SYSTEM AND METHOD FOR BLOCKAGE PREVENTION AND AVOIDANCE IN AUTONOMOUS VEHICLES

The system uses sensors, actuators, and control modules to predict and coordinate vehicle movements via V2V and V2I networks, addressing deadlock issues in autonomous vehicles by ensuring efficient traffic flow and maintaining driver comfort.

DE102023114536B4Active Publication Date: 2024-11-21GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
DE102023114536
Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-05-06
Filing Date
2023-06-02
Publication Date
2024-11-21
Estimated Expiration
2043-06-02

AI Technical Summary

Technical Problem

Existing automated driver assistance systems (ADAS) in autonomous vehicles struggle to prevent and avoid deadlock situations at intersections without increasing complexity, requiring standardization, and while maintaining or improving functionality and driver comfort.

Method used

A system and method for autonomous vehicles that utilize sensors, actuators, and control modules to predict vehicle trajectories, communicate via V2V and V2I networks, and employ programmatic control logic to generate and respond to MDCIPD messages, DPNs, and DPCIs to avoid blockages at intersections.

Benefits of technology

Effectively prevents deadlock situations at intersections by coordinating vehicle movements, ensuring efficient traffic flow and maintaining driver comfort without increasing system complexity or requiring standardization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

A blockage prevention and avoidance system in autonomous vehicles (AVs) comprises AVs equipped with actuators and sensors. The actuators modify the dynamic state of the AVs, and the sensors capture vehicle state and environmental information. The system receives information about the vehicle state and predicts the trajectory of the autonomous vehicle as well as the trajectories of other vehicles approaching, entering, or already present at an intersection. MDCIPD (Multi-directional Conflicts Identification per Driving Direction) messages and vehicle state information are transmitted to a cloud computing device. Based on the MDCIPD messages and vehicle state information, waiting relationships for blockage avoidance are established, and a Blockage Prevention Message (DPN) and / or a Blockage Avoidance Coordination Instruction (DPCI) is generated.In response to the DPN and / or the DPCI, the vehicles execute ADAS (Advanced Driver Assistance System) functions via the actuators, causing the vehicles to avoid blocking at the intersection.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The present disclosure relates to vehicle control systems, and more particularly to automated driver assistance systems (ADAS) that automatically control vehicle driving. Vehicles are increasingly equipped with ADAS systems that control a variety of dynamic vehicle functions. Some vehicles are available with varying degrees of "hands-off" functionality, where the vehicle can drive without human intervention for varying periods of time or until a specific condition or set of conditions occurs. Vehicles equipped with ADAS functionality require inputs from a variety of different sensors, and many also communicate with other vehicles via vehicle-to-vehicle (V2V) communication systems or with the infrastructure via vehicle-to-infrastructure (V2I) communication systems.

[0002] ADAS-equipped vehicles can handle a wide range of driving situations. However, as the number of ADAS-equipped and operating vehicles continues to grow, new situations may arise in which multiple ADAS-equipped vehicles encounter each other while driving, resulting in a deadlock in which the ADAS-equipped and operating vehicles are virtually unable to move.While current systems and methods for controlling vehicle functions through ADAS serve their purpose, there is a need for new and improved ADAS systems and methods that enable ADAS-equipped and operated vehicles to avoid dead-end and gridlock situations without increasing complexity and without the need for standardization, while improving ADAS functionality, redundancy, and speed, while maintaining or improving driver comfort.

[0003] DE 10 2015 219 470 A1 discloses a method for handling a control map containing traffic rules in a vehicle, which method comprises the following steps: detecting an environmental condition by means of a number of environmental sensors, deriving a number of traffic rules based on the environmental condition, generating the control map based at least on the traffic rules, and sending the control map to an external unit.

[0004] DE 11 2020 005 275 T5 discloses a system and method for vehicle navigation. The system for a host vehicle includes a processor that determines target dynamics of a target vehicle based on an output of a sensor of the host vehicle and determines a time to collision based on host dynamics of the host vehicle and the target dynamics. Furthermore, based on the time to collision and the host dynamics, the processor determines a host deceleration for the host vehicle to avoid the collision. Furthermore, based on the time to collision and the target dynamics, a target deceleration for the target vehicle to avoid the collision is determined. The processor determines a host deceleration threshold based on the host deceleration and the target deceleration, and, based on a speed of the host vehicle and the host deceleration threshold, determines a time to brake the host vehicle.

[0005] DE 10 2020 126 217 A1 discloses a system for operating an autonomous vehicle (AV) at a multi-way stop intersection. Upon detecting that the AV is at a primary stop line of the multi-way stop intersection, a planned path through the multi-way stop intersection is obtained. If the AV's planned path through the multi-way stop intersection satisfies a set of one or more intersection clearance criteria, the AV passes the primary stop line. The intersection clearance criteria include a criterion that is satisfied in response to detecting that the path is clear for the AV to safely merge into a lane corresponding to the planned path.

[0006] DE 102021 114 596 A1 discloses an intersection navigation system with a complexity module configured to determine a complexity value for an intersection of two or more streets. The complexity value for the intersection corresponds to a complexity level for a vehicle to navigate the intersection during autonomous driving. A driving control module is configured to control at least one of the following during autonomous driving of a vehicle: steering of the vehicle; braking of the vehicle; and acceleration of the vehicle; and to selectively adapt at least one aspect of autonomous driving based on the complexity value of the intersection.

[0007] DE 11 2020 001 642 T5 discloses a device comprising at least one interface for receiving sensor data from a plurality of sensors of a vehicle; and a processor for autonomously controlling the driving of the vehicle according to a path plan based on the sensor data; determining that autonomous control of the vehicle should end; sending a handover request to a remote computing system so that the remote computing system remotely controls the driving of the vehicle; receiving driving instruction data from the remote computing system; and controlling the driving of the vehicle based on instructions included in the driving instruction data.

[0008] It can be considered a task to provide a system and a method to prevent blocking of autonomous vehicles.

[0009] According to several aspects of the present disclosure, a system for blockage prevention and avoidance in autonomous vehicles comprises one or more autonomous vehicles (AVs). The system further comprises one or more actuators and one or more sensors. The one or more actuators selectively change a dynamic state of the one or more AVs. The one or more sensors are disposed on at least one of the one or more AVs and collect vehicle condition information and information about an environment surrounding the one or more AVs. The system further comprises one or more control modules. At least one of the one or more AVs having the one or more sensors is also equipped with at least one of the one or more control modules. Each of the one or more control modules has memory, a processor, and one or more input / output (I / O) ports.The memory stores programmatic control logic. The processor executes the programmatic control logic, and the I / O ports communicate with the one or more sensors and the one or more actuators. The programmatic control logic includes at least first, second, third, fourth, fifth, and sixth control logic. The first control logic receives information about the vehicle state. The second control logic predicts a trajectory of a host AV approaching an intersection on a road and predicts a trajectory of one or more other vehicles approaching, at, or within the intersection. The third control logic transmits Multi-Directional Conflicts Identification per Driving Direction (MDCIPD) messages and the vehicle state information to a cloud computing device.The fourth control logic determines the waiting relationships for deadlock avoidance at the intersection based on the MDCIPD messages and the vehicle state information. The fifth control logic sends one or more AVs, one or more Deadlock Precaution Notifications (DPNs), and a Deadlock Prevention Coordination Instruction (DPCI) from the cloud computing device and receives one or more AVs from the host AV. The sixth control logic executes one or more Advanced Driver Assistance System (ADAS) functions via the one or more actuators in response to receiving one or more of the DPNs and DPCIs, and causes the one or more AVs to avoid deadlock at the intersection.

[0010] According to the invention, the first control logic further comprises control logic that receives a basic safety message (BSM) from the one or more other vehicles. The BSM contains data about the status of the communicating vehicle. The BSM includes the vehicle size, vehicle type, vehicle speed, vehicle acceleration, vehicle position, vehicle heading, and the vehicle's turn signal status.

[0011] According to the invention, the second control logic further includes control logic for acquiring trajectory-related data for each of the one or more other vehicles and the host AV approaching the intersection by combining the vehicle state information and information about an environment surrounding the host AV and BSMs from the one or more other vehicles. The second control logic further includes control logic that extrapolates a trajectory of each of the one or more vehicles and the host AV from the trajectory-related data.

[0012] In another aspect of the present disclosure, the third control logic further includes control logic that determines the MDCIPD messages, including predicting one or more conflicts between the host AV and the other vehicles, given a current heading and vehicle state information for the host AV and for each of the other vehicles.

[0013] In another aspect of the present disclosure, the fourth control logic further includes control logic that determines the waiting relationships to avoid a blockage based on directions of travel, position, and timing for the host AV and the other vehicles approaching, entering, or located at the intersection, as well as the topology, laws, signage, and rules of the intersection.

[0014] In another aspect of the present disclosure, the waiting relationships define a right-of-way calculation for each of the host AVs and the other vehicles. The right-of-way calculation utilizes the directions, positions, and timing of the host AVs and the other vehicles approaching, entering, or within the intersection, the topology and rules of the intersection, local laws, and signage at or near the intersection.

[0015] In another aspect of the present disclosure, the fifth control logic further includes control logic that generates the DPN from the MDCIPD messages. The fifth control logic also includes control logic for generating the DPCI. The DPN contains information that directly indicates whether a deadlock potential exists. The DPCI contains information that directly indicates the control actions required for the host AV and all other AVs approaching, located in, or entering the intersection to avoid a deadlock at the intersection.

[0016] In another aspect of the present disclosure, the control logic for generating the DPCI further includes control logic that selectively generates the DPCI when it is determined that two or more AVs capable of transmitting the MDCIPD messages are located at, in, or on the intersection.

[0017] In another aspect of the present disclosure, the control logic that selectively generates the DPCI further includes control logic that, if it determines that there is no potential for deadlock at the intersection, causes the host AV to rely solely on the guidance systems and ADAS functions of the host AV to cross the intersection. The control logic that selectively generates the DPCI also includes control logic that, if it determines that there is a potential for deadlock at the intersection due to the presence of at least one other vehicle, causes the host AV to rely solely on the guidance systems and ADAS functions of the host AV to avoid a deadlock at the intersection.The control logic that selectively generates the DPCI also includes control logic that, when it determines that a blind spot threat exists due to the presence of at least one other AV at the intersection, causes the host AV and the at least one other AV to coordinate guidance systems and ADAS functions to jointly avoid and prevent a blind spot at the intersection.

[0018] In another aspect of the present disclosure, a method for blockage prevention and avoidance in autonomous vehicles comprises using one or more autonomous vehicles (AVs) and selectively altering a dynamic state of the one or more AVs with one or more actuators. The method further comprises sensing vehicle state information and information about an environment surrounding the one or more AVs with one or more sensors, wherein the one or more sensors are disposed on at least one of the one or more AVs.The method further comprises executing programmatic control logic stored in memory of one or more control modules, wherein at least one of the one or more AVs having the one or more sensors is also equipped with at least one of the one or more control modules, wherein each of the one or more control modules also includes a processor and one or more input / output (I / O) ports, the processor executing the programmatic control logic and the I / O ports communicating with the one or more sensors and the one or more actuators. The programmatic control logic receives vehicle condition information from the one or more sensors.The programmatic control logic predicts a trajectory of a host AV approaching an intersection on a road and predicts a trajectory of one or more other vehicles approaching, at, or within the intersection. The programmatic control logic transmits Multi-Directional Conflicts Identification per Driving Direction (MDCIPD) messages and the vehicle state information to a cloud computing device. Based on the MDCIPD messages and the vehicle state information, the programmatic control logic determines the waiting relationships for blockage avoidance at the intersection. The programmatic control logic sends one or more Deadlock Precaution Notifications (DPNs) and a Deadlock Prevention Coordination Instruction (DPCI) from the cloud computing device and receives one or more Deadlock Precaution Notifications (DPNs) and a Deadlock Prevention Coordination Instruction (DPCI) from the host AV of the one or more AVs.The programmatic control logic executes one or more Advanced Driver Assistance System (ADAS) functions via the one or more actuators in response to receiving one or more of the DPN and DPCI and causes the one or more AVs to avoid a stop at the intersection.

[0019] In another aspect of the present disclosure, the method further comprises receiving a basic safety message (BSM) from the one or more other vehicles. The BSM includes the vehicle size, vehicle type, vehicle speed, vehicle acceleration, vehicle location, vehicle heading, and turn signal status of the vehicle.

[0020] In another aspect of the present disclosure, the method further comprises collecting trajectory-related data for each of the one or more other vehicles and the host AV approaching the intersection by combining the vehicle state information and information about an environment surrounding the host AV and BSMs from the one or more other vehicles. The method further comprises extrapolating a trajectory for each of the one or more vehicles and the host AV from the trajectory-related data.

[0021] In another aspect of the present disclosure, the method further comprises determining the MDCIPD messages, including predicting one or more conflicts between the host AV and the other vehicles, given current heading and vehicle status information for the host AV and for each of the other vehicles.

[0022] In another aspect of the present disclosure, the method further includes determining queue relationships to avoid blockages based on directions of travel, position, and timing constraints for the host AV and the other vehicles approaching, entering, or located at the intersection, as well as the topology, laws, signage, and rules of the intersection.

[0023] In another aspect of the present disclosure, determining the waiting relationships further includes defining a right-of-way calculation for each of the host AVs and the other vehicles. The right-of-way calculation utilizes the directions, positions, and timing of the host AVs and the other vehicles approaching, entering, or within the intersection, the topology and rules of the intersection, local laws, and signage present at or near the intersection.

[0024] In another aspect of the present disclosure, the method further comprises generating the DPN from the MDCIPD messages and generating the DPCI. The DPN contains information directly indicating whether a deadlock potential exists. The DPCI contains information directly indicating control actions required for each of the host AVs and all other AVs approaching, located in, or entering the intersection to avoid deadlock at the intersection.

[0025] In another aspect of the present disclosure, generating the DPCI further comprises selectively generating the DPCI when it is determined that two or more AVs capable of transmitting the MDCIPD messages are located at the intersection, within the intersection, or into the intersection.

[0026] In another aspect of the present disclosure, selectively generating the DPCI further includes: If it is determined that there is no danger of a deadlock at the intersection, causing the host AV to rely solely on the guidance systems and ADAS functions of the host AV to cross the intersection. If it is determined that there is a deadlock potential at the intersection due to the presence of at least one other vehicle at the intersection, the method causes the host AV to rely solely on the guidance systems and ADAS functions of the host AV to avoid a deadlock at the intersection. If the method determines that there is a deadlock potential due to the presence of at least one other AV at the intersection, the method causes the host AV and the at least one other AV to coordinate the guidance systems and ADAS functions to jointly avoid and prevent a deadlock at the intersection.

[0027] In another aspect of the present disclosure, a method for blockage prevention and avoidance in autonomous vehicles comprises using one or more autonomous vehicles (AVs) and selectively changing a dynamic state of the one or more AVs with one or more actuators. The method further comprises sensing vehicle state information and information about an environment surrounding the one or more AVs with one or more sensors, wherein the one or more sensors are disposed on at least one of the one or more AVs.The method further includes executing programmatic control logic stored in memory of one or more control modules, wherein at least one of the one or more AVs having the one or more sensors is also equipped with at least one of the one or more control modules, each of the one or more control modules also having a processor and one or more input / output (I / O) ports, the processor executing the programmatic control logic and the I / O ports communicating with the one or more sensors and the one or more actuators. The programmatic control logic receives vehicle state information from the one or more sensors, including: receiving a basic safety message (BSM) from the one or more other vehicles.The BSM includes the vehicle size, vehicle type, vehicle speed, vehicle acceleration, vehicle position, vehicle heading, and vehicle turn signal status. The programmatic control logic further includes control logic that acquires trajectory-related data for each of the one or more other vehicles and a host AV approaching an intersection by combining the vehicle state information and information about the environment of the host AV, as well as BSMs from the one or more other vehicles. The programmatic control logic further includes control logic that predicts a trajectory of a host AV approaching the intersection on a roadway and a trajectory of one or more other vehicles approaching the intersection at or within the intersection by extrapolating a trajectory of each of the one or more vehicles and the host AV from the trajectory-related data.The programmatic control logic further includes control logic that determines Multi-Directional Conflicts Identification per Driving Direction (MDCIPD) messages, including predicting one or more conflicts between the host AV and the other vehicles, providing a current driving direction and vehicle state information for the host AV and each of the other vehicles, as well as the MDCIPD messages and the vehicle state information, to a cloud computing device. The programmatic control logic further includes control logic that determines, from the MDCIPD messages and the vehicle state information, queueing relationships for blockage avoidance based on the driving directions, position, and timing for each of the host AVs and the other vehicles approaching, entering, or within the intersection, as well as the intersection's topology, laws, signage, and rules.The waiting relationships define a right-of-way calculation for each of the host AVs and the other vehicles. The right-of-way calculation utilizes the directions, positions, and timing of the host AV and the other vehicles approaching, entering, or at the intersection, the intersection's topology and rules, local laws, and the signage present at or near the intersection. The programmatic control logic further includes control logic that generates one or more Deadlock Precaution Notifications (DPNs) and a Deadlock Prevention Coordination Instruction (DPCI). The DPN is generated from the MDCIPD messages and contains information that directly indicates whether a potential deadlock exists.The DPCI contains information that directly indicates the control actions required for the host AV and any other AVs approaching, in, or entering the intersection to avoid a blockage at the intersection. The programmatic control logic further includes control logic that transmits one or more of the DPN and the DPCI from the cloud computing device and receives one or more of the DPN and the DPCI from the host AV and the one or more AVs. The programmatic control logic further includes control logic that, in response to receiving one or more of the DPN and DPCI, executes one or more advanced driver assistance system (ADAS) functions via the one or more actuators and causes the one or more AVs to avoid a blockage at the intersection.

[0028] In another aspect of the present disclosure, generating the DPCI further comprises selectively generating the DPCI when two or more AVs capable of transmitting the MDCIPD messages are determined to be at, in, or on the intersection. If it is determined that there is no deadlock potential at the intersection, the method causes the host AV to rely solely on the guidance systems and ADAS functions of the host AV to cross the intersection. If the method determines that there is a deadlock potential at the intersection due to the presence of at least one other vehicle, the method causes the host AV to rely solely on the guidance systems and ADAS functions of the host AV to avoid a deadlock at the intersection.If the method determines that there is a potential for a deadlock due to the presence of at least one other AV at the intersection, it causes the host AV and the at least one other AV to coordinate the guidance systems and ADAS functions to jointly avoid and prevent a deadlock at the intersection. Fig. 1 is an environmental view of a blockage prevention and avoidance system for autonomous vehicles according to one aspect of the present disclosure; Fig. 2 is a flowchart illustrating a method for preventing and avoiding blockages for autonomous vehicles from Fig. 1 according to one aspect of the present disclosure; and Fig. 3 is a flowchart illustrating a series of exemplary decisions made by an exemplary vehicle approaching an intersection and embodying the system and method of blockage prevention and avoidance for autonomous vehicles of the Fig. 1 and Fig. 2 according to one aspect of the present disclosure.

[0029] In Fig. 1, an anti-jam system 10 for vehicles 12 is illustrated. More specifically, the vehicles 12 depicted include one or more autonomously driving vehicles (AVs) 12A-12D. However, it should be appreciated that although at least one of the vehicles 12A-12D is an AV, any one or more of the vehicles 12 depicted may be AVs without departing from the scope or intent of the present disclosure. The AVs 12A-12D may be any of a variety of vehicles 12 without departing from the scope or intent of the present disclosure. In some examples, the AVs 12A-12D may be cars, trucks, sport utility vehicles (SUVs), buses, semi-trailers, tractors used in agriculture or construction, or the like, watercraft, aircraft such as airplanes or helicopters, or the like. AVs 12A-12D are shown on road 14 at intersection 16.The road has a plurality of lanes 18 defined by pavement markings 20. The AVs 12A-12D can travel on any type of road 14 with any type of road surface 14, including any type of pavement, gravel, dirt, ice, or other types of surfaces.

[0030] The system 10 generally includes one or more sensors 22 that communicate with one or more control modules 24. While only a single sensor 22 is shown on each of the AVs 12A-12D, it should be understood that the sensor 22 shown is intended to represent any plurality of sensors 22 that may be connected to and communicate via a communications network 26, including one or more vehicle-to-vehicle (V2V) communications networks 28 and a vehicle-to-infrastructure (V2I) communications network 30. For brevity, the term "infrastructure" is used to collectively refer to the network entities capable of ad hoc wireless communications in the direct or branch link, as well as the cellular communications network owned by the service providers, so that vehicle-to-network (V2N) communications also fall within the scope of V2I.

[0031] Sensors 22 may capture AV 12 position information, electromagnetic, and / or optical information in a variety of different wavelengths, including those visible to humans, as well as infrared, ultraviolet, and other portions of the light spectrum not visible to humans. Thus, sensors 22 may be Global Positioning System (GPS) sensors, cameras, Light Detection and Ranging (LIDAR) sensors, Radio Detection and Ranging (RADAR) sensors, Sound Navigation and Ranging (SONAR) sensors, ultrasonic sensors, Inertial Measurement Units (IMUs), wheel speed sensors, or a variety of other sensors 22 that may be used to determine the dynamic state and position of vehicle 12 relative to the surrounding environment, without exceeding the scope or intent of the present disclosure.The sensors 22 may be integrated into the AVs 12A-12D by the manufacturer of the AV 12, or the sensors 22 may be installed as part of a customer service performed by the manufacturer of the AV 12 or the sensor, by a customer, or by other third parties, without departing from the scope or intent of the present disclosure. In some examples, the sensor 22 or sensors 22 may be part of a standalone sensor system 22 without departing from the scope or intent of the present disclosure.

[0032] The control modules 24 are non-generalized electronic control devices with a preprogrammed digital computer or processor 32, a non-transferable computer-readable medium or memory 34 used to store data such as control logic, software applications, instructions, computer code, data, lookup tables, etc., and one or more input / output (I / O) ports 36. The computer-readable medium or memory 34 includes any type of medium accessible by a computer, such as read-only memory (ROM), random access memory (RAM), a hard disk drive, a compact disc (CD), a digital video disc (DVD), solid-state storage, or any other type of storage. A "non-transitory" computer-readable medium or memory 34 excludes wireless, optical, or other communication links that carry electrical or other signals.A non-transitory computer-readable medium or non-transitory storage 34 includes media on which data can be permanently stored and media on which data can be stored and later overwritten, such as any type of program code, including source code, object code, and executable code. The processor 32 is configured to execute the code or instructions. In some examples, the control module 24 may be a dedicated wireless or Wi-Fi controller. The I / O ports 36 are configured to communicate via wired or wireless means, such as the communication network 26, including the V2V communication network 28 and / or the V2I communication network 30, using IEEE 802.11x Wi-Fi protocols, Bluetooth communication protocols, radio frequency (RF) protocols, or the like.

[0033] In several aspects, the control modules 24 include one or more applications 38. An application 38 is a software program configured to perform particular functions or sets of functions. The application 38 may include one or more computer programs, software components, instruction sets, procedures, functions, objects, classes, instances, associated data, or a portion thereof suitable for implementation in suitable computer-readable program code. The applications 38 may be stored in the memory 34 or in an additional or separate memory 34. Examples of the applications 38 include audio or video streaming services, audio or visual processing services, a blocking prevention application (DPA) 40, and the like.

[0034] In several aspects, the DPA 40 selectively utilizes an advanced driver assistance system (ADAS) 42 to alter the dynamics of the AV 12 through actuators of the vehicle dynamics system 44 of the AV 12. In some examples, the actuators of the vehicle dynamics system 44 may include a powertrain 46 that rotates one or more wheels 48 of the AV 12. The powertrain 46 may include an internal combustion engine, a transmission, driveshafts, and the like, and / or one or more electric motors or other powerplants without departing from the scope or intent of the present disclosure. Additional actuators of the vehicle dynamics system 44 include one or more brakes 50 that directly reduce, limit, or completely stop the rotation of the wheels 48 and / or the powertrain 46.The actuators of the vehicle dynamics system 44 may also include a steering system 52 that can change the angular orientation of one or more of the wheels 48 of the AV 12 relative to a longitudinal axis 54 of the AV 12. By changing the angular orientation of the one or more wheels 48, the direction of travel of the AV 12 can be changed.

[0035] One or more of the vehicles 12A-12D is a networked autonomous vehicle (CAV) that communicates via V2V and / or V2I communication networks 28, 30 with at least one of the other vehicles 12A-12D and / or infrastructure such as traffic signals, cloud computing devices 56, or the like. When the vehicles 12 are in the Fig. 1, they may encounter each other as shown. For human-operated vehicles, vehicle operators determine when and how to transit intersection 16 based on laws, signage, the position, and timing of each vehicle 12 approaching, entering, or located in intersection 16. In contrast, the ADAS 42 in AVs 12A-12D uses data from sensors 22 and data communicated via V2V and / or V2I communication networks 28, 30 to determine when and how each vehicle 12 will transit intersection 16. The ADAS 42 may have difficulty determining when and how each vehicle 12 will proceed in some situations, such as when multiple vehicles 12 are approaching or arriving at intersection 16 at substantially the same time.Accordingly, the system 10 of the present disclosure utilizes data communicated via the V2V and / or V2I communication networks 28, 30 within the DPA 40 to avoid situations where congestion, accidents, or other such traffic flow disruptions may be caused by a standstill within one or more AVs 12A-12D present at the intersection 16. The data communicated via the V2V and / or V2I communication networks 28, 30 may include basic safety messages (BSMs) 58, multi-direction conflict identification messages (MDCIPD) 60, deadlock precaution notifications (DPNs) 62, and / or deadlock prevention coordination instructions (DPCIs) 64, which are described in more detail below.

[0036] A deadlock is a situation in which no member of a group can proceed because each member of the group is waiting for another member to act before taking action. Deadlocks are common in multiprocessor, parallel, and distributed systems, because in these contexts, systems such as ADAS use software and / or hardware locks to arbitrate shared resources and implement process synchronization.

[0037] With reference to Fig. 2 and with continued reference to Fig. 1, the DPA 40 is presented in more detail in the form of a flow chart. More specifically, Fig. Figure 2 shows a method for deadlock prevention and prevention that utilizes the programmatic control logic of the DPA 40. In several aspects, the DPA 40 includes a plurality of subroutines or programmatic control logic portions that enable the AVs 12A-12D to avoid deadlock situations. For scenarios such as those in Fig. 1, the DPA 40 can be heuristically checked to ensure that certain steps can effectively serve the intended goals using simple representations of various communications sent over the communications network 26. As the AVs 12A-12D approach the intersection 16, one or more of the AVs 12A-12D engage the DPA 40 to avoid blocking.

[0038] By way of non-limiting example, the method for DPA 40 begins at block 100 for a host AV 12A approaching intersection 16. Since host AV 12A is about to enter intersection 16, blocks 102 and 104 are performed to determine whether host AV 12A can expect multi-directional conflicts with other vehicles 12 at intersection 16. More specifically, at block 102, host AV 12A communicates with the other AVs 12B-12D approaching or located at intersection 16 via V2V communication network 28 and receives BSM 58 information from each of the other AVs 12B-12D communicating via V2V communication network 28. The BSM 58 can contain a variety of different data types, but should be understood as a standardized communication packet that is sent regularly and periodically.In several aspects, the BSMs 58 may be standardized by the Society of Automotive Engineers International or another technical organization. In some examples, the regular periodic basis may be every tenth of a second. The BSM 58 contains data about the state of the communicating vehicle, such as vehicle size and type, speed, acceleration, location, direction, turn signal status, and the like.

[0039] In block 104, the host AV 12A receives sensor data from each of the sensors 22 onboard the host AV 12A. The sensor data may include, but is not limited to, data from a GPS sensor, optical and / or electromagnetic information from cameras, LiDAR, SONAR, ultrasonic sensors, IMUs, wheel speed sensors, and the like. Each of the other vehicles 12B-12D approaching the intersection 16 may pose a potential collision risk to the host AV 12A.

[0040] Accordingly, in block 106, the sensor data and the BSM 58 data are used as input to a programmatic control logic portion that predicts a trajectory of the other vehicles 12B-12D approaching the intersection 16. That is, based on the BSMs 58 of the other vehicles 12B-12D and the data from the onboard sensors 22 of the host AV 12A, the DPA 40 determines a probability that the host AV 12A will approach one or more of the other vehicles 12B-12D at the intersection 16 if the other vehicles 12B-12D are approaching from other directions. The exact distance between the host AV 12A and the other vehicles 12B-12D at the intersection 16 can vary considerably depending on the intersection 16, the type and size of the vehicle 12, and a number of other factors. However, a predetermined threshold for the safety distance can be used as a benchmark on which trajectory-based distance predictions can be based.

[0041] If the DPA 40 determines that, based on the trajectories of the host AV 12A and the other vehicles 12B-12D, there is a sufficiently high probability that the host AV 12A and the other vehicles 12B-12D are approaching with a probability less than the predetermined threshold, then the DPA 40 will proceed to adjust the driving functions of the host AV 12A, and if one or more of the other vehicles 12B-12D are also equipped with ADAS 42 functionality and the DPA 40, then the DPA 40 will adjust the driving functions of the one or more other vehicles 12B-12D that have the DPA 40.

[0042] In some examples, if the host AV 12A is approaching the intersection and two or more other vehicles 12B-12D are approaching the intersection 16 and their trajectory-related data indicate a probability of approach that is below the predetermined threshold, then the host AV 12A may be said to expect multidirectional conflicts. That is, the host AV 12A expects conflicts with other vehicles 12B-12D coming from two or more directions. In some examples, the other vehicles 12B-12D may be classified as potentially colliding vehicles, meaning that the other vehicles 12B-12D have already entered the intersection 16 or are about to enter it from directions other than the direction of travel of the host AV 12A.

[0043] Trajectory-related data for each of the other vehicles 12B-12D may include the location, speed, driving intent (e.g., proceed straight through intersection 16 or turn left or right at intersection 16), route, and other information that may be determined to be relevant to the trajectory of the other vehicle 12B-12D. This data may originate from the BSMs 58 and / or the on-board sensing capabilities of the host AV 12A based on data from one or more sensors 22. If only one data source (i.e., only the BSMs 58 or only the on-board sensors 22) is available, the DPA 40 may assign a lower confidence level to the trajectory-related data for each of the other vehicles 12B-12D.Conversely, if both the BSM 58 and the perception data from the onboard sensors 22 are available to the host AV 12A and the DPA 40, the trajectory-related data for the other vehicles 12B-12D may be assigned a higher confidence level that is greater than the lower confidence level. The confidence levels described above may be applied to the types of actions the host AV 12A may perform in response to the trajectory-related data. When high-confidence data is available, right-of-way calculations and ADAS 42-controlled commands to the actuators of the vehicle dynamics system 44 may be executed at a different amplitude, speed, or acceleration than when only lower-confidence data is available.

[0044] In block 108, the DPA 40 packages the MDCIPD message 60 with the predicted trajectories of the other vehicles 12B-12D approaching the intersection 16. For the host AV 12A, the MDCIPD message 60 uses the predicted trajectories of the other vehicles 12B-12D approaching the intersection 16 and the trajectory of the host AV 12A to determine whether there is a likely conflict between the host AV 12A and the other vehicles 12B-12D at the intersection 16, given the current heading and the status information of the host AV 12A. Additionally, in block 108, the DPA 40 sends the MDCIPD message 60 to the cloud computing device 56 for further processing. The MDCIPD messages 60 may indicate whether or not the host AV 12A expects multidirectional contention, which is appropriate for most scenarios, as generally described in Fig. 1 is sufficient. In other examples, the MCDIPD messages 60 may include additional information, such as the destination direction of the host AV 12A, initial directions associated with the identified conflicts, or the like. The additional information may be used in additional programmatic control logic functions of the DPA 40, such as determining wait relationships at the intersection 16 for all vehicles 12A-12D at the intersection 16, right-of-way calculations, coordination strategy for preventing blocking, and the like.

[0045] In block 110, the cloud computing device 56 receives the MDCIPD messages 60 from one or more vehicles 12 or AVs 12A-12D approaching the intersection 16 in question. In block 112, predefined driving instructions based on the topology and rules of the intersection 16 are retrieved from the sensors 22 and from the memories 34 of the control modules 24 of the host AV 12A, as well as from the memories 34 of all other vehicles 12B-12D at the intersection 16, which happen to be AVs with the DPA 40.

[0046] The MDCIPD messages 60 and the direction of travel information from blocks 110 and 112 are then analyzed in block 114 to determine the waiting relationships for the right-of-way, and, if possible, a deadlock avoidance coordination strategy is developed. That is, the programmatic control logic executed in block 114 is executed on the received MDCIPD messages 60 along with the directions of travel, the topology, and / or the rules of intersection 16 to determine whether a potential deadlock may occur at intersection 16. If it is determined that a deadlock potential exists at intersection 16, the programmatic control logic of the DPA 40, executed in block 114, derives a deadlock avoidance coordination strategy.In an example where the host AV 12A is the only AV approaching the intersection 16 during a predefined time window, the MDCIPD messages 60 relating only to the directions of travel for the host AV 12A are received in block 110. Since the host AV 12A is the only vehicle 12 with the DPA 40 in this example, the directly transmitted DPNs 62 indicate that no other vehicle 12 has transmitted an MDCIPD message 60, and accordingly, no DPCI 64 message should be generated because coordination between the host AV 12A and other vehicles 12B-12D cannot be achieved.

[0047] However, if one or more of the other vehicles 12B-12D at intersection 16 are AVs 12 using DPA 40, the MDCIPD messages 60 relating to the two or more original directions of the two or more AVs 12 at intersection 16 are received, and the DPNs 62 to be sent directly indicate and contain information about multi-direction conflicts that can be expected based on all available original directions of the vehicles 12. Based on a priority ranking of the involved AVs 12A-12D at intersection 16, along with a queue for right-of-way calculations and timing, the coordination strategy to prevent a deadlock after a potential deadlock is determined.

[0048] In block 116, the results of the analysis performed in block 114 are encapsulated in DPNs 62 and DPCIs 64 (if two or more AVs are located with the DPA 40 at the intersection 16) and sent to the corresponding AVs at the intersection 16. The DPA 40 then proceeds to block 118.

[0049] In block 118, the host AV 12A receives the DPNs 62 and DPCIs 64 (if available) from the cloud computing device 56. In block 120, the host AV 12A acts according to the received DPNs 62 and DPCIs 64 (if available). If the received DPNs 62 indicate that no other AV is present at the intersection 16 and no other AV has sent an MDCIPD message 60, then the host AV 12A relies on itself to avoid deadlock. That is, the host AV 12A will act without instruction from the cloud computing device 56. In other examples, the host AV 12A may act by assuming there is no potential deadlock or adjust its own path and / or motion planning based on the received DPCIs 64 to avoid deadlocks.

[0050] In several aspects, blocks 102-108, 118, and 120 are executed locally on host AVs 12A utilizing DPA 40, while blocks 110-116 are executed in and on cloud computing devices 56 that communicate with AVs utilizing DPA 40. Furthermore, it should be noted that DPA 40 may be executed continuously, periodically, or upon the occurrence of a particular triggering factor. In several aspects, host AV 12A may execute DPA 40 upon arrival near all intersections 16, only at certain predefined intersections 16, or the like, without departing from the scope or intent of the present disclosure.

[0051] In Fig. is with further reference to Fig.An example of simplified conditional branches corresponding to simple MDCIPD messages 60 and DPN 62 is presented in flowchart form. The example begins in block 200. In block 202, the host AV 12A determines whether a multidirectional conflict or conflicts are likely. If the host AV 12A does not expect multidirectional conflicts at intersection 16 (e.g., if it is the only vehicle 12 present), no deadlock is possible, and the example continues to block 204, where the host AV 12A proceeds through intersection 16, assuming there is no potential deadlock. Conversely, if in block 202 the host AV 12A determines that there is a possibility of a multi-directional conflict with more than one vehicle 12 approaching the intersection 16, then in block 206 the DPA 40 judges from the DPNs 62 whether other AVs are present at the intersection 16 and have sent an MDCIPD message 60.If no other AVs have sent an MDCIPD message 60, the example proceeds to block 208, and the host AV 12A relies solely on its own guidance systems, the DPA 40 and the ADAS 42, to transit intersection 16 and avoid a blockage. Conversely, if the received DPNs 62 indicate that another AV is present at intersection 16 and has sent an MDCIPD message 60, the example proceeds to block 210. In block 210, if the DPNs 62 received from the host AV 12A indicate that none of the other AVs expect a multidirectional conflict with the DPA 40, then in block 212 the host AV 12A adjusts its path and motion planning based on the received DPCIs 64 to avoid and prevent a blockage at intersection 16.It should be understood that if other AVs are present at intersection 16 and using DPA 40, each of the AVs at intersection 16 will adjust path and motion planning based on the received DPCIs 64 to avoid and prevent blocking. In contrast, at block 210, if the DPNs 62 received by host AV 12A indicate that another AV does not expect multidirectional conflicts with DPA 40, then host AV 12A assumes there is no potential for blocking and proceeds at its discretion to block 204, as previously described.

[0052] A system 10 and method for deadlock preparedness and prevention for autonomous vehicles 12 of the present disclosure offers several advantages. These include the ability to operate to allow host AVs 12A to mitigate the risk of deadlock at an intersection 16 dominated by autonomous vehicles, with the effective prevention of deadlock achievable with the presence of two or more V2V and V2I-capable AVs, or at least preventive notification of potential deadlock with the presence of only a single V2V and V2I-capable AV.The system 10 and method 100 of the present disclosure are resource efficient and are based on the introduction of a few Vehicle-to-Everything (V2X) messages such as BSMs 58, MDCIPD messages 60, DPNs 62, and DPCIs 64, which are either currently standardized or do not require standardization, and a cloud computing device 56 that performs lightweight computations, thus improving ADAS functionality, redundancy, and speed without increasing complexity and while maintaining or improving driver comfort.

Claims

[1] A system (10) for blockage prevention and avoidance in autonomous vehicles, the system (10) comprising: one or more autonomous vehicles, AVs (12A, 12B, 12C, 12D); one or more actuators, wherein the one or more actuators selectively change a dynamic state of the one or more AVs (12A, 12B, 12C, 12D); one or more sensors (22), wherein the one or more sensors (22) are arranged on at least one of the one or more AVs (12A, 12B, 12C, 12D) and detect vehicle condition information and information about an environment around the one or more AVs (12A, 12B, 12C, 12D); one or more control modules (24), wherein the at least one of the one or more AVs (12A, 12B, 12C, 12D) with the one or more sensors (22) is also equipped with at least one of the one or more control modules (24), wherein each of the one or more control modules (24) has a memory (34), a processor (32), and one or more input / output ports (36), I / O, wherein the memory (34) stores programmatic control logic, the processor (32) executes the programmatic control logic, and the I / O ports (36) communicate with the one or more sensors (22) and the one or more actuators; wherein the programmatic control logic comprises: a first control logic for receiving vehicle status information; second control logic for predicting a trajectory of a host AV (12A) approaching an intersection on a road and for predicting a trajectory of one or more other vehicles approaching the intersection, at or within the intersection; a third control logic for transmitting MDCIPD messages, Multi-Directional Conflicts Identification per Driving Direction, and the vehicle state information to a cloud computing device (56); a fourth control logic for determining waiting relationships for blockage avoidance at the intersection based on the MDCIPD messages and the vehicle state information; a fifth control logic for transmitting from the cloud computing device (56) and receiving one or more deadlock prevention notifications, DPN (62), and a deadlock prevention coordination instruction, DPCI (64), by the host AV (12A) of the one or more AVs (12A, 12B, 12C, 12D); and a sixth control logic for executing one or more functions of the advanced driver assistance system, ADAS, via the one or more actuators in response to receiving one or more of the DPN and DPCI and for causing the one or more AVs to avoid a blockage at the intersection wherein the first control logic further comprises control logic for receiving a basic safety message, BSM (58), from the one or more other vehicles (12A, 12B, 12C, 12D), the BSM (58) comprising data about the state of the communicating vehicle, wherein the second control logic continues to include: Control logic for collecting trajectory-related data for each of the one or more other vehicles and the host AV (12A) approaching the intersection by combining the vehicle state information and information about an environment surrounding the host AV (12A) and BSMs from the one or more other vehicles; and Control logic for extrapolating a trajectory of each of the one or more vehicles (12B, 12C, 12D) and the host AV (12A) from the trajectory-related data. [2] The system (10) of claim 1, wherein the BSM comprises: Vehicle size, vehicle type, vehicle speed, vehicle acceleration, vehicle location, vehicle direction, and vehicle turn signal status. [3] The system (10) of claim 1, wherein the third control logic further comprises: Control logic for determining the MDCIPD messages, including predicting one or more conflicts between the host AV (12A) and the other vehicles, taking into account a current direction of travel and vehicle state information for the host AV (12A) and for each of the other vehicles. [4] The system (10) of claim 1, wherein the fourth control logic further comprises: Control logic for determining waiting relationships to avoid a blockage based on directions of travel, position and timing for each of the host AVs (12A) and the other vehicles approaching, entering or located in the intersection, as well as the topology, laws, signage and rules of the intersection. [5] The system (10) of claim 4, wherein the wait relationships define a right-of-way calculation for each of the host AVs (12A) and the other vehicles, and wherein the right-of-way calculation uses directions of travel, positions and times of each of the host AVs (12A) and the other vehicles approaching, entering or within the intersection, the topology and rules of the intersection, local laws and signage present at or near the intersection. [6] The system (10) of claim 1, wherein the fifth control logic further comprises: Control logic for generating the DPN from the MDCIPD messages; and Control logic for generating the DPCI; where the DPN contains information that directly indicates whether a potential blockage exists; and wherein the DPCI contains information directly indicative of control actions required for each of the host AVs (12A) and all other AVs (12B, 12C, 12D) approaching, located in, or entering the intersection to avoid a blockage at the intersection. [7] The system (10) of claim 6, wherein the control logic for generating the DPCI further comprises: Control logic that selectively generates the DPCI when it detects that two or more AVs capable of sending the MDCIPD messages are at, in, or on the intersection. [8] The system (10) of claim 7, wherein the control logic that selectively generates the DPCI further comprises: Control logic that, when determining that there is no risk of blockage at the intersection, causes the host AV (12A) to rely solely on the guidance systems and ADAS functions of the host AV (12A) when crossing the intersection; Control logic that, when it determines that there is a risk of blocking at the intersection due to the presence of at least one other vehicle at the intersection, causes the host AV (12A) to rely exclusively on the guidance systems and ADAS functions of the host AV (12A) to avoid blocking at the intersection; and Control logic that, when determining that there is a risk of blocking at the intersection due to the presence of at least one other AV at the intersection, causes the host AV (12A) and the at least one other AV to coordinate guidance systems and ADAS functions to jointly avoid and prevent a blocking at the intersection. [9] A method for blockage prevention and avoidance in autonomous vehicles, the method comprising: with one or more autonomous vehicles, AVs (12A, 12B, 12C, 12D); selectively changing a dynamic state of the one or more AVs (12A, 12B, 12C, 12D) with one or more actuators; Acquiring vehicle condition information and information about an environment surrounding the one or more AVs (12A, 12B, 12C, 12D) with one or more sensors (22), wherein the one or more sensors (22) are arranged on at least one of the one or more AVs (12A, 12B, 12C, 12D); Executing programmatic control logic stored in a memory (34) of one or more control modules (24), wherein at least one of the one or more AVs (12A, 12B, 12C, 12D) having the one or more sensors (22) is also equipped with at least one of the one or more control modules (24), wherein each of the one or more a plurality of control modules (24) also comprising a processor (32) and one or more input / output ports (36), I / O, wherein the processor (32) executes the programmatic control logic and the I / O ports (36) are in communication with the one or more sensors (22) and the one or more actuators; wherein the programmatic control logic comprises: Receiving vehicle condition information from the one or more sensors, including: Receiving a basic safety message, BSM, from the one or more other vehicles, the BSM comprising: Vehicle size, vehicle type, vehicle speed, vehicle acceleration, vehicle location, vehicle direction and vehicle turn signal status; Collecting trajectory-related data for each of the one or more other vehicles and a host AV (12A) approaching an intersection by combining the vehicle state information and information about an environment surrounding the host AV (12A) and BSMs from the one or more other vehicles; and predicting a trajectory of a host AV (12A) approaching the intersection on a road and predicting a trajectory of one or more other vehicles approaching the intersection, at or within the intersection, by extrapolating a trajectory of each of the one or more vehicles and the host AV (12A) from the trajectory-related data; Determining MDCIPD messages, Multi-Directional Conflicts Identification per Driving Direction, including predicting one or more conflicts between the host AV (12A) and the other vehicles, wherein a current driving direction and vehicle state information for the host AV (12A) and for each of the other vehicles, as well as the MDCIPD messages and the vehicle state information, are provided to a cloud computing device (56); Determining queue relationships for blockage prevention from the MDCIPD messages and vehicle state information based on directions of travel, positions, and timing for each of the host AVs (12A) and the other vehicles approaching, entering, or within the intersection, as well as the topology, laws, signage, and rules of the intersection, wherein the queue relationships define a right-of-way calculation for each of the host AVs (12A) and the other vehicles, and wherein the right-of-way calculation uses the directions of travel, positions, and timing of each of the host AVs (12A) and the other vehicles approaching, entering, or within the intersection, the topology and rules of the intersection, local laws, and signage present at or near the intersection; Generation of one or more Deadlock Precaution Notifications, DPN, and a Deadlock Prevention Coordination Instruction, DPCI; where the DPN is generated from the MDCIPD messages and contains information that directly indicates whether there is a potential for blocking by the; and wherein the DPCI contains information directly indicative of control actions required for each of the host AVs (12A) and all other AVs (12B, 12C, 12D) approaching, located in, or entering the intersection to avoid a blockage at the intersection; Transmitting from the cloud computing device and receiving the one or more AVs (12A, 12B, 12C, 12D) by the host AV (12A), one or more of the DPN and the DPCI; and Executing one or more functions of the advanced driver assistance system, ADAS, via the one or more actuators in response to receiving one or more of the DPN and DPCI and causing the one or more AVs (12A, 12B, 12C, 12D) to avoid a dead end at the intersection.

Citation Information

Patent Citations

  • procedure for handling a control chart

    DE102015219470A1

  • Navigating multi-way stop intersections with an autonomous vehicle

    DE102020126217A1

  • Systems and methods for controlling automated driving based on the complexity of intersections

    DE102021114596A1

  • Autonomous vehicle system

    DE112020001642T5

  • SYSTEMS AND METHODS FOR SELECTIVE DETERMINATION OF A VEHICLE

    DE112020005275T5