Avoidance control method and avoidance control system for autonomous vehicle

Abstract

The invention discloses an avoidance control method of an autonomous vehicle and an avoidance control system thereof, and the avoidance control system is used for the autonomous vehicle. The avoidance control method of the autonomous vehicle comprises the following steps: obtaining roadside sensing information provided by roadside equipment and working condition sensing information provided by a vehicle working condition sensing system; determining vehicle collision information according to the roadside sensing information; and controlling the carriage state of the autonomous vehicle according to the vehicle collision information and the working condition sensing information. According to the method, the carriage state is adjusted in real time in the driving process, the rear vehicle is actively avoided, collision is avoided, and the safety of the automatic driving vehicle is improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a collision avoidance control method and a collision avoidance control system for an autonomous vehicle. Background Technology

[0002] With the continuous development of intelligent driving technology, more and more commercial vehicles are using autonomous driving technology. Because commercial vehicles carry large containers at the rear, it is difficult for commercial vehicle drivers to judge the situation of vehicles directly behind them. When autonomous commercial vehicles decelerate suddenly on highways, it is easy for vehicles behind them to collide with the autonomous commercial vehicles. Summary of the Invention

[0003] This invention aims to at least solve one of the technical problems existing in the prior art. Therefore, one objective of this invention is to propose a collision avoidance control method for autonomous vehicles, which adjusts the vehicle's state in real time during operation to actively avoid vehicles behind, thereby preventing collisions and improving the safety of autonomous vehicles.

[0004] The second objective of this invention is to provide a collision avoidance control system for autonomous vehicles.

[0005] A first aspect of the present invention provides a collision avoidance control method for an autonomous vehicle, which is used in a collision avoidance control system for an autonomous vehicle. The collision avoidance control method for an autonomous vehicle includes: acquiring roadside perception information provided by roadside equipment and operational condition perception information provided by a vehicle operational condition perception system; determining vehicle collision information based on the roadside perception information; and controlling the cabin state of the autonomous vehicle based on the vehicle collision information and the operational condition perception information.

[0006] The obstacle avoidance control method for autonomous vehicles according to embodiments of the present invention integrates roadside perception information provided by roadside equipment and vehicle condition perception information provided by the vehicle condition perception system to comprehensively assess the collision risk between the autonomous vehicle and the following vehicle. Based on the collision risk, the method adjusts the cabin state of the autonomous vehicle in real time to actively avoid the following vehicle, thereby preventing a collision and improving the safety of the autonomous vehicle.

[0007] In some embodiments, the roadside equipment includes a roadside camera and a roadside lidar device; the roadside perception information is obtained by image fusion based on the 2D perception information collected by the roadside camera and the 3D perception information collected by the roadside lidar device.

[0008] In some embodiments, the vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it. The working condition perception information includes road slope information and vehicle cargo load status. Controlling the vehicle cargo state of the autonomous vehicle based on the vehicle collision information and the working condition perception information includes: determining the remaining collision time based on the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and controlling the vehicle cargo state of the autonomous vehicle based on the remaining collision time, road slope information, and vehicle cargo load status.

[0009] In some embodiments, controlling the cabin state of the autonomous vehicle based on the remaining collision time, road slope information, and cabin load status includes: not controlling the cabin of the autonomous vehicle when any of the following conditions are met: determining that the remaining collision time is greater than a first preset duration; determining that the remaining collision time is less than or equal to the first preset duration and the cabin load status is full.

[0010] In some embodiments, controlling the cabin state of the autonomous vehicle based on the remaining collision time, road slope information, and cabin load status includes: if the remaining collision time is less than or equal to a first preset duration, the cabin load status is empty, and the road slope information is greater than or equal to a first preset slope value and less than or equal to a second preset slope value, controlling the cabin of the autonomous vehicle to shorten along the vehicle length direction by a first preset distance; if the remaining collision time is less than or equal to the first preset duration, the cabin load status is empty, and the road slope information is less than the first preset slope value, controlling the cabin of the autonomous vehicle to shorten along the vehicle length direction by a second preset distance; if the remaining collision time is less than or equal to the first preset duration, the cabin load status is empty, and the road slope information is greater than the second preset slope value, controlling the cabin of the autonomous vehicle to shorten along the vehicle length direction by a third preset distance; wherein the second preset distance is greater than the first preset distance, and the first preset distance is greater than the third preset distance.

[0011] A second aspect of the present invention provides a collision avoidance control system for an autonomous vehicle, comprising: a roadside device for collecting roadside perception information; a vehicle condition perception system for collecting condition perception information; an edge computing unit communicatively connected to the roadside device for determining vehicle collision information based on the roadside perception information; and a cloud platform communicatively connected to the vehicle condition perception system and the edge computing unit, wherein the cloud platform controls the cabin state of the autonomous vehicle based on the vehicle collision information and the condition perception information.

[0012] According to the embodiment of the present invention, the collision avoidance control system of an autonomous vehicle can determine vehicle collision information through the edge computing unit 400, and use the cloud platform 500 to fuse the roadside perception information provided by the roadside equipment 200 and the working condition perception information provided by the vehicle working condition perception system 300 to comprehensively judge the collision risk between the autonomous vehicle and the following vehicle. Based on the collision risk, the system can adjust the cabin state of the autonomous vehicle in real time, actively avoid the following vehicle, avoid collision, and improve the safety of the autonomous vehicle.

[0013] In some embodiments, the roadside equipment includes a roadside camera for acquiring 2D perception information and a roadside lidar device for acquiring 3D perception information; the edge computing unit is further configured to perform image fusion on the 2D perception information and the 3D perception information to obtain the roadside perception information.

[0014] In some embodiments, the vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; the working condition perception information includes road slope information and vehicle load status; the cloud platform is used to determine the remaining collision time based on the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and to control the vehicle's cabin state based on the remaining collision time, road slope information, and vehicle load status.

[0015] In some embodiments, the cloud platform is specifically used to: have no control over the passenger compartment of the autonomous vehicle when any of the following conditions are met: determining that the remaining collision time is greater than a first preset duration; determining that the remaining collision time is less than or equal to the first preset duration and the passenger compartment is fully loaded.

[0016] In some embodiments, the cloud platform is further configured to: if the remaining collision time is less than or equal to a first preset duration, the vehicle's load status is empty, and the road slope information is greater than or equal to a first preset slope value and less than or equal to a second preset slope value, control the vehicle's cargo compartment of the autonomous driving vehicle to shorten by a first preset distance along the vehicle's length direction; if the remaining collision time is less than or equal to the first preset duration, the vehicle's load status is empty, and the road slope information is less than the first preset slope value, control the vehicle's cargo compartment of the autonomous driving vehicle to shorten by a second preset distance along the vehicle's length direction; if the remaining collision time is less than or equal to the first preset duration, the vehicle's load status is empty, and the road slope information is greater than the second preset slope value, control the vehicle's cargo compartment of the autonomous driving vehicle to shorten by a third preset distance along the vehicle's length direction; wherein, the first preset distance is less than the second preset distance and greater than the third preset distance.

[0017] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart of an obstacle avoidance control method for an autonomous vehicle according to an embodiment of the present invention; Figure 2 This is a schematic diagram of an autonomous vehicle according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the obstacle avoidance control system of an autonomous vehicle according to an embodiment of the present invention.

[0019] Figure label: 1000 obstacle avoidance control system for autonomous vehicles 100 autonomous vehicles; 200 roadside devices; 300 vehicle condition perception systems; 400 edge computing units; 500 cloud platforms; 10. Carriage compartment; 11. Rear of carriage compartment; 12. Front of carriage compartment; 1. Roadside camera; 2. Roadside lidar equipment; 3. Empty / full load sensor; 4. Slope sensor; 5. Onboard communication module; 6. Roadside communication module; 7. Autonomous driving vehicle controller; 8. Drive motor; 9. Carriage extension device. Detailed Implementation

[0020] The embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. The embodiments of the present invention are described in detail below.

[0021] With the continuous development of intelligent driving technology, more and more commercial vehicles are using autonomous driving technology. Because commercial vehicles carry large containers at the rear, it is difficult for commercial vehicle drivers to judge the situation of vehicles directly behind them. When autonomous commercial vehicles decelerate suddenly on highways, it is easy for vehicles behind them to collide with the autonomous commercial vehicles.

[0022] To address the aforementioned issues, a first aspect of this invention proposes a collision avoidance control method for autonomous vehicles. This method adjusts the vehicle's state in real time during operation to actively avoid vehicles behind, thereby preventing collisions and improving the safety of autonomous vehicles.

[0023] The following is for reference. Figure 1 The present invention describes an obstacle avoidance control method for an autonomous vehicle according to an embodiment of the present invention. The obstacle avoidance control method for an autonomous vehicle includes steps S1-S3, the specific steps of which are as follows.

[0024] Step S1: Obtain roadside perception information provided by roadside equipment and vehicle condition perception information provided by vehicle condition perception system.

[0025] Specifically, roadside equipment can be deployed along the road to monitor roadside perception information in real time. This information can include the motion information of autonomous vehicles and the motion information of vehicles behind them. The vehicle motion information can include the autonomous vehicle's position, speed, angle, and direction. The vehicle condition perception system can be deployed in the vehicle compartment to collect condition perception information in real time. This information can include the vehicle's internal working status and the vehicle's working environment status. For example, the vehicle's internal working status can include the autonomous vehicle's load status, and the working environment status can include the autonomous vehicle's driving gradient.

[0026] Step S2: Determine vehicle collision information based on roadside perception information.

[0027] Specifically, based on roadside perception information, a pre-set collision risk assessment model is used to assess the collision risk between autonomous vehicles and vehicles behind them, thereby determining whether a collision is possible.

[0028] Step S3: Control the cabin state of the autonomous vehicle based on vehicle collision information and working condition perception information.

[0029] For details, please refer to Figure 2 As shown, the passenger compartment 10 of the autonomous vehicle 100 is retractable, and the rear part 11 of the passenger compartment can move along the length of the vehicle. Due to the long passenger compartment of the existing autonomous vehicle, it is difficult for the driver to judge the driving situation of the vehicles behind during driving, so collisions are very likely to occur. In this regard, this application combines vehicle collision information and working condition perception information to comprehensively judge the collision risk between the vehicles behind and the autonomous vehicle. Thus, the passenger compartment state can be adjusted according to the collision risk. When the collision risk is high, the rear part 11 of the passenger compartment can be controlled to move towards the front part 12 of the passenger compartment along the length of the vehicle, thereby changing the overall length of the passenger compartment 10, actively avoiding the vehicles behind, reducing the collision risk, and improving the safety of the autonomous vehicle.

[0030] The obstacle avoidance control method for autonomous vehicles according to embodiments of the present invention integrates roadside perception information provided by roadside equipment and vehicle condition perception information provided by the vehicle condition perception system to comprehensively assess the collision risk between the autonomous vehicle and the following vehicle. Based on the collision risk, the method adjusts the cabin state of the autonomous vehicle in real time to actively avoid the following vehicle, thereby preventing a collision and improving the safety of the autonomous vehicle.

[0031] In some embodiments, the roadside equipment includes a roadside camera and a roadside lidar device; the roadside perception information is obtained by image fusion based on 2D perception information collected by the roadside camera and 3D perception information collected by the roadside lidar device.

[0032] In some embodiments, vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and operating condition perception information includes road slope information and vehicle compartment load status. Controlling the vehicle compartment state of the autonomous vehicle based on the vehicle collision information and operating condition perception information includes: determining the remaining collision time based on the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and controlling the vehicle compartment state of the autonomous vehicle based on the remaining collision time, road slope information, and vehicle compartment load status.

[0033] In some embodiments, controlling the cabin state of an autonomous vehicle based on the remaining collision time, road slope information, and cabin load status includes: having no control over the cabin of the autonomous vehicle when any of the following conditions are met: determining that the remaining collision time is greater than a first preset duration; determining that the remaining collision time is less than or equal to the first preset duration and the cabin load status is full.

[0034] In some embodiments, controlling the cabin state of the autonomous vehicle based on the remaining collision time, road slope information, and cabin load status further includes: if the remaining collision time is less than or equal to a first preset duration, the cabin load status is empty, and the road slope information is greater than or equal to a first preset slope value and less than or equal to a second preset slope value, controlling the cabin of the autonomous vehicle to retract a first preset distance; if the remaining collision time is less than or equal to the first preset duration, the cabin load status is empty, and the road slope information is less than the first preset slope value, controlling the cabin of the autonomous vehicle to retract a second preset distance; if the remaining collision time is less than or equal to the first preset duration, the cabin load status is empty, and the road slope information is greater than the second preset slope value, controlling the cabin of the autonomous vehicle to retract a third preset distance; the second preset distance is greater than the first preset distance, and the first preset distance is greater than the third preset distance.

[0035] A second aspect of the present invention provides a collision avoidance control system for an autonomous vehicle, comprising: a roadside device for collecting roadside perception information; a vehicle condition perception system for collecting condition perception information; an edge computing unit communicatively connected to the roadside device for determining vehicle collision information based on the roadside perception information; and a cloud platform communicatively connected to the vehicle condition perception system and the edge computing unit, wherein the cloud platform is used to control the cabin state of the autonomous vehicle based on the vehicle collision information and the condition perception information.

[0036] According to an embodiment of the present invention, the collision avoidance control system for autonomous vehicles can determine vehicle collision information through an edge computing unit, and then use a cloud platform to integrate roadside perception information provided by roadside equipment and vehicle condition perception information provided by the vehicle condition perception system to comprehensively judge the collision risk between the autonomous vehicle and the following vehicle. Based on the collision risk, the system can adjust the cabin state of the autonomous vehicle in real time, actively avoid the following vehicle, avoid collision, and improve the safety of the autonomous vehicle.

[0037] In some embodiments, the roadside equipment includes a roadside camera for acquiring 2D perception information and a roadside lidar device for acquiring 3D perception information; the edge computing unit is also used to perform image fusion on the 2D perception information and the 3D perception information to obtain roadside perception information.

[0038] Specifically, roadside cameras can be deployed above roadside poles, employing high-definition megapixel vision sensors. Primarily used in daytime scenarios, they can monitor the movement of autonomous vehicles and vehicles behind them in real time. Roadside LiDAR, also deployed above roadside poles, uses a 360° rotating mechanical LiDAR system, primarily used in nighttime scenarios to perform 360° real-time surround scanning of the movement of autonomous vehicles and vehicles behind them. The superposition of 2D and 3D perception information constructs a dynamic stereoscopic visual model, which can be used to calculate vehicle collision information.

[0039] In some embodiments, vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; the condition perception information includes road slope information and vehicle load status; the cloud platform is used to determine the remaining collision time based on the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and to control the vehicle's cabin status based on the remaining collision time, road slope information, and vehicle load status.

[0040] Specifically, the remaining collision time is the time required for a collision between the following vehicle and the autonomous vehicle while maintaining the current speed and direction. When the remaining collision time is lower than a certain preset threshold, it indicates that the distance between the following vehicle and the autonomous vehicle is too close, posing a risk of collision, and measures need to be taken to avoid the collision. On the other hand, considering the impact of uphill and downhill conditions on collision risk, the collision risk is lower on uphill sections and higher on downhill sections, and the road gradient also affects the collision risk. Under high load conditions, the vehicle's inertia is greater and collisions are more likely. Therefore, this application further combines the road gradient and the load condition of the vehicle to dynamically adjust the vehicle's state to avoid collisions. Refer to Formula 1 to understand the calculation of the remaining collision time, where TTC is the remaining collision time, d is the distance between the front of the autonomous vehicle and the following vehicle, and v_rel is the relative speed difference between the two vehicles.

[0041] TTC = d / (v_rel + 0.001) (Formula 1) In some embodiments, the cloud platform is specifically used to: have no control over the passenger compartment of the autonomous vehicle when any of the following conditions are met: determining that the remaining collision time is greater than a first preset duration; determining that the remaining collision time is less than or equal to the first preset duration and the passenger compartment is fully loaded.

[0042] Specifically, if the remaining collision time between the autonomous vehicle and the vehicle behind it is determined to be greater than a first preset time, there is no risk of collision between the autonomous vehicle and the vehicle behind it, therefore no control is exercised on the autonomous vehicle. If the remaining collision time is determined to be less than or equal to the first preset time and the cargo compartment is fully loaded, the cargo compartment cannot be adjusted because the vehicle is fully loaded, and forcibly adjusting the cargo compartment position may affect the stability of the cargo. The first preset time can be set according to the actual situation, for example, it can be set to 3s, 4s, or 5s, etc., and no specific setting is made here. The full-load and empty-load states of the cargo compartment can be set as follows: when the vehicle weight is less than 0.5 tons, the cargo compartment is judged to be empty; when the vehicle weight is greater than or equal to 0.5 tons, the cargo compartment is judged to be fully loaded.

[0043] In some embodiments, the cloud platform is further configured to: control the autonomous vehicle's cargo compartment to retract a first preset distance if the remaining collision time is less than or equal to a first preset duration, the cargo compartment is empty, and the road slope information is greater than or equal to a first preset slope value and less than or equal to a second preset slope value; control the autonomous vehicle's cargo compartment to retract a second preset distance if the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is less than the first preset slope value; and control the autonomous vehicle's cargo compartment to retract a third preset distance if the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than the second preset slope value; wherein the first preset distance is less than the second preset distance and greater than the third preset distance.

[0044] Specifically, if it is determined that the remaining collision time is less than or equal to the first preset time, the cargo compartment is empty, and the road slope information is greater than or equal to the first preset slope value and less than or equal to the second preset slope value, then the autonomous vehicle is on a road with a relatively gentle slope and there is a moderate risk of collision. The rear of the cargo compartment is controlled to move a first preset distance along the length of the vehicle towards the front of the cargo compartment, and the overall length of the cargo compartment is shortened to avoid a collision between the autonomous vehicle and the vehicle behind.

[0045] If it is determined that the remaining collision time is less than or equal to the first preset time, the vehicle is unloaded, and the road slope is less than the first preset slope value, the collision risk is high because downhill sections will increase the collision risk. In this case, the rear of the vehicle is moved a second preset distance along the length of the vehicle to the front of the vehicle, the overall length of the vehicle is shortened, more physical avoidance space is provided, and the autonomous vehicle is prevented from colliding with vehicles behind it.

[0046] If it is determined that the remaining collision time is less than or equal to the first preset time, the cargo compartment is empty, and the road slope information is greater than the second preset slope value, then the autonomous vehicle is on a steep uphill road, and the vehicles behind are unlikely to collide with the autonomous vehicle. Therefore, the collision risk is low. Only the rear of the cargo compartment is controlled to move a third preset distance along the length of the vehicle to the front of the cargo compartment to avoid collision between the autonomous vehicle and the vehicles behind.

[0047] The first preset slope value, the second preset slope value, the first preset distance, the second preset distance, and the third preset distance can be set according to the actual situation. For example, the first preset distance can be set to 20cm, the second preset distance to 30cm, and the third preset distance to 10cm; the first preset slope value can be set to -5°, and the second preset slope value can be set to 5°, etc. No specific restrictions are imposed here.

[0048] A second aspect of this invention provides a collision avoidance control system 1000 for an autonomous vehicle, with reference to... Figure 3As shown, the obstacle avoidance control system 1000 for autonomous vehicles includes: roadside equipment 200, vehicle condition perception system 300, edge computing unit 400, and cloud platform 500.

[0049] Among them, the roadside equipment 200 is used to collect roadside perception information; the vehicle condition perception system 300 is used to collect condition perception information; the edge computing unit 400 is communicatively connected to the roadside equipment 200 and is used to determine the roadside perception information based on the roadside perception information; the cloud platform 500 is communicatively connected to the vehicle condition perception system 300 and the edge computing unit 400, and the cloud platform 500 is used to control the cabin state of the autonomous vehicle based on the vehicle collision information and the condition perception information.

[0050] According to an embodiment of the present invention, the autonomous vehicle avoidance control system 1000 can determine vehicle collision information through the edge computing unit 400, and use the cloud platform 500 to fuse the roadside perception information provided by the roadside equipment 200 and the working condition perception information provided by the vehicle working condition perception system 300 to comprehensively judge the collision risk between the autonomous vehicle and the following vehicle. Based on the collision risk, the system can adjust the cabin state of the autonomous vehicle in real time, actively avoid the following vehicle, avoid collision, and improve the safety of the autonomous vehicle.

[0051] In some embodiments, such as Figure 3 As shown, the roadside equipment 200 includes a roadside camera 1 for collecting 2D perception information and a roadside lidar device 2 for collecting 3D perception information; the edge computing unit 400 is also used to perform image fusion on the 2D perception information and the 3D perception information to obtain vehicle collision information.

[0052] Specifically, the roadside camera 1 can be deployed above the roadside poles. It uses a high-definition vision sensor with megapixels and is mainly used in daytime scenarios. It can monitor the movement information of autonomous vehicles and vehicles behind them in real time. The roadside lidar 2 can be deployed above the roadside poles. It uses a 360-degree rotating mechanical lidar and is mainly used in nighttime scenarios. It can scan the movement information of autonomous vehicles and vehicles behind them in real time with a 360° surround view. The edge computing unit 400 constructs a stereo dynamic visual model by superimposing 2D perception information and 3D perception information to calculate vehicle collision information.

[0053] In some embodiments, vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; the condition perception information includes road slope information and vehicle load status; the cloud platform is used to determine the remaining collision time based on the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and to control the vehicle's cabin status based on the remaining collision time, road slope information, and vehicle load status.

[0054] Specifically, such as Figure 3 As shown, the vehicle condition perception system 300 includes an empty / full load sensor 3 and a slope sensor 4. The empty / full load sensor 3 is located at the rear of the autonomous vehicle's cargo compartment and can collect the vehicle's weight status in real time to determine the cargo compartment's load status. When the vehicle weight is less than 0.5 tons, the cargo compartment is considered empty; when the vehicle weight is greater than or equal to 0.5 tons, the cargo compartment is considered fully loaded, and this information is transmitted to the vehicle communication module 5. The slope sensor 4 is located at the bottom of the autonomous vehicle and monitors the slope information of the road where the autonomous vehicle is located in real time. Uphill sections are marked as +, and downhill sections are marked as -, and the road slope information is transmitted to the vehicle communication module 5. Block 5, the vehicle-mounted communication module 5, is located at the bottom of the autonomous vehicle. It can receive instruction information transmitted by the roadside communication module 6 via 4G / 5G wireless communication. At the same time, it uploads the empty / full load status information of the autonomous vehicle and the slope information of the road to the roadside communication module 6, and transmits them together to the cloud platform 500 for control judgment of the vehicle's status. The roadside communication module 6 can receive instruction information transmitted by the cloud platform and transmit the instructions to the vehicle-mounted communication module 5 via wireless communication to control the status of the autonomous vehicle's vehicle. At the same time, it uploads the vehicle load status and the slope information of the road to the autonomous vehicle transmitted by the vehicle-mounted communication module 5 for the cloud platform's instruction judgment.

[0055] In some embodiments, the cloud platform is specifically used to: have no control over the autonomous vehicle when any of the following conditions are met: determining that the remaining collision time is greater than a first preset duration; determining that the remaining collision time is less than or equal to the first preset duration and the vehicle is fully loaded.

[0056] Specifically, after obtaining the remaining collision time and the cargo compartment load status, if the cloud platform 500 determines that the remaining collision time between the autonomous vehicle and the vehicle behind it is greater than the first preset time, there is no risk of collision between the autonomous vehicle and the vehicle behind it, so no control is exercised on the autonomous vehicle; if it determines that the remaining collision time is less than or equal to the first preset time and the cargo compartment load status is full, the cargo compartment status cannot be adjusted because the vehicle is fully loaded, and forcibly adjusting the cargo compartment position may affect the stability of the cargo.

[0057] In some embodiments, the cloud platform is further configured to: control the autonomous vehicle's cargo compartment to retract a first preset distance if the remaining collision time is less than or equal to a first preset duration, the cargo compartment is empty, and the road slope information is greater than or equal to a first preset slope value and less than or equal to a second preset slope value; control the autonomous vehicle's cargo compartment to retract a second preset distance if the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is less than the first preset slope value; and control the autonomous vehicle's cargo compartment to retract a third preset distance if the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than the second preset slope value; wherein the second preset distance is greater than the first preset distance, and the first preset distance is greater than the third preset distance.

[0058] Specifically, after acquiring the remaining collision time, the vehicle's load status, and the road slope information, if the cloud platform 500 determines that the remaining collision time is less than or equal to the first preset duration, the vehicle's load status is empty, and the road slope information is greater than or equal to the first preset slope value and less than or equal to the second preset slope value, then the autonomous vehicle is on a road with a relatively gentle slope and there is a moderate risk of collision. The system then controls the rear of the vehicle to move a first preset distance along the length of the vehicle towards the front, shortening the length of the vehicle and preventing the autonomous vehicle from colliding with vehicles behind it.

[0059] If it is determined that the remaining collision time is less than or equal to the first preset time, the vehicle is unloaded, and the road slope is less than the first preset slope value, the collision risk is high because downhill sections will increase the collision risk. In this case, the rear of the vehicle is moved a second preset distance along the length of the vehicle to the front of the vehicle, the length of the vehicle is shortened, more physical avoidance space is provided, and the autonomous vehicle is prevented from colliding with the vehicle behind.

[0060] If it is determined that the remaining collision time is less than or equal to the first preset time, the cargo compartment is empty, and the road slope information is greater than the second preset slope value, then the autonomous vehicle is on a steep uphill road, and the vehicles behind are unlikely to collide with the autonomous vehicle. Therefore, the collision risk is low. Only the rear of the cargo compartment is controlled to move a third preset distance along the length of the vehicle to the front of the cargo compartment to avoid collision between the autonomous vehicle and the vehicles behind.

[0061] For details, please refer to Figure 2 and Figure 3As shown, the telescopic device of the carriage is connected to the front 12 of the carriage at one end and to the rear 11 of the carriage at the other end. It can extend and retract under the action of the drive motor 7. The cloud platform 500 sends instructions to the autonomous vehicle controller 7 through the vehicle communication module 5 to control the drive motor 8 to drive the telescopic device 9 of the carriage to retract, thereby controlling the rear 11 of the carriage to move along the length of the vehicle and adjusting the overall length of the carriage. When the risk of collision is high, the rear 11 of the carriage can be controlled to move towards the front 12 of the carriage along the length of the vehicle, shortening the overall length of the carriage, avoiding vehicles behind, leaving more space, and avoiding collisions.

[0062] In the description of this specification, any process or method described in the flowcharts or otherwise herein may be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0063] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0064] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0065] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0066] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0067] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0068] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0069] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A collision avoidance control method for an autonomous vehicle, characterized in that, A collision avoidance control system for an autonomous vehicle, wherein the collision avoidance control method for the autonomous vehicle includes: Acquire roadside perception information provided by roadside equipment and vehicle condition perception information provided by the vehicle condition perception system; Vehicle collision information is determined based on the roadside sensing information; The cabin state of the autonomous vehicle is controlled based on the vehicle collision information and the operating condition perception information.

2. The obstacle avoidance control method for an autonomous vehicle according to claim 1, characterized in that, The roadside equipment includes roadside cameras and roadside lidar equipment; The roadside perception information is obtained by image fusion based on the 2D perception information collected by the roadside camera and the 3D perception information collected by the roadside lidar device.

3. The obstacle avoidance control method for an autonomous vehicle according to claim 1 or 2, characterized in that, The vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it, and the relative speed difference between the autonomous vehicle and the vehicle behind it. The operational condition perception information includes road gradient information and the vehicle's cargo load status. Controlling the vehicle's cargo load status based on the vehicle collision information and the operational condition perception information includes: The remaining collision time is determined based on the distance between the autonomous vehicle and the front of the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it. The vehicle's cabin status is controlled based on the remaining collision time, road slope information, and cabin load status.

4. The obstacle avoidance control method for an autonomous vehicle according to claim 3, characterized in that, The autonomous vehicle's cabin state is controlled based on the remaining collision time, road gradient information, and cabin load status, including: The passenger compartment of the autonomous vehicle is not controlled when any of the following conditions are met: It is determined that the remaining collision time is greater than the first preset duration; It is determined that the remaining collision time is less than or equal to the first preset duration and the carriage is fully loaded.

5. The obstacle avoidance control method for an autonomous vehicle according to claim 4, characterized in that, The autonomous vehicle's cabin state is controlled based on the remaining collision time, road gradient information, and cabin load status, including: If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than or equal to the first preset slope value and less than or equal to the second preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by the first preset distance along the length of the vehicle. If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is less than the first preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by a second preset distance along the length of the vehicle. If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than the second preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by a third preset distance along the length of the vehicle. Wherein, the second preset distance is greater than the first preset distance, and the first preset distance is greater than the third preset distance.

6. A collision avoidance control system for an autonomous vehicle, characterized in that, include: Roadside equipment is used to collect roadside sensing information; The vehicle operating condition perception system is used to collect operating condition perception information; An edge computing unit, which is communicatively connected to the roadside equipment, is used to determine vehicle collision information based on the roadside sensing information; A cloud platform is communicatively connected to the vehicle condition perception system and the edge computing unit. The cloud platform is used to control the cabin state of the autonomous vehicle based on the vehicle collision information and the condition perception information.

7. The obstacle avoidance control system for an autonomous vehicle according to claim 6, characterized in that, The roadside equipment includes a roadside camera for collecting 2D perception information and a roadside lidar device for collecting 3D perception information; the edge computing unit is also used to perform image fusion on the 2D perception information and the 3D perception information to obtain the roadside perception information.

8. The obstacle avoidance control system for an autonomous vehicle according to claim 6, characterized in that, The vehicle collision information includes the distance between the front of the autonomous vehicle and the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it. The working condition perception information includes road slope information and vehicle load status. The cloud platform is used to determine the remaining collision time based on the distance between the autonomous vehicle and the front of the vehicle behind it and the relative speed difference between the autonomous vehicle and the vehicle behind it; and to control the cabin state of the autonomous vehicle based on the remaining collision time, road slope information and cabin load status.

9. The obstacle avoidance control system for an autonomous vehicle according to claim 8, characterized in that, The cloud platform is specifically used for: The passenger compartment of the autonomous vehicle is not controlled when any of the following conditions are met: It is determined that the remaining collision time is greater than the first preset duration; It is determined that the remaining collision time is less than or equal to the first preset duration and the carriage is fully loaded.

10. The obstacle avoidance control system for an autonomous vehicle according to claim 9, characterized in that, The cloud platform is also specifically used for: If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than or equal to the first preset slope value and less than or equal to the second preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by the first preset distance along the length of the vehicle. If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is less than the first preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by a second preset distance along the length of the vehicle. If the remaining collision time is less than or equal to the first preset duration, the cargo compartment is empty, and the road slope information is greater than the second preset slope value, the cargo compartment of the autonomous driving vehicle is controlled to shorten by a third preset distance along the length of the vehicle. Wherein, the second preset distance is greater than the first preset distance, and the first preset distance is greater than the third preset distance.

Images