communication capabilities (e.g., lack of responsiveness); positioning sensor capabilities (e.g., GPS, IMU failure); collision detection (e.g., vehicle collision); perception sensor capabilities (e.g., camera, LIDAR, radar, microphone array failure); computing resource capabilities (e.g., VCU or ECU failure or lack of responsiveness, abnormal temperature of the computing unit); angle between the tractor and trailer in a towing situation (e.g., tractor-trailer, 18-wheeler, or semi-trailer truck); unauthorized entry of a living being (e.g., a human or animal) into the interior of an autonomous truck; and the like. Preventive actions may include: performing a minimum risk condition (MRC) maneuver, seeking service, or rerouting off the highway or other routes that may relieve the autonomous vehicle. Autonomous vehicles whose system health data meets or exceeds a threshold set at the supervisory system or by an operator may receive instructions automatically sent from the supervisory system to perform preventive actions.

[0046] An operator may be aware of situations that affect one or more autonomous vehicles communicating with or monitored by a supervisory system, while the affected autonomous vehicle(s) may not be aware. Such situations may include: irregular or sudden changes in traffic flow (e.g., traffic jams or accidents); sudden changes in weather; sudden changes in visibility; emergencies (e.g., fires, sinkholes, bridge failures); power outages that affect signal lights; unexpected road construction; large or obscure road debris (e.g., objects that cannot be identified by the autonomous vehicle); law enforcement activities on the road (e.g., car chases or road clearing activities); and the like. These types of situations that may not be detected by the autonomous vehicle may be brought to the attention of the supervisory system operator through traffic reports, law enforcement communications, data from other vehicles communicating with the supervisory system, reports from drivers of other vehicles in the area, and similar distributed information venues. Such situations may not be detected by the autonomous vehicle due to limitations of the sensor system or due to the inability to access information distribution devices (e.g., inability to communicate directly with meteorological agencies). The operator at the supervisory system may push such information to the affected autonomous vehicle communicating with the supervisory system. The affected autonomous vehicle may change its route, trajectory, or speed in response to the information pushed from the supervisory system. In some instances, information received by the supervisory system may trigger a threshold condition indicating that an MRC (Minimum Risk Condition) maneuver is necessary; alternatively or additionally, an operator may evaluate the situation and determine that the affected autonomous vehicle should perform an MRC maneuver and then send such instructions to the affected vehicle. In these cases, each autonomous vehicle receives information or instructions from the supervisory system, or the supervisory system operator uses its onboard computing unit (e.g., VCU) to determine how to proceed safely, including performing an MRC maneuver, including pulling over or stopping.

[0047] Other interactions that a remote center operator (RCO) may have with an autonomous vehicle or fleet of autonomous vehicles include any of the following: pre-planned event avoidance; real-time route information updates; real-time route feedback; tracking connection status; first responder communication request processing; notification of aggressive vehicles in the vicinity; identification of construction interval changes; the state of the autonomous vehicle relative to its operational design domain (ODD), such as alerting the RCO when the autonomous vehicle approaches or enters a state outside the ODD; RCO notification when the autonomous vehicle is within a threshold distance from a toll booth, and appropriate instructions / communications may be sent to the autonomous vehicle or toll agency to allow the autonomous vehicle to bypass the toll booth; RCO notification when the autonomous vehicle bypasses a toll booth; RCO notification when the autonomous vehicle is within a threshold distance from a weigh station, and appropriate instructions / communications may be sent to the autonomous vehicle or appropriate agency to allow the autonomous vehicle to bypass the weigh station; when the autonomous vehicle bypasses a weigh station RCO notification of when a vehicle stops; notification from the RCO to the autonomous vehicle regarding the dispatch or need for refueling or maintenance; RCO authorization for third-party access to the cab of the autonomous vehicle; the ability for the RCO to start / restart the automated driving system (ADS) on the vehicle; the ability for an administrator (who may be the RCO) to set roles for system users, including ground personnel, law enforcement personnel, and third parties (e.g., customers, shippers); RCO support for communication with the service maintenance system of fleet vehicles; notification of acceleration events from the autonomous vehicle to the RCO; instructions from the RCO to the autonomous vehicle to continue the mission even when communications are interrupted; RCO monitoring of the autonomous vehicle during and after the execution of the MRC maneuver; support for continuous communication between the autonomous vehicle and the yard operator at the facility where the autonomous vehicle is preparing to start the mission or the autonomous vehicle is expected to arrive; monitoring of the software system on the autonomous vehicle by the supervisory system and receipt of alerts by the supervisory system when the software system is compromised; etc.

[0048] The supervisory system or command center may allow third parties to interact with the supervisory system operator, with the self-driving truck, or with both the human system operator and the self-driving truck. The third party may be a customer who is transporting freight, a law enforcement or emergency service provider, or a person who assists the self-driving truck when service is needed. In its interactions with third parties, the supervisory system may identify different levels of access so that a customer concerned about the timing or progress of a shipment may only be able to view status updates of the self-driving truck, or may be able to view the status and provide information to the supervisory system about which parameters are prioritized (e.g., speed, economy, maintaining the original planned route). By providing input to the supervisory system about parameter priorities, customers can influence the route and / or operating parameters of the self-driving truck.

[0049] The actions that an autonomous vehicle, and in particular an autonomous truck, as described herein may be configured to perform to safely traverse a course while complying with applicable rules, laws, and regulations may include those actions that are successfully completed by an autonomous truck driven by a human. These actions or maneuvers may be described as being characteristic of the truck because these actions may be executable programming stored on the VCU 150 (vehicle control computer unit). These actions or features may include actions or features related to reactions to detecting certain types of conditions or objects, such as: appropriate movement on a hill; appropriate movement on a curve, appropriate movement at a highway exit; appropriate movement or action in response to detecting one or more stopped vehicles, detecting one or more vehicles in an emergency lane; detecting an emergency vehicle that may be approaching the autonomous vehicle with flashing lights; movement in response to detecting one or more large vehicles approaching, adjacent to, or about to be adjacent to the autonomous vehicle; movement or action in response to pedestrians, cyclists, etc. after identifying and classifying these actors; movement or action for curved or inclined portions of the road; and / or movement in response to identifying on- and off-ramps on a highway or freeway, encountering intersections; performing merges into traffic in adjacent lanes or areas of traffic; detecting the need to clean one or more sensors and cleaning the appropriate sensors; identifying law enforcement / emergency vehicles and personnel and complying with related instructions or regulations; performing minimum risk condition maneuvers when needed; and identifying road debris or unknown objects; etc. Other features of the autonomous truck may include those actions or features required for any type of maneuver, including those required to complete the counter-action features or actions listed above.

[0050] Supporting features may include: safely changing lanes; operating turn lights on the autonomous truck to alert other drivers of the intended change in motion; causing the autonomous truck to bias in its lane (e.g., move away from the center of the lane to accommodate the motion or size of neighboring vehicles or nearby objects); the ability to maintain an appropriate following distance; the ability to turn right and left with appropriate signals and movements, and more. Supporting features may also include: the ability to navigate roundabouts; the ability to use onboard lights for appropriate illumination as required by ambient light and in compliance with local laws; the minimum amount of deceleration required to apply any given maneuver; determining position at all times; dynamic vehicle control that adapts to trailer load distribution, excluding wheel adjustments; starting (reaching target speed), accelerating, stopping and yielding; operating on roads with bumps and potholes; entering minimum risk conditions (MRC) on the shoulder; accessing local laws and regulations based on location along the route; operating on asphalt, concrete, mixed grade, scraped pavement and gravel; the ability to operate in response to metered lights / signals at entrance ramps; operating on roads with a width up to a predetermined width; being able to stop at crosswalks and maintain adequate stopping distance; navigating two-way left turn lanes; operating on roads with entrance and exit ramps; communicating with other drivers using the vehicle horn; etc. One or more features and / or one or more supporting features described in this patent document may be combined and may be performed by an onboard control computer in an autonomous truck.

[0051] In some embodiments, actions or features may be considered supporting features and may include: speed control; the ability to maintain a straight path; etc. These supporting features, as well as the reactive features listed above, may include controlling or changing steering, engine power output, brakes, or other vehicle control subsystems 146. The reactive features and supporting features listed above are discussed in more detail below.

[0052] Figure 4 An exemplary block diagram of a remote computer 400 associated with a supervisory system is shown. Figure 3 350 in FIG. 7 ) may include a remote computer 400, which may be located at a fixed location outside the autonomous vehicle. In this patent document, the description related to the operations performed by the supervision system may be performed by a supervision module (shown as 425 in FIG. 7 ) in the remote computer 400. The remote computer 400 includes at least one processor 410 and a memory 405 having instructions stored thereon. These instructions, when executed by the processor 410, configure the remote computer 400 to perform operations related to the supervision module 425, wherein the supervision module 425 may perform operations related to at least Figures 1 to 3The remote computer 400 may include one or more servers. The transmitter 415 transmits or sends information or data to one or more autonomous vehicles, and the receiver 420 receives information or data from one or more autonomous vehicles.

[0053] III. Cabin Camera View

[0054] The autonomous vehicle may include one or more cameras, sensors, imaging devices, etc. positioned inside the cabin of the autonomous vehicle, and the cameras, sensors, imaging devices, etc. are configured to collect sensor data that captures the interior environment of the cabin. For example, the collected sensor data may include image or video data for monitoring one or more human operators of the autonomous vehicle located in the cabin. In some examples, image processing operations may be automatically performed to blur or block the operator's face to protect the operator's privacy. As another example, the collected sensor data may include temperature data for monitoring the temperature of the cabin. As yet another example, the collected sensor data may include gas composition data for detecting fault conditions such as engine smoke, exhaust leaks, or faults. The gas composition data may include CO (carbon monoxide) levels, VOx (volatile organic components) levels, and the like.

[0055] In some embodiments, the collected sensor data may be transmitted to a computer or autonomous driving system located on the autonomous vehicle, which is configured to relay the collected sensor data to a supervisory system or remote computer (e.g., Figure 3 Supervision system in 350, Figure 4 400 in the remote computer 400). In some embodiments, the onboard computer or system of the autonomous vehicle is configured to collect image or video data of the interior of the vehicle cabin and provide a real-time stream to the supervision system so that the remote center operator (RCO) can monitor the operator located inside the vehicle cabin. For example, through the real-time stream, the image or video data is transmitted to the supervision system within a predetermined time (e.g., 0.5 seconds, 1 second, 2 seconds, 5 seconds, 10 seconds) when the image or video data is collected by the camera, sensor, imaging device, etc. In some embodiments, the real-time stream can be provided to other remote computers associated with other relevant third parties, such as a staffing entity that contracts with the operator located in the vehicle cabin, a customer entity to which the autonomous vehicle travels, a law enforcement entity, and the like. In some embodiments, the autonomous vehicle can provide a real-time stream in response to receiving a request from the supervision system to view the interior of the vehicle cabin.

[0056] IV. Weather-Related Vehicle Operations

[0057] In response to the relevant weather conditions or weather conditions located along the planned route of the autonomous vehicle, the autonomous vehicle may be rerouted or caused to perform certain operations. The autonomous vehicle may be caused to reroute or perform certain operations based on commands received from a supervisory system or a remote computer, which may be configured to monitor and analyze weather conditions. For example, the supervisory system or remote computer may be configured to interface with a third-party entity that provides or publishes weather data. The supervisory system may be configured to automatically collect real-time weather data via an application programming interface (API) and identify autonomous vehicles associated with the real-time weather data.

[0058] Based on the severity of the determined or predicted weather condition, the supervisory system may determine an alternate route for the autonomous vehicle. For example, the supervisory system may compare a severity metric (e.g., determined by the supervisory system based on acquired weather data, determined by a weather data provider that generates the weather data) to a threshold severity, and based on the severity metric satisfying the threshold severity, the supervisory system may determine an alternate route. The alternate route may be configured to completely bypass an area subject to severe weather conditions or an area predicted to be subject to severe weather conditions. The alternate route may be configured based on the movement of predicted severe weather conditions.

[0059] In some examples, the autonomous vehicle may be (commanded to) maintain its original route but perform other actions to safely navigate the adverse weather conditions. For example, the supervisory system may command the autonomous vehicle to travel at a lower speed and may establish a maximum speed that is a predetermined amount lower than the speed limit of the road. As another example, the supervisory system may command the autonomous vehicle to minimize the number of lane changes along its original route, and accordingly, for example, the autonomous vehicle may maintain the same lane along the original route. Thus, for example, the supervisory system may limit certain operations or command the autonomous vehicle to minimize certain operations based on weather conditions relevant to the autonomous vehicle.

[0060] V. Heavy Traffic Operation

[0061] Steering Figure 5 , a flow chart illustrating the operation of an example method for operating an autonomous vehicle is provided. The example method may be performed to operate the autonomous vehicle when the autonomous vehicle is near a high-density vehicle group, such as heavy traffic, traffic jams, or traffic queues. For example, the example method may be performed when the autonomous vehicle is passing adjacent to a high-density vehicle group, when the autonomous vehicle is approaching a high-density vehicle group from behind, when the autonomous vehicle is within a high-density vehicle group, and so on.

[0062] At operation 502, sensor data capturing a plurality of vehicles is collected. The plurality of vehicles are located within a portion of a road on which the autonomous vehicle is operating. In some examples, the portion of the road may be one of a plurality of lanes of the road, such as a lane in which the autonomous vehicle is located, a lane of a road adjacent to a lane in which the autonomous vehicle is located, a toll lane of a toll booth facility, and the like. In other examples, the portion of the road may be a distance range along the road ahead of a current location of the autonomous vehicle, a distance range along the road on which the autonomous vehicle is currently located, and the like.

[0063] At operation 504, a classification of the plurality of vehicles is determined. The classification of the plurality of vehicles indicates a degree of vehicle traffic or a degree of vehicle density present within the plurality of vehicles. The classification is determined from the sensor data based on the number of the plurality of vehicles, the relative distances between the vehicles (e.g., average vehicle-to-vehicle distance), and the average vehicle speed of the plurality of vehicles.

[0064] At operation 506, when the autonomous vehicle is within a threshold distance of at least one of the plurality of vehicles, the autonomous vehicle is operated at a speed according to the classification of the plurality of vehicles. For example, when the autonomous vehicle is within a threshold distance of at least one of the plurality of vehicles, the control computer transmits instructions to one or more driving subsystems of the autonomous vehicle through a subsystem interface, and the instructions are configured to cause the one or more driving subsystems to operate to cause the autonomous vehicle to travel at a speed corresponding to the classification of the plurality of vehicles.

[0065] In some embodiments, a plurality of vehicles or at least one vehicle is located in front of a current position of the autonomous vehicle, and the transmitted instructions include instructions configured to cause the driving subsystem to operate to cause the autonomous vehicle to include causing the autonomous vehicle to decelerate to a certain speed. For example, the autonomous vehicle may be caused to decelerate at a rate based on a threshold distance. In some embodiments, the speed is determined based on a sensor uncertainty value associated with a sensor that is located on the autonomous vehicle and via which the sensor data is collected.

[0066] In some embodiments, the example method further includes receiving a map update configured to cause a determination of a classification of a vehicle located within the portion of the road. In some embodiments, the map update may be received from a remote computer (e.g., Figure 4 In some embodiments, the method further comprises providing an indication of the classification of the plurality of vehicles to the remote computer as part of the map survey update. In some embodiments, the method further comprises providing an indication of the classification of the plurality of vehicles to a second autonomous driving vehicle associated with a route extending through the portion of the road.

[0067] In some embodiments, the example method also operates a warning light of the autonomous vehicle before the autonomous vehicle is within a threshold distance of at least one of the plurality of vehicles. For example, the warning light is operated during deceleration of the autonomous vehicle.

[0068] In some embodiments, the portion of the road may include a toll booth facility, and various operations related to interacting with the toll booth facility may be performed in conjunction with the operations disclosed in this section. For example, the example method may also include identifying a starting point of the toll booth facility and a plurality of toll lanes associated with the toll booth facility, and selecting a particular toll lane from the plurality of toll lanes. The starting point of the toll booth facility may be identified as a point along the road at which a pair of lateral road boundaries have a divergence angle greater than a predetermined threshold angle, and the particular toll lane is selected based on the presence of a toll collection device located on the autonomous vehicle. The portion of the road may be a toll lane of the toll booth facility, and the speed may be a complete stop based on at least one of the plurality of vehicles coming to a complete stop at a toll booth associated with the toll lane.

[0069] V.(a) Definition of heavy traffic

[0070] When various conditions are met, the autonomous vehicle can identify heavy traffic on a road such as a highway. In some embodiments, the autonomous vehicle identifies heavy traffic when the following three conditions are met: (i) the vehicle is located in every lane of the road, excluding lanes leading to road exits or lanes blocked due to construction; (ii) the average speed of vehicles in these lanes is less than or equal to a predetermined speed (e.g., 20 miles per hour, 30 miles per hour, 40 miles per hour); and (iii) the average bumper-to-bumper longitudinal distance between consecutive vehicles in each of these lanes is less than a predetermined distance (e.g., 15 meters, 20 meters, 25 meters, 30 meters, 35 meters). The predetermined speed compared to the average speed of the vehicle can be based on the speed limit of the road.

[0071] V.(b) Definition of Traffic Congestion

[0072] When various conditions are met, the autonomous vehicle can identify traffic congestion on a road such as a highway. In some embodiments, the autonomous vehicle identifies traffic congestion when the following three conditions are met: (i) the vehicle is located in each lane of the road, excluding lanes leading to road exits or lanes blocked due to construction; (ii) the average speed of vehicles in these lanes is less than or equal to a predetermined speed (e.g., 8 miles per hour, 10 miles per hour, 12 miles per hour, 15 miles per hour); and (iii) the average bumper-to-bumper longitudinal distance between consecutive vehicles in each of these lanes is less than a predetermined distance (e.g., 8 meters, 10 meters, 12 meters, 14 meters). The predetermined speed compared to the average speed of the vehicle can be based on the speed limit of the road. In some embodiments, the predetermined speed for identifying traffic congestion is lower than the predetermined speed for identifying heavy traffic, and the predetermined bumper-to-bumper distance for identifying traffic congestion is lower than the predetermined speed for identifying heavy traffic. Therefore, in some embodiments, traffic congestion is identified as a road traffic condition with a vehicle density higher than heavy traffic.

[0073] V.(c) Traffic Queuing Definition

[0074] The autonomous vehicle may identify a traffic queue on a road, such as a highway, when various conditions are met. In some embodiments, the autonomous vehicle identifies a traffic queue when the following three conditions are met: (i) a plurality of vehicles are located in any particular lane of the road, including a lane leading to an exit from the road; (ii) the average speed of the vehicles in the lane is less than or equal to a predetermined speed (e.g., 8 miles per hour, 10 miles per hour, 12 miles per hour, 15 miles per hour); and (iii) the average bumper-to-bumper longitudinal distance between consecutive vehicles in the lane is less than a predetermined distance (e.g., 8 meters, 10 meters, 12 meters, 14 meters).

[0075] In some embodiments, the autonomous vehicle can update the identification of multiple traffic queues in adjacent lanes on the road to an identification of traffic congestion. In some embodiments, the autonomous vehicle identifies the traffic congestion based on the traffic queues for each lane of the road.

[0076] V.(d) Surrounding vehicles

[0077] When identifying traffic jams, heavy traffic, and / or traffic queues, the autonomous vehicle may consider the number of vehicles, the spacing between vehicles, and the speeds at which the vehicles are traveling.

[0078] V.(e) Detection distance

[0079] Unless the oncoming vehicle and the road are partially obscured due to horizontal and / or vertical curvature, the autonomous vehicle may be able to detect the oncoming vehicle from at least a predetermined distance (e.g., 200 m, 250 m, 300 m) or at a predetermined rate (e.g., -1.25 m / s 2 、-1.5m / s 2 、-1.75m / s 2 、-2.0m / s 2 ) to identify or sense heavy traffic, traffic jams, and traffic queues from at least a predetermined distance or a distance required to reach a destination. After identifying heavy traffic, traffic jams, and traffic queues within the detection distance of the autonomous vehicle, the autonomous vehicle can travel at a speed based on the identification.

[0080] V.(f) Maximum passing speed

[0081] When an autonomous vehicle is traveling in heavy traffic, traffic congestion, or a lane adjacent to a traffic queue, the autonomous vehicle may maintain a relative speed with nearby vehicles that is less than a predetermined value (e.g., 15 mph, 20 mph, 25 mph, 30 mph).

[0082] V.(g) Maps - Real-time traffic data

[0083] The autonomous vehicle may receive map updates based on real-time traffic data indicating when there is heavy traffic or potential slowdown ahead, and the real-time traffic data for the map updates may be obtained via an application programming interface (API). Similarly, the autonomous vehicle may generate and transmit map updates based on traffic data identified by the autonomous vehicle. In some embodiments, the autonomous vehicle may identify heavy traffic, traffic jams, or traffic queues, and the autonomous vehicle may transmit its indication to one or more other vehicles, such as another autonomous vehicle traveling along the same road. Real-time traffic data may be provided by a supervisory system or a remote control center. Another autonomous vehicle in communication with the autonomous vehicle may provide real-time traffic data.

[0084] V.(h) Traffic computing capability

[0085] The autonomous vehicle may have the computing capability to monitor at least a predetermined number of vehicles ahead of the autonomous vehicle in each lane of travel.

[0086] V. (i) Relaxing the target gap

[0087] When changing lanes in heavy or congested traffic, the autonomous vehicle may relax the target front-to-rear gap tolerance such that the autonomous vehicle can complete the lane change as long as the gap in the target lane is greater than the entire length of the autonomous vehicle (e.g., including the trailer) plus an additional buffer of a predetermined number of meters in each forward and rearward direction to account for sensor and positioning uncertainties. The relaxation of the target gap is possible due to the reduced speed of the autonomous vehicle and surrounding vehicles (e.g., NPCs), and may occur when the speed of the autonomous vehicle and / or surrounding vehicles is below a threshold.

[0088] V.(j) Stopping and following distance

[0089] When following a vehicle in heavy traffic, traffic jams, or traffic queues, the autonomous vehicle may maintain a minimum following distance. The minimum following distance is configured to allow the autonomous vehicle room to avoid collision by reaching a certain speed (including a complete stop) such that the autonomous vehicle is not expected to collide with the vehicle in front of the autonomous vehicle. The minimum following distance may be defined to enable a change in trajectory to leave the current lane without colliding with the vehicle ahead.

[0090] When the leading vehicle and the autonomous vehicle are stopped due to heavy traffic, traffic jams, and traffic queues, the autonomous vehicle can maintain a recommended stopping distance. The recommended stopping distance is configured to allow room for the autonomous vehicle to change lanes from a stationary or stopped position and prevent other vehicles from cutting in. Thus, with the recommended stopping distance, the autonomous vehicle will have enough room to maneuver around the leading vehicle if needed or desired.

[0091] V.(k) Planned exit with traffic queues

[0092] If the autonomous vehicle is approaching its intended exit and the autonomous vehicle identifies a traffic queue that extends onto the shoulder of the road, the autonomous vehicle can travel to (e.g., pull over to) the shoulder portion of the road and wait in line behind the last vehicle in the traffic queue to avoid blocking the non-exit travel lane of the highway.

[0093] V.(l) Warning light

[0094] When slowing down due to heavy traffic, traffic jams, or traffic queues, the autonomous vehicle can turn on warning lights to warn other drivers. In some embodiments, when slowing down due to heavy traffic, traffic jams, or traffic queues and the autonomous vehicle's speed is below the road speed limit for more than a predetermined number (e.g., 15 mph, 18 mph, 20 mph, 22 mph, 25 mph) or below a predetermined threshold speed (e.g., 30 mph, 35 mph, 40 mph, 45 mph, 50 mph), the autonomous vehicle can turn on warning lights.

[0095] The autonomous vehicle may turn off the warning lights when the autonomous vehicle has reached a vehicle in heavy traffic, a traffic jam, or a traffic queue and there is a vehicle behind the autonomous vehicle or the autonomous vehicle is no longer in heavy traffic, whichever occurs first. In some embodiments, the autonomous vehicle may turn off the warning lights when the autonomous vehicle is within a predetermined distance (e.g., 40 meters, 45 meters, 50 meters, 55 meters, 60 meters) of a vehicle in a lane in which the autonomous vehicle is traveling and there is a vehicle behind the autonomous vehicle.

[0096] An autonomous vehicle can temporarily turn off its warning lights when changing lanes and restore them when the lane change is complete.

[0097] V.(m) Change lanes in advance for the upcoming exit

[0098] When the autonomous vehicle approaches heavy traffic or traffic congestion and the intended exit of the autonomous vehicle is within a predetermined threshold distance (e.g., 3 miles, 4 miles, 5 miles, 8 miles), the autonomous vehicle can navigate to an exit lane on the road that corresponds to the intended exit. For example, the exit lane may be the slowest lane on the road, and in some geographic areas where the autonomous vehicle is operating, it may be the rightmost lane of the road (relative to the direction of travel). By navigating to an exit lane (e.g., a slow lane, a rightmost lane), the autonomous vehicle can travel in preparation for an upcoming intended exit.

[0099] V.(n) Re-route when lane change is not possible

[0100] When driving in heavy traffic or traffic jams, if the autonomous vehicle is approaching its intended exit and is unable to change lanes to an exit lane (e.g., the slowest lane in traffic, the rightmost lane on an example North American road) in time to successfully navigate through the intended exit, the autonomous vehicle may re-route its trajectory so that the autonomous vehicle can still reach the final destination. For example, multiple alternative routes may be determined for the autonomous vehicle that may involve different exits.

[0101] V.(o) Deceleration strategy

[0102] Upon detecting heavy traffic, traffic jams, or a traffic queue in the current lane of travel, the autonomous vehicle can begin to slow down and match the speed of the oncoming vehicle. Upon detecting a traffic queue in an adjacent lane, the autonomous vehicle can slow down to achieve the maximum passing speed.

[0103] VI. Toll booth interaction

[0104] As an autonomous vehicle operates along a road, the autonomous vehicle may encounter various toll booths, toll booths, toll facilities, toll plazas, etc. located along the road. According to various embodiments described herein, the autonomous vehicle may be configured to communicate with the toll booths and / or detect certain road features (e.g., lane topology) associated with or proximate to the toll booths so that the autonomous vehicle can continue to operate on the road without significant interruption and without the need for manual intervention.

[0105] Steering Figure 6 , a flow chart illustrating the operations of an example method for operating an autonomous vehicle is provided. The example method may be performed to operate an autonomous vehicle to process and navigate a toll booth facility located along a road. For example, the example method includes operations that may be performed prior to arriving at a toll booth facility, while located at a toll booth facility, and while exiting a toll booth facility.

[0106] In operation 602, toll booth facilities located along a road through which a route of the autonomous vehicle extends are detected. Detecting the toll booth facilities includes identifying a starting point of the toll booth facilities along the road and identifying a plurality of toll lanes associated with the toll booth facilities.

[0107] In some embodiments, detecting a toll booth facility includes: collecting sensor data capturing an external environment of the autonomous vehicle by a computer located on the autonomous vehicle (e.g., VCU 150), and based on the sensor data capturing a road sign located in the external environment indicating the presence of a toll booth facility, detecting the toll booth facility by a computer located on the autonomous vehicle. In some embodiments, detecting a toll booth facility includes: collecting a sensor data capturing an external environment of the autonomous vehicle by a computer located on the autonomous vehicle (e.g., VCU 150). Figure 4A remote computer 400 in the autonomous vehicle receives a message indicating that a toll booth facility is about to appear based on the current position of the autonomous vehicle, and the computer on the autonomous vehicle detects the toll booth facility based on the received message. In some embodiments, detecting the toll booth facility includes: obtaining map data indicating the locations of multiple toll booth facilities by the computer on the autonomous vehicle, and identifying the given toll booth facility as a toll booth facility by the computer on the autonomous vehicle based on determining that the current position of the autonomous vehicle is at a threshold distance from the location of a given toll booth facility among the multiple toll booth facilities.

[0108] At operation 604, a specific toll lane from among a plurality of toll lanes associated with a toll booth facility is selected. In some embodiments, the specific toll lane is selected based on a toll configuration of the autonomous vehicle indicating the presence of an electronic toll collection device on the autonomous vehicle. In some embodiments, selecting the specific toll lane includes: identifying a subset of the plurality of toll lanes based on a toll sign associated with each of the plurality of toll lanes indicating whether each toll lane is closed; and selecting the specific toll lane from the subset of available lanes. In some embodiments, selecting the specific toll lane includes: ranking the plurality of toll lanes based on a number of vehicles located in each of the plurality of toll lanes, and selecting the specific toll lane based on the ranking.

[0109] At operation 606, a trajectory of the autonomous vehicle extending through a particular toll lane is determined. In some embodiments, the trajectory is configured to minimize the number of lateral movements or lane changes of the autonomous vehicle within the roadway. In some embodiments, the trajectory includes a complete stop of the autonomous vehicle at a toll booth associated with the particular toll lane. In some embodiments, the trajectory includes: the autonomous vehicle comes to a complete stop before the toll booth when another vehicle is located at the toll booth associated with the particular toll lane.

[0110] At operation 608, in response to the autonomous vehicle arriving at the starting point of the toll booth facility, the autonomous vehicle is caused to drive according to the trajectory. The autonomous vehicle is caused to drive according to the trajectory until the autonomous vehicle is located at a toll booth associated with a specific toll lane. For example, in response to the autonomous vehicle arriving at the starting point of the toll booth facility, a plurality of instructions are transmitted by the control computer through the subsystem interface to drive the subsystems of the autonomous vehicle, and the plurality of instructions are configured to cause the driving subsystems to operate together to cause the autonomous vehicle to drive according to the trajectory until the autonomous vehicle is located at a toll booth associated with the specific toll lane.

[0111] In some embodiments, the example method includes further operations including: after being at a toll booth associated with a particular toll lane, receiving a message indicating a toll payment status. In some embodiments, the example method also includes: after being at a toll booth associated with a particular toll lane, receiving a message indicating a toll payment status, and transmitting an indication of the toll payment status to a location external to the autonomous vehicle. In some embodiments, the example method also includes: after being at a toll booth associated with a particular toll lane, determining a toll payment status of the autonomous vehicle based on a display of the toll booth.

[0112] In some embodiments, the example method also includes: after being located at a toll booth associated with a particular toll lane, determining when to cause the autonomous vehicle to pass through a toll booth based on the detected presence of one or more vehicles located at one or more other toll booths associated with one or more other toll lanes of the toll booth facility.

[0113] VI.(a) Available toll booth signs

[0114] An autonomous vehicle can identify and autonomously navigate toll stations located along a road. For example, an autonomous vehicle can detect toll stations located along a road and determine a trajectory for navigating the toll stations. The toll station locations can be indicated in map data. The various embodiments described herein enable an autonomous vehicle to autonomously navigate toll stations in accordance with various operational requirements associated with toll stations. Instructions for autonomous driving operations related to toll stations can be determined according to the various embodiments described herein. In some embodiments, instructions can be determined based on identification or detection of an upcoming toll station. Alternatively or additionally, instructions can be predetermined based on toll stations located along a predetermined route of the autonomous vehicle.

[0115] VI.(b) Examples of Toll Station Facilities

[0116] Toll station facilities or toll station plazas can be areas where toll stations are located to collect tolls (manually or electronically) from transit vehicles. In some cases, toll station facilities can include checkpoints or inspection points, where law enforcement officers may wish that vehicles slow down for inspections, such as immigration inspections or agricultural inspections. In some cases, toll stations may be temporary settings, such as sobriety checkpoints along highways temporarily set up during certain holidays. In some examples, toll station facilities used herein include controlled roadblocks or gates. Therefore, in various examples, toll station facilities or toll stations can adjust other parts of vehicle access roads according to various standards or conditions (e.g., paying tolls, checking passengers and / or goods).

[0117] The starting point or entry point of a toll station facility may be identified where normal highway lanes begin to diverge into multiple toll lanes, or by a traffic sign indicating the distance to the toll station. Thus, in some embodiments, the autonomous vehicle may identify the starting point or entry point of the toll station facility based at least on identifying an increase in the number of lanes on the road and / or identifying a traffic sign indicating a toll station facility. In some examples, the starting point of the toll station facility is identified as the point at which a traffic sign indicating the toll station facility is located. In some examples, the starting point of the toll station facility is identified as a point along the road at which the lateral road boundaries of the road begin to diverge at an angle greater than a threshold angle.

[0118] The end of the toll plaza facility is identified as where the plurality of toll lanes begin to merge into normal highway lanes. For example, in some embodiments, the autonomous vehicle may detect the end of the toll plaza facility based at least on detecting a decrease in the number of lanes on the road.

[0119] Once identified by the autonomous vehicle or mapping vehicle, the location of the starting and stopping points of each toll plaza facility can be added to a map used by the autonomous vehicle for planning and / or navigation. In addition, the updated map or information about the starting and stopping points of each toll plaza facility can be provided to any of the following: other autonomous vehicles in direct communication with the autonomous vehicle (e.g., other autonomous vehicles in a fleet), a supervision system, and a remote control center (including a remote control operator (RCO)). Autonomous vehicles approaching a toll plaza facility can use sensor data to confirm data about the toll plaza facility provided on the map.

[0120] Figure 7A-7C A diagram showing an example toll booth facility and its road configuration is provided. Fig. 7A As shown in , the starting point of a toll plaza facility can be defined by the point where the road lanes diverge into multiple toll lanes, and the toll plaza traffic sign is located at the starting point. Therefore, the autonomous vehicle can determine the starting point of the toll plaza facility based on the change in lane configuration and the detection of the toll plaza traffic sign. Similarly, in Figure 7B In the toll booth facility, the starting point can be defined by the point where the road lanes are divided into multiple toll lanes and the toll booth traffic sign is located. Figure 7B In , different toll lanes can be associated with different toll collection operations and autonomous vehicle configurations (e.g., whether the autonomous vehicle is configured for electronic toll collection). Fig. 7A and Figure 7B In each of the toll booth facilities, the toll lane merges back into the road lane at the end point of the toll booth facility. In some examples, the road lane at the end point of the toll booth facility matches the configuration of the road lane at the start point of the toll booth facility.

[0121] Figure 7C Another example of a toll booth facility is illustrated, wherein the toll lanes are separated from the road lanes at the starting point of the toll booth facility. At the ending point of the toll booth facility, the toll lanes rejoin and merge with the road lanes.

[0122] In some examples, the toll booth facility may not be split into multiple lanes, and in such examples, the starting and ending points of the toll booth facility may be considered based on traffic signs indicating the toll booth speed limit at the beginning of the approach area and the new speed limit at the end of the departure area. Figure 8 is a diagram illustrating different sections of a toll booth facility. For example, the toll booth facility includes an approach area spanning the length of the road before the toll booth facility in the direction of travel, and the toll booth facility also includes a departure area spanning the length of the road after the toll booth facility in the direction of travel. As discussed, the approach area and the departure area may be determined based on traffic signs and indicated speed limits. Figure 8 As illustrated in , the approach and departure zones may be determined based on road boundaries having diverging or converging angles.

[0123] VI.(c) Toll station sign detection

[0124] An autonomous vehicle can detect traffic signs indicating when a toll booth is closed. In some examples, a toll booth facility can include multiple toll booths (each toll booth corresponding to a lane of travel through the toll booth facility), and the toll booth facility can include a sign for each toll booth indicating whether the toll booth is open or closed. In some examples, the sign for each toll booth is electronic and / or image-based; for example, a display device or electronic sign is located above each toll booth and can display a positive indicator (e.g., a green arrow) indicating that the toll booth is open or a negative indicator (e.g., a red cross) indicating that the toll booth is closed. Therefore, in order to determine whether a toll booth is closed, an autonomous vehicle can be configured to detect such signs located at a toll booth facility, associate the signs with the toll booth, and analyze data collected from the signs to determine whether the toll booth is closed.

[0125] VI.(d) Toll station facility expectations

[0126] The autonomous vehicle can detect toll booth traffic signs and begin to slow down at a predetermined distance (e.g., 525 meters, 555 meters, 575 meters, 600 meters) before reaching the toll booth facility. In some examples, the autonomous vehicle can use map data and traffic signs to identify all toll booths within the route. Figure 9A-9E An example road sign is shown by which an autonomous vehicle can identify a toll booth. Figure 9A-9EIllustration of a road sign that, when detected by an autonomous vehicle, notifies the autonomous vehicle that a toll booth may be approaching on the road.

[0127] VI.(e) Approaching a toll booth

[0128] The map used to operate the autonomous vehicle may include traffic sign locations of all toll booth facilities within its path. Using at least the map, the autonomous vehicle may identify all or part of the toll booths along the route. As previously disclosed, the autonomous vehicle may also determine that it is approaching a toll booth based on markings along the road.

[0129] VI.(f) Speed ​​at toll booth facilities

[0130] The autonomous vehicle can gradually reduce speed according to the speed limit of the toll booth. In some embodiments, the speed limit can be explicitly displayed on a roadside sign. In some embodiments, the speed limit can be implicitly issued based on applicable local rules and regulations. In some embodiments, the autonomous vehicle can determine two values: a first value based on an implicit or explicit sign at a toll booth, and a second value determined only based on other surrounding driving circumstances (such as the speed of neighboring vehicles and local weather conditions) without using the fact that the vehicle is approaching the toll booth. The autonomous vehicle can select the smaller of the two values ​​as the final actual speed of the autonomous vehicle. In some embodiments, as a first option, the autonomous vehicle can reduce speed via engine braking.

[0131] VI.(g) Electronic toll collection line section

[0132] The autonomous vehicle may select a toll lane within a toll booth facility based on the toll payment type of the autonomous vehicle. For example, the autonomous vehicle may be configured with an automatic payment type (e.g., toll pass ETC). In some embodiments, the autonomous vehicle selects a toll lane at a predetermined distance (e.g., at least 20 meters, at least 35 meters, at least 50 meters, at least 65 meters, at least 80 meters) before the toll booth.

[0133] The autonomous vehicle can consider each lateral maneuver (e.g., lane change, lane offset, curb) depending on trailer inertia and stability criteria to limit lateral dynamics.

[0134] VI.(h) Toll route gap

[0135] The autonomous vehicle can detect obstacles in its trajectory toward a toll booth. In various examples, the obstacles can include speed limiters, such as one-way spikes, road bumps or speed bumps, rumble strips, and the like, through which the autonomous vehicle can travel at a reduced speed. In other examples, the obstacles can include physical obstacles that the autonomous vehicle is not allowed to travel through, such as gates, pedestrians, other vehicles, and the like. Therefore, when the autonomous vehicle detects an obstacle in its trajectory, the autonomous vehicle can classify the obstacle according to whether the autonomous vehicle can travel through the obstacle (e.g., at a reduced speed). When the obstacle is classified as an obstacle that the autonomous vehicle can travel through (e.g., a one-way spike, a speed bump, etc.), the autonomous vehicle can determine a reduced speed for traveling through the obstacle and slow down before reaching the obstacle.

[0136] VI.(i) Waiting in line

[0137] The autonomous vehicle may wait for other vehicles to leave the toll booth before the autonomous vehicle enters the toll booth. For example, at a certain time, the autonomous vehicle may determine that it will be the next vehicle to be processed at the toll booth. After determining that the autonomous vehicle will be the next vehicle to be processed at the toll booth, the autonomous vehicle may (e.g., continuously) monitor the leading vehicle to leave the toll booth. After detecting that the leading vehicle has left the toll booth area, the autonomous vehicle may control its own vehicle speed to be at or below a predetermined value and enter the toll booth area.

[0138] VI.(j) Distance to vehicle ahead

[0139] The autonomous vehicle may maintain a separation or following distance from the vehicle ahead based on various criteria and logic. The following distance may refer to the distance ahead of the autonomous vehicle and across to the vehicle ahead of the autonomous vehicle, such as Fig.10. The following distance may be based on a bumper-to-bumper gap, which refers to the gap or distance between the front bumper of the autonomous vehicle and the rear bumper of the leading vehicle. In some embodiments, the autonomous vehicle may be able to make an instant prediction of the expected deceleration of the vehicle ahead in the target lane (if any). In some embodiments, the autonomous vehicle may define the critical distance to the target ahead vehicle as the maximum gap from the following options: (i) the bumper-to-bumper gap required to maintain at least a threshold confidence measurement of sensor coverage; (ii) the bumper-to-bumper gap required to exceed the minimum response time; and (iii) the bumper-to-bumper gap required to avoid a collision assuming that both the autonomous vehicle and the target lane ahead vehicle must decelerate to a complete stop at the expected deceleration of the target lane ahead vehicle and the expected reactive deceleration of the autonomous vehicle (the gap may take into account the reaction time of the autonomous vehicle and may include an additional safety buffer zone). If the target ahead vehicle is not expected to decelerate, the gap may be equal to the safety buffer zone. In some examples, there is a predetermined minimum distance. The autonomous vehicle shall not change lanes within the critical distance from the target lane ahead vehicle.

[0140] For all but critical safety lane change intent situations, the automated vehicle may prefer to change lanes with a bumper-to-bumper clearance of at least a predetermined distance (e.g., 10 meters, 12.5 meters, 15 meters, 17.5 meters, 20 meters) from a target ahead vehicle. The automated vehicle may prefer not to change lanes behind a slow-moving target ahead vehicle.

[0141] VI.(k) Complete stop at toll booths

[0142] When approaching a toll booth (e.g., when the vehicle ahead of the autonomous vehicle has left the toll booth), the autonomous vehicle can come to a complete stop at a predetermined distance (e.g., 1 meter, 2 meters, 3 meters) from the toll booth gate when the toll booth gate closes.

[0143] VI.(l) Speed ​​up after the toll booth

[0144] The autonomous vehicle can accelerate at a predetermined acceleration (e.g., 1 m / s) after passing through the toll booth. 2 , 1.5m / s 2 , 2m / s 2 ) increases its speed until the permitted speed limit is reached. The permitted speed limit may be based on speed limits associated with the road and external environmental conditions (such as weather).

[0145] VI.(m) Toll Payment Status

[0146] The autonomous vehicle may confirm that the toll payment has been registered and immediately report any problems with the payment to the supervisory system or remote computer. In some embodiments, the autonomous vehicle may determine the toll payment status based on communication with the toll collection system. For example, the autonomous vehicle may be configured to wirelessly communicate with a toll collection system located at a given toll station or with a toll collection system associated with multiple toll stations at a toll collection facility. In some embodiments, upon approaching a toll station, the autonomous vehicle may transmit an indication to the toll collection system, thereby indicating that the autonomous vehicle is operating autonomously and requesting to provide confirmation of the toll payment. In response to the transmitted indication and based on the possibility that the autonomous vehicle is located at the toll station, the autonomous vehicle may receive an indication that the toll payment was successful. In some examples, the autonomous vehicle may receive an indication of a request for operation; for example, the autonomous vehicle may receive an indication from the toll collection system that the autonomous vehicle needs to travel a specified distance forward so that the toll collection station can scan the toll collection device of the autonomous vehicle. In some examples, for toll lanes that do not require the autonomous vehicle to stop completely and are configured to scan the toll collection device of the autonomous vehicle when the autonomous vehicle travels through the toll lane, the autonomous vehicle may receive an indication of a successful toll payment based on the unique association of the autonomous vehicle with the toll collection device. For example, a toll collection system may scan a toll collection device, and based on the unique association between the toll collection device and the autonomous vehicle, the toll collection system may transmit a message to the autonomous vehicle.

[0147] VI.(n) Available lane detection

[0148] The autonomous vehicle may identify a lane indicated by the map to continue the trip. At a toll booth facility, the toll lane layout may be different from the lane layout before and after the toll booth facility. Fig.11 An example of changing the layout of toll lanes at a toll station facility 1100 is illustrated. At area 1 before the toll station facility 1100, the road has a first lane configuration (e.g., two lanes). At area 2 at the toll station facility 1100, the road includes an increased number of lanes, or a second lane configuration that is different from the first lane configuration. At area 3 after the toll station facility 1100, the road includes a lane configuration that is different from the lane configuration at area 2. In some examples, the lane configuration at area 3 is the same as the lane configuration at area 1. In some examples, some toll lanes (e.g., in area 2) may be out of service, closed for maintenance and construction, closed due to accidents, and the like. Therefore, in some embodiments, the autonomous driving vehicle is configured to dynamically detect available lanes at points before the toll station facility, at the toll station facility, and after the toll station facility.

[0149] In some embodiments, the autonomous vehicle may select one of the detected available lanes based on the presence of other vehicles in each detected available lane. For example, the autonomous vehicle may rank the detected available lanes based on the number of other vehicles located in each detected available lane. Based on the ranking, the autonomous vehicle may select an available toll lane with the fewest other vehicles. In some embodiments, the autonomous vehicle may select one of the detected available lanes based on the lane of the road that the autonomous vehicle was in before arriving at the toll booth facility. For example, if the autonomous vehicle is in the rightmost lane of the road before arriving at the toll booth facility, the autonomous vehicle may select an available toll lane located to the right of the toll booth facility instead of another available toll lane located to the left of the toll booth facility, thereby minimizing the degree of lateral movement of the autonomous vehicle when traveling through the toll booth facility.

[0150] VI.(o) Leaving from the toll booth

[0151] The autonomous vehicle can ensure safe exit from the toll booth based on determining that there are no objects (including toll gates, NPC vehicles (e.g., surrounding vehicles), personnel, etc.) blocking the path out of the toll booth. Figure 7A-7C As shown in , the toll lanes exiting the toll station facility may merge with or merge into the lanes of the road, and similar to the number of lanes expanded at the starting point of the toll station facility, the end point of the toll station facility may have a compressed or reduced number of lanes. Therefore, when the autonomous vehicle leaves the toll station, the autonomous vehicle may select the lane of the road to which the autonomous vehicle will travel. The autonomous vehicle may prefer the slowest traffic lane after the end point of the toll station facility (e.g., the rightmost lane in an area where traffic travels on the right side of the road), or the road that requires the least lateral movement from the current position of the autonomous vehicle at the toll station. When the autonomous vehicle determines the trajectory to the selected lane of the road located outside the end point of the toll station facility, the autonomous vehicle may identify whether other toll lanes of the toll station facility other than the toll lane where the autonomous vehicle is currently located are merged into the selected lane. Based on determining that one or more other toll lanes merge with the selected lane of the road, the autonomous vehicle may monitor the presence of other vehicles in the other toll lanes, and if other vehicles deviate from their corresponding toll lanes before the autonomous vehicle leaves the toll station, the other vehicles may be given way.

[0152] VI.(p) Lane change required

[0153] If a lane change is required when navigating a toll booth facility, the autonomous vehicle can execute the lane change. For example, when it is determined that the toll booth targeted by the autonomous vehicle is closed, the autonomous vehicle can target another toll booth and execute the lane change. As another example, when it is determined that the vehicle is located at a toll booth for at least a threshold amount of time, the autonomous vehicle can target another toll booth and execute the lane change. This lane change can be performed after the autonomous vehicle selects a particular toll lane and monitors the toll booth associated with the particular toll lane. For example, after selecting a particular toll lane, the autonomous vehicle can monitor whether the toll booth remains open as the autonomous vehicle approaches the toll booth until the autonomous vehicle arrives at the toll booth. Through monitoring, if the autonomous vehicle determines that the toll booth is closed (e.g., via a toll sign indicating the open / closed status of the toll booth), the autonomous vehicle can execute the lane change.

[0154] VI.(q) Collision Avoidance of Toll Station Facilities

[0155] The autonomous vehicle can detect and avoid collisions with any pedestrians, obstacles, and vehicles within the toll booth facility by maintaining a predetermined safe distance (e.g., 1 meter, 2 meters, 3 meters) from these objects. For example, the autonomous vehicle can maintain a certain distance from pedestrians or toll booth staff to avoid running over them. In some examples, the predetermined safe distance maintained by the autonomous vehicle from objects at the toll booth facility is based on object type, such as vehicle object type, human object type (e.g., pedestrian, toll booth attendant, etc.), environmental object type (e.g., toll booth itself, guardrail, gate, etc.).

[0156] VI.(r) Yield sign detection

[0157] The self-driving vehicle can detect if there is a yield sign or if it needs to yield to other vehicles that are also leaving the toll booth.

[0158] Electronic toll collection (ETC) lanes with favorable geometry generally allow vehicles to move through toll plazas without stopping, but generally within a set regulatory speed limit or recommended speed. The autonomous vehicle may determine different trajectories or maneuvers based on whether the autonomous vehicle is located in or targeting an ETC toll lane or a non-ETC toll lane.

[0159] VI.(s) Path Clearance Confirmation

[0160] In some examples, when the autonomous vehicle exits the toll booth facility, an obstacle, vehicle, or pedestrian may block the trajectory of the autonomous vehicle. Upon detecting such a blocking obstacle, the autonomous vehicle may come to a complete stop and monitor the movement of the blocking obstacle. Once the blocking obstacle, vehicle, or pedestrian has been cleared from the trajectory of the autonomous vehicle, for example, once the blocking obstacle is located a predetermined distance from the trajectory of the autonomous vehicle, the autonomous vehicle may resume its route.

[0161] VII. Minimum risk condition operation

[0162] The autonomous vehicle can receive information from a supervisory system or a remote computer (e.g. Figure 3 Supervision system in 350, Figure 4 The supervisory system or remote computer 400 in the autonomous vehicle receives a command to initiate a minimum risk condition (MRC) maneuver. The supervisory system or remote computer can initiate an MRC maneuver of the autonomous vehicle for various reasons, such as determining a fault condition of the autonomous vehicle based on sensor data received from the autonomous vehicle, a request from a law enforcement entity to verify the autonomous vehicle, an inclement weather event, etc. In some embodiments, the command to initiate the MRC maneuver can be transmitted from the supervisory system or remote computer to the autonomous vehicle with a high priority so that the autonomous vehicle receives and processes the command within a predetermined amount of time.

[0163] In some embodiments, a supervisory system or remote computer may transmit a batch of MRC commands to a plurality of autonomous vehicles, causing each of the plurality of autonomous vehicles to perform an MRC maneuver. For example, a supervisory system or remote computer may identify a severe weather event associated with a geographic area, and may accordingly transmit a batch of MRC commands to all autonomous vehicles located in the geographic area, all autonomous vehicles having routes that travel through the geographic area, all autonomous vehicles that are within a threshold distance of the geographic area, and so on. As another example, a supervisory system or remote computer may identify a heavy traffic event at a portion of a road, and may transmit a batch of MRC commands to all autonomous vehicles that plan to travel through the portion of the road, so that the supervisory system has time to plan an alternate route for each autonomous vehicle.

[0164] In some examples, a supervisory system or a remote computer can cause multiple autonomous vehicles to perform MRC maneuvers based on inter-vehicle communication propagation. For example, the supervisory system can transmit a batch of MRC commands to a leader autonomous vehicle, and after receiving the batch of MRC commands, the leader autonomous vehicle can transmit separate MRC commands to one or more other autonomous vehicles associated with the leader autonomous vehicle. Similarly, the supervisory system can transmit a batch of MRC commands to a specific autonomous vehicle, and the specific autonomous vehicle can be configured to communicate with other autonomous vehicles within a predetermined radius to enable the other autonomous vehicles to perform MRC maneuvers. Therefore, the supervisory system can effectively cause a group of autonomous vehicles, a fleet of autonomous vehicles, or multiple autonomous vehicles to each perform an MRC maneuver by operating as follows: a batch of MRC commands is sent to one autonomous vehicle, which then relays or propagates the command to other autonomous vehicles.

[0165] VIII. Emergency Free Space Escape

[0166] After performing a minimum risk condition (MRC) maneuver (an operation configured to allow the autonomous vehicle to reach a minimum risk condition, such as a complete stop), the autonomous vehicle may be located at an emergency free space. For example, a minimum risk condition for the autonomous vehicle may be defined as a complete stop at an emergency free space, such as off the shoulder area of ​​a road or in the rightmost lane of a road (e.g., a lane that is the slowest traffic lane of the road based on the jurisdiction in which the road is located).

[0167] Since the autonomous vehicle is in the emergency free space, the fault condition that triggered the MRC maneuver may be resolved, and the autonomous vehicle may need to leave the emergency free space and get back on the road to continue its route. For example, the autonomous vehicle leaves the emergency free space after performing the MRC maneuver and recovering.

[0168] Leaving the emergency free space can be performed in response to determining that the triggered fault condition has been resolved. In some examples, for example, when the supervisory system or remote computer initiates the MRC maneuver, the autonomous vehicle can receive an indication from the supervisory system or remote computer that the fault condition has been resolved. In some examples, the autonomous vehicle may have initiated the MRC maneuver locally, and the autonomous vehicle may determine that the fault condition that triggered the MRC maneuver has become irrelevant, has been resolved, or has become alleviated or less severe. In some examples, the human operator of the autonomous vehicle may have manually checked the fault condition of the autonomous vehicle, and the human operator may provide user input (e.g., override code, PIN) to the autonomous driving system of the autonomous vehicle to indicate that the fault condition has been resolved. The human operator may be a safety driver or service personnel. The supervisory system or remote control center may dispatch a safety driver or service personnel to assist an autonomous vehicle in an MRC, such as an autonomous vehicle that has to stop due to deterioration of vehicle health, sensor cleaning or alignment problems, collisions, and the like.

[0169] In response to the triggering fault condition being resolved, the autonomous vehicle is configured to monitor traffic on the road and determine a trajectory that allows the autonomous vehicle to rejoin traffic on the road. The autonomous vehicle may collect sensor data from sensors (e.g., cameras, light detection and ranging sensors) toward the rear of the autonomous vehicle within a predetermined amount of time to observe approaching traffic. The autonomous vehicle may predict the trajectory of detected vehicles that are approaching the autonomous vehicle in order to identify gaps between vehicles into which the autonomous vehicle may travel. The trajectory of the detected vehicle may be predicted using a machine learning model, a predictive model, an extrapolation model, and the like.

[0170] The autonomous vehicle may also predict the speed of the detected vehicle (e.g., the average speed of the vehicle) and may begin accelerating to a given speed before re-entering the road. For example, the autonomous vehicle may accelerate along an emergency free space (e.g., a shoulder area of ​​the road) before entering a road lane.

[0171] IX. Conclusion

[0172] To perform the above features, the autonomous vehicle may utilize any sensors, particularly data acquired from the sensors, in conjunction with the autonomous vehicle's onboard computing facilities (such as those associated with or in communication with the VCU). Alternatively or additionally, the above features may be performed by the autonomous vehicle with the assistance of a supervisory system or control center and optionally with the assistance of a human remote control operator. The supervisory system (and in some cases the remote control operator) may transmit environmental data, map updates, instructions, or other information to the autonomous vehicle. The autonomous vehicle may use onboard maps (such as high-definition maps) to implement some of the features described herein, particularly when it is necessary to understand the location and local regulations (e.g., speed limits, legal obligations, traffic conventions, intersection types) to complete the tasks described in the features.

[0173] Although this document refers to self-driving trucks, it should be understood that any self-driving ground vehicle can have such features. Self-driving vehicles that travel on the ground may include: semi-trailers, tractor trailers, 18-wheelers, trucks, Class 8 vehicles, passenger cars, delivery vans, trucks, recreational vehicles, golf carts, transport vehicles, etc.

[0174] Although several embodiments have been provided in the present disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples should be considered illustrative rather than restrictive, and are not intended to be limited to the details given herein. For example, various elements or components may be combined or integrated in another system, or certain features may be omitted or not implemented.

[0175] In addition, the techniques, systems, subsystems, and methods described and illustrated as discrete or separately in various embodiments may be combined or integrated with other systems, modules, techniques, or methods without departing from the scope of the present disclosure. Other items shown or discussed as coupled or directly coupled or communicating with each other may be indirectly coupled or communicated through some interface, device, or intermediate component, whether electrically, mechanically, or otherwise. Other examples of changes, substitutions, and variations may be determined and made by those skilled in the art without departing from the spirit and scope disclosed herein.

[0176] The implementation of the subject matter and functional operations described in this patent document can be implemented in various systems, semiconductor devices, ultrasonic devices, digital electronic circuits, or in computer software, firmware or hardware, including the structures disclosed in this specification and their structural equivalents or in a combination of one or more of them. The implementation of various aspects of the subject matter described in this specification can be implemented as one or more computer program products, such as one or more modules of computer program instructions encoded on a tangible and non-transient computer-readable medium for a data processing device to execute or control the operation of the data processing device. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a material composition that affects a machine-readable propagation signal, or a combination of one or more of them. The term "data processing unit" or "data processing device" covers all devices, equipment and machines for processing data, including, for example, a programmable processor, a computer or multiple processors or computers. In addition to hardware, the device may also include code to create an execution environment for the computer program in question, such as code constituting a processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.

[0177] A computer program (also referred to as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted languages, and it may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or portions of code). A computer program may be deployed to be executed on one or more computers located at one site or distributed across multiple sites and interconnected by a communications network.

[0178] The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits, and the apparatus can also be implemented as special purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application specific integrated circuits).

[0179] For example, processors suitable for executing computer programs include general and special purpose microprocessors, and any one or more processors of any type of digital computer. Typically, the processor will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include or be operably coupled to receive data from or transmit data to one or more large-capacity storage devices (such as magnetic disks, magneto-optical disks, or optical disks) for storing data, or both. However, a computer does not need to have such a device. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices. The processor and memory can be supplemented by or incorporated into a dedicated logic circuit.

[0180] Although this patent document contains many details, these details should not be interpreted as limitations on the scope of any invention or content that may be claimed, but rather descriptions of the features of a particular embodiment or part that may be specific to a particular invention. Certain features described in the context of separate embodiments or parts in this patent document may also be implemented in combination in a single embodiment or a single part. On the contrary, the various features described in the context of a single embodiment or a single part may also be implemented in multiple embodiments or multiple parts separately or in any suitable sub-combination. The features or operations described in an embodiment or a part may be combined with another feature or another operation from another embodiment or another part in any reasonable manner. In addition, although the characteristics may be described above as working in certain combinations and even initially claimed, one or more features from the claimed combination may be deleted from the claimed combination in some cases, and the claimed combination may involve a sub-combination or a variant of a sub-combination.

[0181] Similarly, although operations are depicted in a particular order in the drawings, this should not be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations be performed, in order to achieve the desired results. In addition, the separation of various system components in the embodiments described in this patent document should not be understood as requiring such separation in all embodiments.

[0182] Only a few implementations and examples are described, and other implementations, enhancements, and variations may be made based on what is described and illustrated in this patent document.

Claims

1. A method of operating an autonomous vehicle, comprising: detecting, by a control computer located on the autonomous vehicle, toll booth facilities located along a road through which a route for the autonomous vehicle extends based on sensor data acquired through a subsystem interface between the control computer and one or more sensor subsystems of the autonomous vehicle, Wherein detecting the toll station facility comprises: identifying a starting point of the toll station facility on the road and a plurality of toll lanes associated with the toll station facility; selecting, by the control computer, a particular toll lane from among the plurality of toll lanes associated with the toll booth facility; determining, by the control computer, a trajectory for the automated vehicle extending through the particular toll lane; and In response to the autonomous driving vehicle arriving at the starting point of the toll booth facility, the control computer transmits a plurality of instructions to one or more driving subsystems of the autonomous driving vehicle through the subsystem interface, wherein the plurality of instructions are configured to cause the one or more driving subsystems of the autonomous driving vehicle to operate together to cause the autonomous driving vehicle to travel along the trajectory until the autonomous driving vehicle is located at a toll booth associated with the specific toll lane.

2. The method according to claim 1, wherein detecting the toll booth facility comprises: The control computer collects sensor data of the external environment of the autonomous driving vehicle through the subsystem interface; as well as The toll booth facility is detected by the control computer based on the sensor data capturing road signs located in the external environment indicating the presence of the toll booth facility.

3. The method of claim 1, wherein detecting the toll booth facility comprises: receiving a message from a remote computer at a location external to the autonomous vehicle, the message indicating that the toll booth facility is imminent based on a current location of the autonomous vehicle; as well as The control computer detects the toll booth facility based on the received message.

4. The method of claim 1, wherein detecting the toll booth facility comprises: acquiring, by the control computer, map data indicating locations of a plurality of toll booth facilities; as well as The control computer identifies the given toll booth facility as the toll booth facility based on determining that the current position of the autonomous driving vehicle is within a threshold distance of the position of the given toll booth facility among the multiple toll booth facilities.

5. The method of claim 1, wherein the number of the plurality of toll lanes is greater than the number of lanes of the road, and wherein the starting point of the toll booth facility is identified as a point along the road at which the number of lanes on the road changes.

6. The method of claim 1, wherein the starting point of the toll booth facility is identified as a point along the road at which a pair of lateral road boundaries of the road have a divergence angle greater than a predetermined threshold angle.

7. The method of claim 1, wherein the starting point of the toll booth facility is identified as a point along the road at which a road sign associated with the toll booth facility is located.

8. The method of claim 1, wherein the specific toll lane is selected based on a toll configuration of the autonomous vehicle, the toll configuration indicating the presence of an electronic toll collection device on the autonomous vehicle.

9. The method of claim 1 , wherein selecting the specific toll lane comprises: identifying a subset of the plurality of toll lanes based on a toll sign associated with each of the plurality of toll lanes, the toll sign indicating whether each toll lane is closed; as well as The particular toll lane is selected from the subset of available lanes.

10. The method of claim 1, wherein selecting the specific toll lane comprises: ranking the plurality of toll lanes based on a number of vehicles located in each of the plurality of toll lanes; as well as The specific toll lane is selected according to the ranking.

11. The method according to claim 1, further comprising: After being located at a toll booth associated with the particular toll lane, a message is received indicating a toll payment status.

12. The method according to claim 1, further comprising: receiving, after being located at a toll booth associated with the particular toll lane, a message indicating a toll payment status; as well as An indication of the toll payment status is transmitted to a remote computer located at a location external to the autonomous vehicle.

13. The method according to claim 1, further comprising: After being located at a toll booth associated with the particular toll lane, a toll payment status of the autonomous vehicle is determined based on a display of the toll booth.

14. The method according to claim 1, further comprising: After being located at a toll booth associated with the particular toll lane, determining when to cause the autonomous vehicle to pass through the toll booth based on detecting the presence of one or more vehicles located at one or more other toll booths associated with one or more other toll lanes of the toll booth facility.

15. The method of claim 1, wherein the trajectory of the autonomous vehicle is configured to minimize lateral movement of the autonomous vehicle within the road.

16. The method of claim 1, wherein the trajectory of the autonomous vehicle is configured to minimize the number of lane changes of the autonomous vehicle.

17. The method of claim 1, wherein the trajectory of the autonomous vehicle includes a complete stop of the autonomous vehicle at the toll booth associated with the particular toll lane.

18. The method of claim 1, wherein the trajectory of the autonomous vehicle comprises: When another vehicle is located at the toll booth associated with the particular toll lane, the autonomous vehicle comes to a complete stop in front of the toll booth.

19. A system for operating an autonomous vehicle, the system comprising a computer including a processor configured to perform the method according to any one or more of claims 1 to 18.

20. A non-transitory computer readable program storage medium having stored thereon codes which, when executed by a processor, cause the processor to perform the method according to any one or more of claims 1 to 18.

21. A method of operating an autonomous vehicle, comprising: collecting, by a control computer located on an autonomous vehicle, sensor data from one or more sensor subsystems of the autonomous vehicle via a subsystem interface, the sensor data capturing a plurality of vehicles located within a portion of a road on which the autonomous vehicle is operating; determining a classification of the plurality of vehicles, the classification representing a degree of vehicular traffic present within the plurality of vehicles, wherein the classification is determined based on the sensor data, the sensor data being based on a number of the plurality of vehicles, relative distances between the vehicles, and an average vehicle speed; as well as When the autonomous driving vehicle is within a threshold distance of at least one of the multiple vehicles, the control computer transmits instructions to one or more driving subsystems of the autonomous driving vehicle through the subsystem interface, and the instructions are configured to cause the one or more driving subsystems of the autonomous driving vehicle to operate to cause the autonomous driving vehicle to travel at a speed corresponding to the classification of the multiple vehicles.

22. A method according to claim 21, wherein the multiple vehicles are located in front of the current position of the autonomous vehicle, and wherein the instructions are configured to cause the one or more driving subsystems of the autonomous vehicle to operate to cause the autonomous vehicle to decelerate to the speed before traveling at the speed.

23. A method according to claim 21, wherein at least one of the plurality of vehicles is located in front of the current position of the autonomous vehicle, and wherein the instructions are configured to cause the one or more driving subsystems of the autonomous vehicle to operate to cause the autonomous vehicle to decelerate to the speed at a rate based on the threshold distance.

24. The method of claim 21, further comprising receiving a map update configured to cause determination of the classification of a vehicle located within the portion of the road.

25. The method of claim 21, further comprising: Prior to determining the classification of the plurality of vehicles, a map update is received by the control computer from a remote computer located at a location external to the autonomous vehicle, the map update including a previous classification for vehicles located within the portion of the road.

26. The method of claim 21, further comprising: Before the autonomous vehicle is within the threshold distance of at least one of the plurality of vehicles, the control computer transmits an instruction to a warning light of the autonomous vehicle to cause the warning light to operate.

27. The method of claim 21, further comprising: Before the autonomous vehicle is within the threshold distance of at least one of the plurality of vehicles, the control computer transmits to a warning light of the autonomous vehicle an instruction for causing the warning light to operate during deceleration of the autonomous vehicle.

28. The method of claim 21, wherein the portion of the road is one lane of a plurality of lanes of the road.

29. The method of claim 21, wherein the portion of the road is a lane of the road in which the autonomous vehicle is located.

30. The method of claim 21, wherein the portion of the road is a lane of the road adjacent to a lane in which the autonomous vehicle is located.

31. A method according to claim 21, wherein the speed of operating the autonomous vehicle is determined based on a sensor uncertainty value associated with a sensor located on the autonomous vehicle.

32. The method of claim 21, wherein the portion of the road includes a toll booth facility, and wherein the method further comprises: A starting point of the toll booth facility and a plurality of toll lanes associated with the toll booth facility are identified.

33. The method of claim 32, wherein the starting point of the toll booth facility is identified as a point along a road at which a pair of lateral road boundaries have a divergence angle greater than a predetermined threshold angle.

34. The method of claim 21, wherein the portion of the road includes a toll booth facility, and wherein the method further comprises: A particular toll lane among a plurality of toll lanes associated with the toll booth facility is selected.

35. The method of claim 34, wherein the particular toll lane is selected based on the presence of an electronic toll collection device located on the autonomous vehicle.

36. The method of claim 21, wherein the portion of the roadway is a toll lane of a toll booth facility, and the speed is a complete stop based on at least one vehicle of the plurality of vehicles coming to a complete stop at a toll booth associated with the toll lane.

37. The method of claim 21, further comprising: An indication of the classification of the plurality of vehicles is provided to a remote computer at a location external to the autonomous vehicle as part of a map survey update.

38. The method of claim 21, further comprising: An indication of the classification of the plurality of vehicles is provided to a second autonomous vehicle that is associated with a route that extends through the portion of the road.

39. A system for operating an autonomous vehicle, the autonomous vehicle comprising a computer, the computer comprising a processor configured to execute the method according to any one or more of claims 21 to 38.

40. A non-transitory computer readable program storage medium having stored thereon codes which, when executed by a processor, cause the processor to perform the method according to any one or more of claims 21 to 38.

Images