Trajectory planning method and device for vehicle, equipment and automatic driving vehicle

Abstract

The present disclosure provides a trajectory planning method and device for a vehicle, electronic equipment, computer readable storage medium, computer program product and an autonomous vehicle, relates to the field of artificial intelligence, and in particular to the field of autonomous driving and intelligent transportation technology. The implementation scheme is: obtaining the speed and position of one or more risk obstacles around the vehicle; selecting, according to the speed and position of the one or more risk obstacles, a side lane with lower risk relative to the one or more risk obstacles from adjacent lanes on both sides of the vehicle as a low-risk lane; generating, for each lane of the current driving lane of the vehicle and the low-risk lane, a travel trajectory of the lane; and selecting, according to the position of the one or more risk obstacles, a travel trajectory of the vehicle from the travel trajectories of the current driving lane of the vehicle and the low-risk lane.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and more particularly to the fields of autonomous driving and intelligent transportation technology, specifically to a trajectory planning method, apparatus, electronic device, computer-readable storage medium, computer program product, and autonomous vehicle for vehicles. Background Technology

[0002] With the rapid development of computer technology and artificial intelligence, autonomous vehicles have shown broad application prospects in various fields such as transportation, military, logistics and warehousing, and daily life. As a core component of autonomous driving technology, trajectory planning requires timely adjustments to the trajectory based on surrounding obstacles to ensure vehicle safety.

[0003] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for trajectory planning of vehicles.

[0005] According to one aspect of this disclosure, a trajectory planning method for a vehicle is provided, comprising: acquiring the speed and position of one or more risky obstacles around the vehicle; selecting, based on the speed and position of the one or more risky obstacles, a lane with a lower risk relative to the one or more risky obstacles from adjacent lanes on both sides of the vehicle as a low-risk lane, wherein the adjacent lanes include a left lane located to the left of the vehicle and a right lane located to the right of the vehicle; generating a travel trajectory for each lane in the vehicle's current driving lane and the low-risk lane, wherein the travel trajectory of the current driving lane corresponds to the path along which the vehicle will travel in the current driving lane, and the travel trajectory of the low-risk lane corresponds to the path along which the vehicle will change lanes from the current driving lane to the low-risk lane and travel in the low-risk lane after completing the lane change; and selecting the vehicle's travel trajectory from the travel trajectories of the vehicle's current driving lane and the low-risk lane based on the position of the one or more risky obstacles. According to another aspect of this disclosure, a trajectory planning apparatus for a vehicle is provided, comprising: an obstacle determination unit configured to: acquire the speed and position of one or more risky obstacles around the vehicle; a lane selection unit configured to: select, based on the speed and position of the one or more risky obstacles, a lane with a lower risk relative to the one or more risky obstacles from adjacent lanes on both sides of the vehicle as a low-risk lane, wherein the adjacent lanes include a left lane located on the left side of the vehicle and a right lane located on the right side of the vehicle; a trajectory generation unit configured to: generate a travel trajectory for each of the vehicle's current driving lane and the low-risk lane, wherein the travel trajectory of the current driving lane corresponds to the path along which the vehicle will travel in the current driving lane, and the travel trajectory of the low-risk lane corresponds to the path along which the vehicle will change lanes from the current driving lane to the low-risk lane and travel in the low-risk lane after completing the lane change; and a trajectory selection unit configured to: select the vehicle's travel trajectory from the travel trajectories of the vehicle's current driving lane and the low-risk lane based on the position of the one or more risky obstacles. According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0006] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods described in this disclosure.

[0007] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in this disclosure.

[0008] According to another aspect of this disclosure, an autonomous vehicle is provided, including the electronic devices described in this disclosure.

[0009] According to another aspect of this disclosure, an edge computing device is provided, including the electronic device described in this disclosure.

[0010] According to one or more embodiments of this disclosure, trajectory planning is performed by screening low-risk lanes, which reduces the complexity of trajectory selection and enables vehicles to perform trajectory planning more quickly and accurately.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram of an exemplary system in which the various methods described herein may be implemented according to embodiments of the present disclosure is shown;

[0014] Figure 2A-2C A schematic diagram illustrating an application scenario of trajectory planning according to embodiments of the present disclosure is shown;

[0015] Figure 3 A flowchart of a trajectory planning method for a vehicle according to an embodiment of the present disclosure is shown;

[0016] Figure 4 A schematic diagram illustrating an application scenario of trajectory planning according to embodiments of the present disclosure is shown;

[0017] Figure 5 A flowchart illustrating the process of selecting a low-risk lane from adjacent lanes on both sides of a vehicle according to an embodiment of the present disclosure is shown.

[0018] Figure 6 A schematic diagram illustrating an application scenario of trajectory planning according to embodiments of the present disclosure is shown;

[0019] Figure 7 A flowchart illustrating the process of selecting a vehicle's trajectory from its current driving lane and a low-risk lane according to an embodiment of the present disclosure is shown.

[0020] Figure 8 A schematic diagram illustrating an application scenario of trajectory planning according to embodiments of the present disclosure is shown;

[0021] Figure 9 A schematic diagram illustrating an application scenario of trajectory planning according to embodiments of the present disclosure is shown;

[0022] Figure 10 A structural block diagram of a trajectory planning device for a vehicle according to an embodiment of the present disclosure is shown; and

[0023] Figure 11 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0026] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0027] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0028] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes a motor vehicle 110, a server 120, and one or more communication networks 130 that couple the motor vehicle 110 to the server 120.

[0029] In embodiments of this disclosure, the motor vehicle 110 may include a computing device according to embodiments of this disclosure and / or be configured to perform a method according to embodiments of this disclosure.

[0030] Server 120 may run one or more services or software applications for trajectory planning methods for vehicles. In some embodiments, server 120 may also provide other services or software applications that may include non-virtual and virtual environments. Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. A user of motor vehicle 110 may sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0031] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0032] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0033] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from vehicle 110. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of vehicle 110.

[0034] Network 130 can be any type of network well known to those skilled in the art, and can support data communication using any of a variety of available protocols (including, but not limited to, TCP / IP, SNA, IPX, etc.). By way of example only, one or more networks 130 can be satellite communication networks, local area networks (LANs), Ethernet-based networks, token ring networks, wide area networks (WANs), the Internet, virtual networks, virtual private networks (VPNs), intranets, extranets, public switched telephone networks (PSTNs), infrared networks, wireless networks (including, for example, Bluetooth, WiFi), and / or any combination of these with other networks.

[0035] System 100 may also include one or more databases 150. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 150 may be used to store information such as audio files and video files. The data repository 150 may reside in various locations. For example, a data repository used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. The data repository 150 may be of different types. In some embodiments, the data repository used by server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data from and from the database in response to commands.

[0036] In some embodiments, one or more of the databases 150 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0037] Motor vehicle 110 may include sensors 111 for sensing the surrounding environment. Sensors 111 may include one or more of the following sensors: a visual camera, an infrared camera, an ultrasonic sensor, a millimeter-wave radar, and a lidar (LiDAR). Different sensors can provide different detection accuracy and range. Cameras may be mounted in front of, behind, or at other locations on the vehicle. Visual cameras can capture the situation inside and outside the vehicle in real time and present it to the driver and / or passengers. In addition, by analyzing the images captured by the visual cameras, information such as traffic light indications, intersection conditions, and the operating status of other vehicles can be obtained. Infrared cameras can capture objects in night vision conditions. Ultrasonic sensors may be mounted around the vehicle to measure the distance of objects outside the vehicle using the strong directionality of ultrasound. Millimeter-wave radar may be mounted in front of, behind, or at other locations on the vehicle to measure the distance of objects outside the vehicle using the characteristics of electromagnetic waves. LiDAR may be mounted in front of, behind, or at other locations on the vehicle to detect the edges and shape information of objects, thereby performing object recognition and tracking. Due to the Doppler effect, the radar device can also measure the speed changes of the vehicle and moving objects.

[0038] The motor vehicle 110 may also include a communication device 112. The communication device 112 may include a satellite positioning module capable of receiving satellite positioning signals (e.g., BeiDou, GPS, GLONASS, and GALILEO) from satellite 141 and generating coordinates based on these signals. The communication device 112 may also include a module for communicating with a mobile communication base station 142. The mobile communication network can implement any suitable communication technology, such as current or emerging wireless communication technologies (e.g., 5G technology) like GSM / GPRS, CDMA, and LTE. The communication device 112 may also have a vehicle-to-everything (V2X) module, configured to enable vehicle-to-the-world communication, for example, vehicle-to-vehicle (V2V) communication with other vehicles 143 and vehicle-to-infrastructure (V2I) communication with infrastructure 144. Furthermore, the communication device 112 may also have a module configured to communicate with a user terminal 145 (including but not limited to smartphones, tablets, or wearable devices such as watches) via, for example, a wireless local area network conforming to the IEEE 802.11 standard or Bluetooth. Using the communication device 112, the motor vehicle 110 can also access the server 120 via the network 130.

[0039] The motor vehicle 110 may also include a control unit 113. The control unit 113 may include a processor, such as a central processing unit (CPU) or a graphics processing unit (GPU), or other dedicated processors, that communicates with various types of computer-readable storage devices or media. The control unit 113 may include an autonomous driving system for automatically controlling various actuators in the vehicle. The autonomous driving system is configured to control the powertrain, steering system, and braking system of the motor vehicle 110 (not shown) via multiple actuators in response to inputs from multiple sensors 111 or other input devices to control acceleration, steering, and braking respectively, without human intervention or with limited human intervention. Some processing functions of the control unit 113 can be implemented via cloud computing. For example, some processing can be performed using an onboard processor while other processing can be performed using cloud computing resources. The control unit 113 may be configured to perform methods according to this disclosure. Furthermore, the control unit 113 may be implemented as an example of a computing device on the motor vehicle side (client) according to this disclosure.

[0040] It is understood that motor vehicles are not necessarily required to include all of the aforementioned vehicle-mounted sensing devices. According to some embodiments of the present invention, safe and reliable autonomous driving can still be achieved even when the motor vehicle does not have or does not activate these vehicle-mounted sensing devices.

[0041] Autonomous vehicles are extremely complex systems, operating in diverse and ever-changing real-world driving environments, which introduces numerous uncertainties regarding their safety. Safety of the Intended Functionality (SOTIF) is a crucial component of the autonomous driving safety system, primarily addressing hazards caused by deficiencies in autonomous driving functions and foreseeable human misuse. Anticipated functional safety (AD SOTIF) for single-vehicle autonomous driving mainly involves five aspects: perception, prediction, decision-making, control, and human-machine interaction, with perception and prediction being the most prominent challenges currently faced.

[0042] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0043] In the embodiments described in this disclosure, "obstacle" refers to any object present in autonomous driving that may interact with the vehicle performing autonomous driving or potentially affect its trajectory.

[0044] In the embodiments described in this disclosure, a "lane" can be a physically existing real lane, defined by physical facilities such as road markings, curbs, and guardrails. According to other embodiments, a lane in this disclosure can be a virtual lane marked in the absence of a real lane (e.g., at an intersection), for example, a virtual lane generated based on road geometry, vehicle trajectory, and road usage habits. In the embodiments described in this disclosure, a "vehicle" refers to a vehicle currently performing or preparing to perform an autonomous driving task (e.g., as referenced). Figure 3 The described trajectory planning method for vehicles (300) can also be referred to as the "main vehicle".

[0045] Figure 2A-2C A schematic diagram of an application scenario 200 for trajectory planning according to an embodiment of the present disclosure is shown.

[0046] According to some embodiments, the current trajectory of the obstacle crosses the current trajectory of the vehicle (e.g., the master vehicle in an autonomous driving scenario), for example, as Figure 2A As shown, vehicle 210 travels at a speed v adc Traveling in the current lane 242, while obstacle 220 travels at a speed v obs As the vehicle moves forward, obstacle 220 may interact with vehicle 210 in the interaction area 230 at a future time. For example, obstacle 220 may be a pedestrian crossing the road, and interaction area 230 may be the area at an intersection corresponding to a zebra crossing. According to some embodiments, vehicle 210 may choose to continue traveling in the current lane 242, or it may choose to change lanes to the left lane 241 or the right lane 243 of the current lane 242.

[0047] According to some embodiments, the obstacle's direction of travel is opposite to the direction of travel of the vehicle (e.g., the main vehicle in an autonomous driving scenario), for example, as Figure 2B As shown, vehicle 210 travels at a speed v adc Proceeding, while obstacle 220 travels at a speed of v obs As the vehicle moves forward, obstacle 220 may interact with vehicle 210 in the interaction area 230 at a future time. For example, obstacle 220 may be another vehicle traveling in the opposite direction, and interaction area 230 is the area where the other vehicle and vehicle 210 will meet. According to some embodiments, vehicle 210 may choose to continue traveling in the current lane 242, or it may choose to change lanes to the left lane 241 or the right lane 243 of the current lane 242.

[0048] According to some embodiments, a portion of the obstacle's trajectory overlaps with a portion of the vehicle's trajectory (e.g., the host vehicle in an autonomous driving scenario), for example, such as... Figure 2C As shown, vehicle 210 travels at a speed vadc Traveling in the current lane 242, while obstacle 220 travels at a speed v obs As the vehicle moves forward, obstacle 220 may interact with vehicle 210 in the interaction area 230 at a future time. For example, obstacle 220 may be other vehicles merging onto the main road from a different lane than vehicle 210, and the interaction area is the intersection of the lane and the main road. According to some embodiments, vehicle 210 may choose to continue traveling in the current lane 242, or it may choose to change lanes to the left lane 241 or the right lane 243 of the current lane 242.

[0049] As can be seen from the above analysis, there are various scenarios in autonomous driving where obstacles may interact with the vehicle. Therefore, it is necessary to identify risk scenarios in autonomous driving in a timely manner and take corresponding actions, such as adjusting the vehicle's trajectory in the current driving lane or changing lanes to avoid collisions with obstacles.

[0050] In one existing technical solution, trajectory planning can be performed simultaneously for the vehicle's current lane and the lanes on both sides. However, this can consume significant computational resources and result in low trajectory planning efficiency, failing to take timely actions to avoid obstacles. In another existing technical solution, trajectory planning can be performed only for the vehicle's current lane by default, with other lanes only planned when a risk is identified, thus conserving computational resources. However, this may lead to missed lane-changing opportunities due to overlooked risk identification.

[0051] Therefore, an embodiment of the present disclosure provides a trajectory planning method for vehicles. Figure 3 A flowchart of a trajectory planning method 300 for a vehicle according to an embodiment of the present disclosure is shown.

[0052] like Figure 3 As shown, method 300 includes:

[0053] Step S310: Obtain the speed and position of one or more risk obstacles around the vehicle;

[0054] Step S320: Based on the speed and position of one or more risk obstacles, select the lane with a lower risk relative to one or more risk obstacles from the adjacent lanes on both sides of the vehicle as the low-risk lane, wherein the adjacent lanes include the left lane located to the left of the vehicle and the right lane located to the right of the vehicle.

[0055] Step S330: For each lane in the vehicle's current driving lane and the low-risk lane, generate the travel trajectory for that lane, where the travel trajectory for the current driving lane corresponds to the path the vehicle will take along the current driving lane, and the travel trajectory for the low-risk lane corresponds to the path the vehicle takes from the current driving lane to the low-risk lane and then travels along the low-risk lane after completing the lane change; and

[0056] Step S340: Select the vehicle's trajectory from the vehicle's current driving lane and the low-risk lane based on the location of one or more risk obstacles.

[0057] According to embodiments of this disclosure, optimizing the trajectory planning process by comprehensively considering the risks of obstacles around the vehicle not only improves planning efficiency and accuracy but also effectively enhances vehicle driving safety. Specifically, by performing risk assessment and pruning on adjacent lanes, the number of lanes requiring trajectory planning is reduced, thereby effectively reducing the computational complexity of the trajectory planning process and making it more efficient; by excluding adjacent lanes with higher risks, the final selected travel trajectory is ensured to be safer, reducing the possibility of conflicts with risky obstacles; and by explicitly assessing obstacle risks, the possibility of overlooking important risk scenarios is reduced, making the planning results more comprehensive and reliable.

[0058] According to some embodiments, the risk obstacle may include pedestrians, other vehicles or other obstacles, etc., without limitation.

[0059] According to some embodiments, in an autonomous driving system, a vehicle can detect all obstacles around it using various sensors such as LiDAR, radar, and cameras. However, to improve the system's decision-making efficiency and accuracy, the system can further filter and analyze the detected obstacles to identify those that truly pose a risk to the vehicle.

[0060] According to some embodiments, in an autonomous driving system, a vehicle can obtain the position and speed of surrounding obstacles in real time while detecting them using sensors. For example, lidar can use laser ranging to provide the distance of the obstacle from the vehicle and the position of the obstacle, radar uses the Doppler effect to measure the speed of the obstacle, and cameras can help identify the position and direction of travel of the obstacle.

[0061] According to some embodiments, based on the current position and speed of the obstacle, subsequent low-risk lane selection and travel trajectory selection are performed.

[0062] According to some embodiments, based on the vehicle's current driving lane, obstacles that are relatively close to the vehicle's current driving lane among the detected obstacles are identified as risk obstacles.

[0063] According to some embodiments, obtaining obstacle information of one or more risky obstacles around a vehicle includes: for each obstacle around the vehicle, determining the obstacle as a risky obstacle in response to the distance between the location of the obstacle and the entry point of the obstacle into the current driving lane of the vehicle being less than or equal to an interaction threshold.

[0064] According to some embodiments, the entry point of the obstacle into the vehicle's current driving lane is the point where the obstacle enters the vehicle's current driving lane along the direction of the obstacle's velocity. According to some embodiments, the entry point of the obstacle into the vehicle's current driving lane refers to the position where the obstacle enters the vehicle's current driving lane while continuing to travel at the obstacle's current speed.

[0065] The following is Figure 4 For example, Figure 4 As shown, the entry point 401 of obstacle 220 entering the current driving lane 242 of vehicle 210 can be based on the detected speed v of obstacle 220. obs The predicted value is that the speed v along the obstacle 220 from its position will be... obs The intersection of the straight line extending in the direction of the obstacle 220 with the boundary line of the current driving lane 242 of the vehicle 210 near the obstacle 220 is determined as the entry point 401 of the obstacle 220 entering the current driving lane 242 of the vehicle 210. The distance d1 between the obstacle 220 and the entry point 401 is the distance between the position of the obstacle and the entry point of the obstacle entering the current driving lane of the vehicle.

[0066] According to some embodiments, the interaction threshold can be a predetermined distance threshold, for example, 5m.

[0067] According to other embodiments, all detected obstacles may be considered as risk obstacles, for example, when the number of detected obstacles is small.

[0068] According to some embodiments, in addition to the speed and position of the obstacle, other information about the obstacle, such as its acceleration and attitude, can also be obtained.

[0069] According to some embodiments, the lane information can be provided by a professional map provider that provides high-precision maps, or by sensor acquisition and / or a positioning system.

[0070] According to some embodiments, the adjacent lanes on both sides of the vehicle are the left and right lanes of the lane in which the vehicle is currently located.

[0071] Figure 5The process of selecting a low-risk lane from adjacent lanes on both sides of a vehicle, according to embodiments of the present disclosure, is illustrated (e.g., Figure 3 The flowchart of step S320 in the process. According to some embodiments, such as Figure 5 As shown, step S320 includes:

[0072] Step S501: For each adjacent lane of the vehicle, determine the risk value of each obstacle among the obstacles on the side where the adjacent lane is located from one or more risk obstacles;

[0073] Step S502: For each adjacent lane, determine the risk value of that adjacent lane based on the risk value of one or more obstacles on the side where the adjacent lane is located; and

[0074] Step S503: Determine low-risk lanes based on the risk value of each adjacent lane of the vehicle.

[0075] According to the embodiments described in this disclosure, low-risk lanes required for subsequent trajectory selection can be selected, and high-risk lanes can be discarded. This saves computational resources compared to the prior art solution that retains lanes with high risk and low probability of being selected.

[0076] According to some embodiments, in step S501, determining the risk value of each obstacle among the obstacles on the side of the adjacent lane for each of the one or more adjacent lanes of the vehicle includes: determining the time when the obstacle enters the vehicle's current driving lane based on the speed and position of the obstacle; and determining the risk value of the obstacle based on the time when the obstacle enters the vehicle's current driving lane for each of the one or more adjacent lanes of the vehicle.

[0077] According to some embodiments, one or more risk obstacles are divided into obstacles on one side of each adjacent lane. For example, the side of the risk obstacle can be determined based on the direction of the risk obstacle relative to the vehicle, and / or the side of the risk obstacle can be determined based on the distance between the risk obstacle and each adjacent lane.

[0078] According to some embodiments, the time it takes for an obstacle to enter the vehicle's current driving lane refers to the time required for the obstacle to enter the vehicle's current driving lane while continuing to travel at its current speed; that is, in Figure 4 The time taken to travel from the current position of obstacle 220 to entry point 401 in the scenario shown.

[0079] According to some embodiments, determining the time when the obstacle enters the vehicle's current driving lane may include: determining the entry point of the obstacle into the vehicle's current driving lane based on the obstacle's position and velocity direction (e.g., as referenced). Figure 4 (as described); the time when the obstacle enters the vehicle's current driving lane is determined based on the distance between the obstacle's position and the point of entry of the obstacle into the vehicle's current driving lane, and the speed of the obstacle.

[0080] According to some embodiments, the risk value of an obstacle is determined based on the time it takes for the obstacle to enter the vehicle's current driving lane. For example, when the time it takes for the obstacle to enter the vehicle's current driving lane is less than a first time threshold, the risk value of the obstacle is set to a first preset value; when the time it takes for the obstacle to enter the vehicle's current driving lane is greater than or equal to the first time threshold and less than a second time threshold, the risk value of the obstacle is set to a second preset value; when the time it takes for the obstacle to enter the vehicle's current driving lane is greater than or equal to the second time threshold and less than a third time threshold, the risk value of the obstacle is set to a third preset value.

[0081] According to some embodiments, in addition to the time when the obstacle enters the vehicle's current driving lane, the risk value of the obstacle is also determined based on the distance between the location of the obstacle and the entry point of the obstacle into the vehicle's current driving lane.

[0082] According to some embodiments, for each of one or more risky obstacles on the side of the adjacent lane, determining the risk value of the obstacle based on the time the obstacle enters the vehicle's current driving lane includes: for each of one or more risky obstacles on the side of the adjacent lane, determining a first sub-risk value of the obstacle based on the time the obstacle enters the vehicle's current driving lane; determining a second sub-risk value of the obstacle based on the distance between the obstacle's position and the entry point of the obstacle into the vehicle's current driving lane, wherein the entry point of the obstacle into the vehicle's current driving lane is the entry point where the obstacle enters the vehicle's current driving lane along the direction of the obstacle's velocity; and determining the risk value of the obstacle based on the first and second sub-risk values.

[0083] According to some embodiments, the Frenet coordinate system is defined based on the centerline of the vehicle's current driving lane or other lanes (e.g., any adjacent lanes) to describe position, distance, or length in an autonomous driving scenario.

[0084] According to some embodiments, for each lane in the vehicle's current driving lane or other lanes, for the Frenet coordinate system corresponding to that lane, the centerline of that lane is used as a reference curve, the direction along the centerline of that lane is used as the longitudinal direction, and the direction perpendicular to the centerline of that lane is used as the lateral direction.

[0085] According to some embodiments, for each lane in the vehicle's current driving lane or other lanes, for the Frenet coordinate system corresponding to that lane, the s value represents the distance along the centerline of that lane, and the d value represents the lateral offset relative to the centerline of that lane.

[0086] According to some embodiments, for each lane in which the vehicle is currently traveling or in other lanes, the origin of the coordinate system is the point on the center line of the lane where the vehicle's position is projected.

[0087] According to some embodiments, the centerline of a lane is a line located in the center of the lane and extending along the geometric axis of the road. According to some embodiments, the centerline of a lane can be a physically existing marked line, such as a line clearly defined by road markings like solid or dashed lines, or it can be a virtual reference line, such as a reference line calculated from road geometry, map data, or sensor information. According to some embodiments, the process of determining a first sub-risk value of an obstacle based on the time the obstacle enters the vehicle's current lane can be the same as or similar to the process described above for determining the risk value of an obstacle based on the time the obstacle enters the vehicle's current lane. According to some embodiments, determining a second sub-risk value of an obstacle based on the distance between the location of the obstacle and the entry point of the obstacle into the vehicle's current lane includes:

[0088] Based on the position and speed of the obstacle, determine the area where the vehicle enters the interaction zone between the vehicle and the obstacle (e.g., Figure 2A-2C The estimated obstacle position of the obstacle is shown in the interactive area 230.

[0089] Based on the distance between the estimated location of the obstacle and the entry point of the obstacle into the vehicle's current lane, the lateral distance of the vehicle is determined; and

[0090] A second sub-risk value for the obstacle is determined based on the difference between the distance between the obstacle's location and the entry point of the obstacle into the vehicle's current driving lane, and the vehicle's lateral distance.

[0091] According to some embodiments, the interaction area between the vehicle and the obstacle is the spatial range in which interaction, collision, or interference may occur between the vehicle and the surrounding obstacle. For example, the interaction area is as follows: Figure 2A The intersection shown corresponds to the zebra crossing area, such as... Figure 2BThe intersections where the two vehicles may meet, and as shown, Figure 2C The diagram shows the intersection area of ​​the branch roads. According to some embodiments, the interaction area between the vehicle and the obstacle is determined based on environmental information (e.g., road planning information) in autonomous driving, the vehicle's current trajectory, and / or the obstacle's current trajectory.

[0092] According to some embodiments, as described above, the entry point of the obstacle into the vehicle's current driving lane is the point where the obstacle enters the vehicle's current driving lane along the direction of the obstacle's velocity.

[0093] It should be understood that the lateral distance of the vehicle is calculated based on the assumption that the obstacle and the vehicle continue to move in their current states of motion (i.e., maintaining constant speed and acceleration).

[0094] The following is Figure 6 For example, Figure 6 As shown, assuming vehicle 210 continues to move in its current state of motion, it will enter the interaction zone 230 with obstacle 220 at the vehicle's estimated position 610, while assuming obstacle 220 maintains a speed v obs The obstacle 220 will move to its estimated position 620 at this time, where the lateral distance d2 of the vehicle is the distance between the estimated position 620 of the obstacle and the entry point 401 of the obstacle 220, and the entry point 401 can be compared with a reference point. Figure 4 The described entry point 401 is the same as or similar to that described above, i.e., it is the point along the obstacle 220 from its position with a velocity v. obs The intersection of the straight line extending in the direction of the vehicle 210 and the boundary line of the current driving lane 242 of the vehicle 210 on the side closer to the obstacle 220.

[0095] It should be understood that, in order to clearly show the lateral distance of vehicles, Figure 6 The image only shows the vehicle's current lane, omitting the adjacent lanes.

[0096] For example, the second risk value can be determined according to the following formula (1):

[0097] second_cost=original_obs_cutin_s-obs_dist_when_adc_cutin (1)

[0098] Wherein, second_cost is the second risk value, original_obs_cutin_s is the distance between the position of the obstacle and the entry point of the obstacle into the current driving lane of the vehicle, and obs_dist_when_adc_cutin is the lateral distance of the vehicle, that is, as mentioned above, the distance between the estimated position of the obstacle when the vehicle enters the interaction area between the vehicle and the obstacle and the entry point of the obstacle into the current driving lane of the vehicle.

[0099] According to some embodiments, the first risk value and the second risk value can be weighted and summed to obtain the risk value of the obstacle.

[0100] For example, the risk value of the obstacle can be determined according to the following formula (2):

[0101] risk_cost=w1*first_cost+w2*second_cost (2)

[0102] Where risk_cost is the risk value of the obstacle, first_cost is the first risk value, second_cost is the second risk value, w1 is the first weight corresponding to the first risk value, and w2 is the second weight corresponding to the second risk value.

[0103] According to some embodiments, in step S502, for each adjacent lane, the risk values ​​of obstacles on the side of the adjacent lane among one or more risky obstacles are summed to determine the risk value of the adjacent lane. According to some embodiments, in step S503, the adjacent lane with the lower risk value is selected as the low-risk lane.

[0104] According to some embodiments, in step S330, for each lane in the vehicle's current driving lane and the low-risk lane, a travel trajectory for that lane is generated. The travel trajectory of the current driving lane corresponds to the path the vehicle will travel along the current driving lane, and the travel trajectory of the low-risk lane corresponds to the path the vehicle will take from the current driving lane to the low-risk lane and then travel along the low-risk lane after completing the lane change. According to some embodiments, a path refers to a set of spatial points traversed by the vehicle from its current location. According to some embodiments, a trajectory is a travel plan for the vehicle from its current location, where the trajectory includes not only the set of spatial points traversed by the vehicle from its current location but also dynamic information such as time, speed, and acceleration of the vehicle at these points to indicate the vehicle's specific driving behavior.

[0105] In some embodiments, in autonomous driving, the generated travel trajectory is not infinitely extended, but has a finite length. For example, the travel trajectory generated by the autonomous driving algorithm each time corresponds to a path with a preset length (e.g., 80 meters).

[0106] Figure 7 The process of selecting a vehicle's trajectory from its current driving lane and a low-risk lane, according to embodiments of the present disclosure, is illustrated (e.g., Figure 7 The flowchart of step S340 in the process is shown. According to some embodiments, step S340 includes:

[0107] Step S701: For each of the one or more risk obstacles, determine the longitudinal distance of the risk obstacle based on the difference between the s-value of the entry point of the risk obstacle into the current driving lane of the vehicle in the first Frenet coordinate system and the s-value of the vehicle's position in the first Frenet coordinate system, wherein the entry point of the risk obstacle into the current driving lane of the vehicle is the entry point of the risk obstacle into the current driving lane of the vehicle along the direction of the speed of the risk obstacle, and the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the current driving lane of the vehicle;

[0108] Step S702: Designate the risk obstacle with the smallest longitudinal distance among one or more risk obstacles as the critical obstacle;

[0109] Step S703: For each lane in the vehicle's current driving lane and the low-risk lanes, determine the longitudinal risk value of that lane; and

[0110] Step S704: Select a vehicle's travel trajectory from the vehicle's current travel lane and the low-risk lane, based at least in part on the longitudinal risk values ​​of the vehicle's current travel lane and the low-risk lane. For example, when it is determined that the vehicle will continue to travel along the current travel lane, select the travel trajectory of the current travel lane (i.e., the trajectory corresponding to the path the vehicle will travel along the current travel lane, for example, ...). Figure 8 The shown travel trajectory 852) is used as the vehicle's travel trajectory. For example, when determining whether a vehicle is changing lanes to an adjacent lane, the travel trajectory of the adjacent lane is selected (i.e., the trajectory corresponding to the vehicle's path from its current lane to a low-risk lane, and its subsequent travel along the low-risk lane after the lane change, for example, ...). Figure 8 The trajectory shown is 853, which serves as the vehicle's trajectory.

[0111] According to some embodiments, for each of one or more risk obstacles, the longitudinal distance of the risk obstacle is determined based on the difference between the s-value of the entry point of the risk obstacle into the vehicle's current driving lane in the first Frenet coordinate system and the s-value of the vehicle's position in the first Frenet coordinate system, wherein the entry point of the risk obstacle into the vehicle's current driving lane is the entry point of the risk obstacle into the vehicle's current driving lane along the direction of the risk obstacle's velocity (e.g., Figure 8 The entry point is 401), and the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the vehicle's current driving lane.

[0112] According to some embodiments, since the key obstacles closest to the vehicle in the longitudinal direction are selected by minimizing the longitudinal distance in steps S701 and S702, and used to evaluate the vehicle's current driving lane and low-risk lane trajectory, the trajectory evaluation is performed efficiently, further reducing the amount of computation.

[0113] In practical applications, it is desirable for vehicles to travel as far as possible while avoiding obstacles to avoid sudden braking or premature stopping at a distance from the interaction zone. According to some embodiments, the length of the travel trajectory in each lane can be compared with the distance from the vehicle's position to the potential interaction zone between the vehicle and the obstacle.

[0114] According to some embodiments, for each lane in the vehicle's current driving lane and the low-risk lanes, a longitudinal risk value for that lane is determined (e.g., Figure 7 Step S703 includes:

[0115] Based on the difference between the s-value of the obstacle intersection point in the Frenet coordinate system corresponding to the lane and the s-value of the vehicle's position in the Frenet coordinate system corresponding to the lane, the target distance of the critical obstacle corresponding to the lane is determined. Here, the obstacle intersection point is the point where the critical obstacle travels along the direction of its velocity and intersects the centerline of the lane. Furthermore, the Frenet coordinate system corresponding to the lane is a Frenet coordinate system defined based on the centerline of the lane.

[0116] Based on the target distance of the critical obstacle corresponding to the lane and the planned length of the lane's trajectory, the longitudinal risk value of the lane is determined. The planned length of the lane's trajectory is the distance from the vehicle's position to the end point of the lane's trajectory. When there is a braking point in the lane's trajectory, the end point of the lane's trajectory is the braking point in the lane's trajectory. When there is no braking point in the lane's trajectory, the end point of the lane's trajectory is the end point of the lane's trajectory.

[0117] According to some embodiments, for each of the vehicle's current driving lane and low-risk lanes, the obstacle intersection point of that lane is the intersection point from the location of the critical obstacle along the direction of the critical obstacle's speed to the centerline of the corresponding lane.

[0118] For example, in Figure 9 In the scenario shown, for the current driving lane 242 of vehicle 210, the obstacle intersection 965 of that lane can be determined based on the speed v of the detected obstacle 220. obs The predicted velocity v along obstacle 220 from its position is... obs The intersection of the straight line extending in the direction of the vehicle 210 with the centerline 252 of the vehicle 210's current driving lane 242; and, for the low-risk lane 243 of the vehicle 210, the obstacle intersection 967 of that lane can be determined based on the speed v of the detected obstacle 220. obs The predicted velocity v along obstacle 220 from its position is... obs The intersection of the straight line extending in the direction of vehicle 210 with the center line 253 of the low-risk lane 243.

[0119] According to some embodiments, the target distance of a critical obstacle to the lane is the difference between the s-value of the obstacle intersection point in the Frenet coordinate system corresponding to the lane and the s-value of the vehicle position in the Frenet coordinate system corresponding to the lane, wherein the Frenet coordinate system corresponding to the lane is a Frenet coordinate system defined based on the centerline of the lane.

[0120] For example, in Figure 9 In the scenario shown, for the current driving lane 242, the target distance of vehicle 210 corresponding to the lane is the distance on the centerline 252 of the lane at the intersection point 965 of the vehicle 210's position and the obstacle of the lane. That is, the distance between the centerline 252 of the lane at the centerline projection point 968 of vehicle 210 and the intersection point 965 of the obstacle of the lane. Here, the centerline projection point 968 of vehicle 210 is the point on the centerline 252 of the lane at which the position of vehicle 210 is projected.

[0121] For example, in Figure 9 In the scenario shown, for low-risk lane 243, the target distance of vehicle 210 corresponding to that lane is the distance on the centerline 253 of the lane at the intersection point 967 of the vehicle 210's position and the obstacle of that lane. That is, the distance between the centerline 253 of the lane and the centerline projection point 961 of vehicle 210 and the intersection point 967 of the obstacle of that lane. Here, the centerline projection point 961 of vehicle 210 is the point on the centerline 253 of the lane where the position of vehicle 210 is projected.

[0122] According to some embodiments, for each of the vehicle's current driving lane and low-risk lanes, the planned length of the lane's travel trajectory is the distance from the vehicle's position to the end point of the lane's travel trajectory, wherein when there is a braking point in the lane's travel trajectory, the end point of the lane's travel trajectory is the braking point in the lane's travel trajectory, and when there is no braking point in the lane's travel trajectory, the end point of the lane's travel trajectory is the end point of the lane's travel trajectory.

[0123] For example, in Figure 9 In the scenario shown, there is a braking point 962 on the travel trajectory 952 of the current driving lane 242. The planned length of the travel trajectory 952 of the current driving lane 242 is the distance from the position of vehicle 210 to the braking point 962 on the travel trajectory 952. Furthermore, there is no braking point on the travel trajectory 953 of the low-risk lane 243. The planned length of the travel trajectory 953 of the low-risk lane 243 is the distance from the position of vehicle 210 to the end point 963 of the travel trajectory 953.

[0124] According to some embodiments, for each of the vehicle's current driving lane and low-risk lanes, a longitudinal risk value for that lane is determined based on the target distance of the critical obstacle corresponding to that lane and the planned length of the lane's travel trajectory.

[0125] For example, for each lane, the longitudinal risk value of the lane can be determined according to the following formula (3):

[0126] longitudinal_cost=max(0.0,min(end_s-adc_s,30.0)-plan_end_s) (3)

[0127] Where, longitudinal_cost is the longitudinal risk value, end_s is the s value of the obstacle intersection point of the lane in the Frenet coordinate system corresponding to the lane, adc_s is the s value of the vehicle position in the Frenet coordinate system corresponding to the lane, and plan_end_s is the planned length of the lane's travel trajectory.

[0128] According to some embodiments, step S704 includes: determining the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane; and in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being less than or equal to a longitudinal threshold, selecting the vehicle's current driving lane trajectory as the vehicle's driving trajectory, that is, not changing lanes.

[0129] According to some embodiments, in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being greater than a longitudinal threshold, the travel trajectory of the lane to be selected is determined based on other parameters (e.g., the lateral risk value, which will be described in detail below) to ensure safety, or the travel trajectory corresponding to the low-risk lane can be directly selected for lane changing.

[0130] According to some embodiments, selecting a vehicle's trajectory from the trajectories of the vehicle's current driving lane and low-risk lanes based on the location information of one or more risky obstacles further includes: determining a lateral distance between the location of a critical obstacle and the trajectories of the lane based on the distance between the location of the critical obstacle and the entry point of the obstacle into the trajectories of the lane, wherein the entry point of the obstacle into the trajectories of the lane is the entry point of the obstacle into the trajectories of the lane along the direction of the obstacle's velocity; and for each of the vehicle's current driving lanes and low-risk lanes, determining a lateral risk value for that lane includes: determining a lateral risk value for that lane based on the lateral distance between the location of the critical obstacle and the trajectories of the lane, wherein selecting a vehicle's trajectory from the trajectories of the vehicle's current driving lane and low-risk lanes, at least partially based on the longitudinal risk values ​​of the vehicle's current driving lane and low-risk lanes, includes: selecting a vehicle's trajectory from the trajectories of the vehicle's current driving lane and low-risk lanes based on both the longitudinal and lateral risk values ​​of the vehicle's current driving lane and low-risk lanes.

[0131] For example, in Figure 9 In the scenario shown, for the current driving lane 242 of vehicle 210, the entry point 964 of the trajectory of that lane can be determined based on the speed v of the detected obstacle 220. obs The predicted velocity v along obstacle 220 from its position is... obsThe intersection of the straight line extending in the direction of the current driving lane 242 with the boundary of the side of the current driving lane 242 closest to the obstacle 220, and the lateral distance between the position of the obstacle 220 and the driving track of the lane is the distance between the position of the obstacle 220 and the entry point 964 of the driving track of the lane.

[0132] For example, for the low-risk lane 243 of vehicle 210, the obstacle intersection 966 of that lane can be based on the speed v of the detected obstacle 220. obs The predicted velocity v along obstacle 220 from its position is... obs The intersection of the straight line extending in the direction of the vehicle 210 and the boundary of the low-risk lane 243's travel trajectory 953 on the side closest to the obstacle 220, and the lateral distance between the position of the obstacle 220 and the travel trajectory of the lane is the distance between the position of the obstacle 220 and the entry point 966 of the travel trajectory of the lane.

[0133] According to some embodiments, selecting a vehicle's travel trajectory from the current driving lane and the low-risk lane's travel trajectory based on the longitudinal and lateral risk values ​​of the vehicle's current driving lane and the low-risk lane includes: selecting the low-risk lane's travel trajectory as the vehicle's travel trajectory in response to the difference between the lateral risk value of the current driving lane and the lateral risk value of the low-risk lane being greater than a lateral threshold, and in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being greater than a longitudinal threshold; and selecting the current driving lane's travel trajectory as the vehicle's travel trajectory in response to the difference between the lateral risk value of the current driving lane and the lateral risk value of the low-risk lane being less than or equal to a lateral threshold, or in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being less than or equal to a longitudinal threshold.

[0134] In the embodiments described herein, the safety of possible lane-changing operations (i.e., switching to a low-risk lane) is ensured by evaluating the travel trajectory of the lane to be selected from both lateral and longitudinal risk dimensions.

[0135] According to some embodiments, the lateral threshold is determined based on the difference between the s-value of the position of the critical obstacle in the first Frenet coordinate system and the s-value of the position of the vehicle in the first Frenet coordinate system, wherein the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the vehicle's current driving lane. For example, the greater the distance between the position of the critical obstacle and the position of the vehicle in the direction of the centerline of the current driving lane, the larger the lateral threshold is set.

[0136] According to some embodiments, the method described in this disclosure further includes: in response to determining that the selected vehicle's travel trajectory is a travel trajectory of a low-risk lane, and in response to determining that the vehicle has not entered a low-risk lane, determining a longitudinal risk value and a lateral risk value for each of the vehicle's current travel lane and the low-risk lane; and determining, based on the longitudinal risk value and the lateral risk value of the vehicle's current travel lane and the low-risk lane, whether to change the vehicle's travel trajectory to the travel trajectory of the current travel lane.

[0137] According to the embodiments described in this disclosure, the safety and reliability of lane change operations are improved by continuing to evaluate the lane trajectory when a lane change operation is selected (i.e., the trajectory of the selected vehicle is determined to be the trajectory of a low-risk lane) but the lane change has not yet occurred (i.e., the vehicle has not entered the low-risk lane).

[0138] According to embodiments of this disclosure, such as Figure 10 The diagram also discloses a trajectory planning device 1000 for a vehicle, comprising: an obstacle determination unit 1010 configured to: acquire the speed and position of one or more risky obstacles around the vehicle; a lane selection unit 1020 configured to: select a lane with a lower risk relative to the one or more risky obstacles from adjacent lanes on both sides of the vehicle as a low-risk lane based on the speed and position of the one or more risky obstacles, wherein the adjacent lanes include a left lane located on the left side of the vehicle and a right lane located on the right side of the vehicle; a trajectory generation unit 1030 configured to: generate a travel trajectory for each lane in the vehicle's current driving lane and the low-risk lane, wherein the travel trajectory of the current driving lane corresponds to the path along which the vehicle will travel in the current driving lane, and the travel trajectory of the low-risk lane corresponds to the path along which the vehicle will change lanes from the current driving lane to the low-risk lane and travel in the low-risk lane after completing the lane change; and a trajectory selection unit 1040 configured to: select the vehicle's travel trajectory from the travel trajectories of the vehicle's current driving lane and the low-risk lane based on the position of one or more risky obstacles.

[0139] According to some embodiments, the lane selection unit 1020 includes: an obstacle risk determination subunit configured to: for each adjacent lane of the vehicle, determine the risk value of each obstacle among one or more risky obstacles on the side of the adjacent lane, including: for each obstacle among one or more risky obstacles on the side of the adjacent lane, determining the time when the obstacle enters the vehicle's current driving lane based on the obstacle's speed and position; and for each obstacle among one or more risky obstacles on the side of the adjacent lane, determining the risk value of the obstacle based on the time when the obstacle enters the vehicle's current driving lane; a lane risk determination subunit configured to: for each adjacent lane, determine the risk value of the adjacent lane based on the risk value of one or more risky obstacles on the side of the adjacent lane; and a lane selection subunit configured to: determine low-risk lanes based on the risk values ​​of each adjacent lane of the vehicle.

[0140] Here, the operation of each of the above units 1010 to 1040 of the device 1000 is similar to the operation of steps S310 to S340 described above, and will not be repeated here.

[0141] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0142] According to embodiments of this disclosure, an electronic device, a readable storage medium, and a computer program product are also provided.

[0143] According to another aspect of this disclosure, an edge computing device is also provided. Optionally, in addition to electronic devices, the edge computing device may also include communication components, etc. The electronic devices and communication components can be integrated or separately configured. The electronic devices can acquire data from roadside sensing devices (such as roadside cameras), such as images and videos, thereby performing image and video processing and data calculations, and then transmitting the processing and calculation results to the cloud control platform via the communication components.

[0144] Optionally, the edge computing device can also be a Road Side Computing Unit (RSCU). Alternatively, the electronic device itself can also have the functions of acquiring and communicating sensing data, such as an AI camera. The electronic device can directly perform image and video processing and data calculation based on the acquired sensing data, and then transmit the processing and calculation results to the cloud control platform.

[0145] Optionally, the cloud control platform performs processing in the cloud, including image and video processing and data calculation. The cloud control platform can also be called a vehicle-road cooperative management platform, V2X platform, cloud computing platform, central system, cloud server, etc.

[0146] refer to Figure 11 The present invention describes a structural block diagram of an electronic device 1100 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0147] like Figure 11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of the electronic device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0148] Multiple components in electronic device 1100 are connected to I / O interface 1105, including: input unit 1106, output unit 1107, storage unit 1108, and communication unit 1109. Input unit 1106 can be any type of device capable of inputting information to electronic device 1100. Input unit 1106 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 1107 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1108 may include, but is not limited to, a hard disk and an optical disk. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and / or chipsets, such as Bluetooth devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or the like.

[0149] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as method 300. For example, in some embodiments, method 300 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of method 300 described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute method 300 by any other suitable means (e.g., by means of firmware).

[0150] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0152] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0154] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0155] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0156] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0157] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A trajectory planning method for vehicles, comprising: Obtain the speed and position of one or more potential obstacles around the vehicle; Based on the speed and position of the one or more risk obstacles, a lane with a lower risk relative to the one or more risk obstacles is selected from the adjacent lanes on both sides of the vehicle as a low-risk lane, wherein the adjacent lanes include the left lane located to the left of the vehicle and the right lane located to the right of the vehicle. For each of the vehicle's current driving lane and low-risk lanes, a travel trajectory for that lane is generated, wherein the travel trajectory for the current driving lane corresponds to the path along which the vehicle will travel, and the travel trajectory for the low-risk lane corresponds to the path along which the vehicle will change lanes from the current driving lane to the low-risk lane and then travel along the low-risk lane after completing the lane change; and Based on the location of the one or more risk obstacles, selecting the vehicle's travel trajectory from the vehicle's current driving lane and the low-risk lane's travel trajectory includes: For each of the one or more risk obstacles, the longitudinal distance of the risk obstacle is determined based on the difference between the s-value of the entry point of the risk obstacle into the current driving lane of the vehicle in the first Frenet coordinate system and the s-value of the vehicle's position in the first Frenet coordinate system, wherein the entry point of the risk obstacle into the current driving lane of the vehicle is the entry point of the risk obstacle into the current driving lane of the vehicle along the direction of the speed of the risk obstacle, and the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the current driving lane of the vehicle; The risk obstacle with the smallest longitudinal distance among the one or more risk obstacles is designated as the critical obstacle; For each of the vehicle's current driving lane and low-risk lanes, determine the longitudinal risk value of that lane, including: Based on the difference between the s-value of the obstacle intersection point in the Frenet coordinate system corresponding to the lane and the s-value of the vehicle's position in the Frenet coordinate system corresponding to the lane, the target distance of the critical obstacle corresponding to the lane is determined. Here, the obstacle intersection point is the point where the critical obstacle travels along the direction of its velocity and intersects the centerline of the lane. Furthermore, the Frenet coordinate system corresponding to the lane is a Frenet coordinate system defined based on the centerline of the lane. Based on the target distance of the critical obstacle corresponding to the lane and the planned length of the lane's trajectory, the longitudinal risk value of the lane is determined. The planned length of the lane's trajectory is the distance from the vehicle's position to the end point of the lane's trajectory. Where a braking point exists within the lane's trajectory, the end point of the lane's trajectory is the braking point within the lane's trajectory; and where no braking point exists within the lane's trajectory, the end point of the lane's trajectory is the end point of the lane's trajectory. The vehicle's trajectory is selected from the trajectories of the vehicle's current driving lane and the low-risk lane, based at least in part on the longitudinal risk values ​​of the vehicle's current driving lane and the low-risk lane.

2. The method according to claim 1, wherein, The process of obtaining obstacle information about one or more potential obstacles around the vehicle includes: For each obstacle around the vehicle, the obstacle is determined to be a risk obstacle in response to the distance between the obstacle's position and its entry point into the vehicle's current driving lane being less than or equal to an interaction threshold, wherein the entry point of the obstacle into the vehicle's current driving lane is the entry point of the obstacle into the vehicle's current driving lane along the direction of the obstacle's velocity.

3. The method according to claim 1, wherein, The step of selecting a lane from adjacent lanes on both sides of the vehicle that poses a lower risk relative to the one or more risky obstacles, based on the speed and position of the one or more risky obstacles, as a low-risk lane includes: For each adjacent lane of the vehicle, determine the risk value of each obstacle among the obstacles on the side of that adjacent lane, including: For each of the one or more risk obstacles on the side of the adjacent lane, the time at which the obstacle enters the vehicle's current lane is determined based on the obstacle's speed and position; and For each of the one or more risk obstacles on the side of the adjacent lane, the risk value of the obstacle is determined based on the time the obstacle enters the vehicle's current driving lane; For each adjacent lane, the risk value of that adjacent lane is determined based on the risk value of the obstacle on the side of the one or more risk obstacles located in that adjacent lane; and The low-risk lane is determined based on the risk value of each adjacent lane of the vehicle.

4. The method according to claim 3, wherein, For each of the one or more risk obstacles located on the side of the adjacent lane, determining the risk value of the obstacle based on the time the obstacle entered the vehicle's current driving lane includes: For each of the one or more risk obstacles on the side where the adjacent lane is located, a first sub-risk value for the obstacle is determined based on the time when the obstacle enters the vehicle's current driving lane; A second sub-risk value for the obstacle is determined based on the distance between the obstacle's location and its entry point into the vehicle's current lane, wherein the entry point of the obstacle into the vehicle's current lane is the point where the obstacle enters the vehicle's current lane along the direction of its velocity; and The risk value of the obstacle is determined based on the first sub-risk value and the second sub-risk value of the obstacle.

5. The method according to claim 1, wherein, The step of selecting the vehicle's trajectory from the current driving lane and the low-risk lane based on the location information of the one or more risk obstacles further includes: For each of the vehicle's current driving lane and low-risk lanes, determine the lateral risk value for that lane, including: Based on the distance between the position of the critical obstacle and the entry point of the obstacle's trajectory into the lane, the lateral distance between the position of the critical obstacle and the trajectory of the lane is determined, wherein the entry point of the obstacle's trajectory into the lane is the point where the obstacle enters the lane along the direction of its velocity; and Based on the lateral distance between the location of the critical obstacle and the travel trajectory of the lane, the lateral risk value of the lane is determined. The step of selecting the vehicle's travel trajectory from the travel trajectories of the vehicle's current travel lane and the low-risk lane, based at least in part on the longitudinal risk values ​​of the vehicle's current travel lane and the low-risk lane, includes: Based on the longitudinal risk value and the lateral risk value of the vehicle's current driving lane and the low-risk lane, the vehicle's travel trajectory is selected from the vehicle's travel trajectories in the current driving lane and the low-risk lane.

6. The method according to claim 5, wherein, The step of selecting the vehicle's travel trajectory from the travel trajectories of the vehicle's current driving lane and the low-risk lane based on the longitudinal risk value and the lateral risk value of the vehicle's current driving lane and the low-risk lane includes: In response to the difference between the lateral risk value of the current driving lane and the lateral risk value of the low-risk lane being greater than a lateral threshold, and in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being greater than a longitudinal threshold, the travel trajectory of the vehicle in the low-risk lane is selected as the vehicle's travel trajectory. In response to the difference between the lateral risk value of the current driving lane and the lateral risk value of the low-risk lane being less than or equal to the lateral threshold, or in response to the difference between the longitudinal risk value of the current driving lane and the longitudinal risk value of the low-risk lane being less than or equal to the longitudinal threshold, the travel trajectory of the vehicle's current driving lane is selected as the travel trajectory of the vehicle.

7. The method according to claim 6, wherein, The lateral threshold is determined based on the difference between the s-value of the position of the critical obstacle in the first Frenet coordinate system and the s-value of the position of the vehicle in the first Frenet coordinate system, wherein the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the vehicle's current driving lane.

8. The method of claim 5, further comprising: In response to determining that the selected vehicle's travel trajectory is the travel trajectory of the low-risk lane, and in response to determining that the vehicle has not entered the low-risk lane, for each of the vehicle's current travel lane and the low-risk lane, a longitudinal risk value and a lateral risk value for that lane are determined. as well as Based on the longitudinal risk value and the lateral risk value of the vehicle's current driving lane and the low-risk lane, it is determined whether to change the vehicle's travel trajectory to the travel trajectory of the current driving lane.

9. A trajectory planning device for a vehicle, comprising: An obstacle determination unit is configured to: acquire the speed and position of one or more potential obstacles around the vehicle; The lane selection unit is configured to select, based on the speed and position of the one or more risk obstacles, a lane on the side of the adjacent lanes on both sides of the vehicle that has a lower risk relative to the one or more risk obstacles, as a low-risk lane, wherein the adjacent lanes include a left lane located to the left of the vehicle and a right lane located to the right of the vehicle. The trajectory generation unit is configured to: generate a travel trajectory for each of the vehicle's current driving lane and low-risk lanes, wherein the travel trajectory for the current driving lane corresponds to the path along which the vehicle will travel, and the travel trajectory for the low-risk lane corresponds to the path along which the vehicle will change lanes from the current driving lane to the low-risk lane and then travel along the low-risk lane after completing the lane change; and The trajectory selection unit is configured to: select the vehicle's trajectory from the vehicle's current driving lane and low-risk lane trajectories based on the location of the one or more risk obstacles, including: For each of the one or more risk obstacles, the longitudinal distance of the risk obstacle is determined based on the difference between the s-value of the entry point of the risk obstacle into the current driving lane of the vehicle in the first Frenet coordinate system and the s-value of the vehicle's position in the first Frenet coordinate system, wherein the entry point of the risk obstacle into the current driving lane of the vehicle is the entry point of the risk obstacle into the current driving lane of the vehicle along the direction of the speed of the risk obstacle, and the first Frenet coordinate system is a Frenet coordinate system defined based on the centerline of the current driving lane of the vehicle; The risk obstacle with the smallest longitudinal distance among the one or more risk obstacles is designated as the critical obstacle; For each of the vehicle's current driving lane and low-risk lanes, determine the longitudinal risk value of that lane, including: Based on the difference between the s-value of the obstacle intersection point in the Frenet coordinate system corresponding to the lane and the s-value of the vehicle's position in the Frenet coordinate system corresponding to the lane, the target distance of the critical obstacle corresponding to the lane is determined. Here, the obstacle intersection point is the point where the critical obstacle travels along the direction of its velocity and intersects the centerline of the lane. Furthermore, the Frenet coordinate system corresponding to the lane is a Frenet coordinate system defined based on the centerline of the lane. Based on the target distance of the critical obstacle corresponding to the lane and the planned length of the lane's trajectory, the longitudinal risk value of the lane is determined. The planned length of the lane's trajectory is the distance from the vehicle's position to the end point of the lane's trajectory. Where a braking point exists within the lane's trajectory, the end point of the lane's trajectory is the braking point within the lane's trajectory; and where no braking point exists within the lane's trajectory, the end point of the lane's trajectory is the end point of the lane's trajectory. The vehicle's trajectory is selected from the trajectories of the vehicle's current driving lane and the low-risk lane, based at least in part on the longitudinal risk values ​​of the vehicle's current driving lane and the low-risk lane.

10. The apparatus according to claim 9, wherein, The lane selection unit includes: The obstacle risk determination subunit is configured as follows: For each adjacent lane of the vehicle, determine the risk value of each obstacle among the obstacles on the side of that adjacent lane, including: For each of the one or more risk obstacles on the side of the adjacent lane, the time at which the obstacle enters the vehicle's current lane is determined based on the obstacle's speed and position; and For each of the one or more risk obstacles on the side of the adjacent lane, the risk value of the obstacle is determined based on the time the obstacle enters the vehicle's current driving lane; The lane risk determination subunit is configured to: for each adjacent lane, determine the risk value of that adjacent lane based on the risk value of an obstacle on the side of the one or more risk obstacles located in that adjacent lane; and The lane selection subunit is configured to determine the low-risk lane based on the risk value of each adjacent lane of the vehicle.

11. An electronic device, comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

13. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-8.

14. An autonomous vehicle, comprising the electronic device according to claim 11.

15. An edge computing device, comprising the electronic device according to claim 11.

Images