Trajectory planning method and related apparatus
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- YINWANG INTELLIGENT TECHNOLOGIES CO LTD
- Filing Date
- 2024-12-20
- Publication Date
- 2026-06-25
Smart Images
Figure CN2024141151_25062026_PF_FP_ABST
Abstract
Description
Trajectory planning methods and related devices Technical Field
[0001] This application relates to the field of vehicle control technology, and in particular to a trajectory planning method and related apparatus. Background Technology
[0002] In the context of autonomous driving and assisted driving, U-turns and various obstacle-avoidance scenarios are key connecting scenarios for road navigation. For example, in U-turn scenarios on narrow roads, dead ends, or where there are other obstacles, the vehicle's turning ability limits its ability to pass through in one go using a single gear. Similarly, in obstacle-avoidance scenarios such as passing through narrow turnstiles or starting from a roadside parking space, it is impossible to pass through in one go using a single gear.
[0003] Currently, in the aforementioned scenarios of vehicle U-turns and various escape routes, unreasonable planning of vehicle trajectories can lead to vehicles being unable to pass or getting stuck, resulting in low traffic efficiency. Summary of the Invention
[0004] This application provides a trajectory planning method and related apparatus, which can reasonably plan the trajectory of vehicles for U-turns and various escape scenarios, so as to enable vehicles to pass smoothly and improve traffic efficiency.
[0005] In a first aspect, embodiments of this application provide a trajectory planning method applied to a first vehicle, the trajectory planning method comprising:
[0006] The system acquires static and dynamic information about the environment in which the first vehicle is located, and generates a planned trajectory based on this information. The static information includes road condition information for the road segment where the first vehicle is located, and the dynamic information includes the movement information of dynamic obstacles in that road segment. The planned trajectory includes at least a first trajectory and a second trajectory. The gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory. The planned trajectory is used to instruct the first vehicle to leave the target driving scenario using multiple gears. The planned trajectory does not conflict with the movement trajectories of the dynamic obstacles.
[0007] This application provides a trajectory planning method. For a first vehicle in a target driving scenario, a planned trajectory is generated by combining static and dynamic information of the vehicle's environment. This generated trajectory comprehensively considers the dynamic interaction between the first vehicle and dynamic obstacles. As the first vehicle leaves the target driving scenario in multiple gears according to the planned trajectory, it can dynamically interact with dynamic obstacles, adapting to complex changes in the dynamic interaction environment to avoid conflicts with the movement trajectories of dynamic obstacles. This reduces the probability of the first vehicle getting stuck due to trajectory conflicts with dynamic obstacles, requiring premature manual intervention and ensuring the continuity of intelligent driving. Therefore, the trajectory planning method in this application can rationally plan the vehicle's trajectory for scenarios including but not limited to vehicle U-turns and various escape scenarios, enabling smooth vehicle passage and improving traffic efficiency.
[0008] Optionally, the aforementioned static information includes, but is not limited to, road condition information of the road segment where the first vehicle is located. For example, road condition perception information of the road segment where the first vehicle is located (road boundaries, lane lines, road signs, road guide lines, static obstacles, etc.), traffic light information of the road segment where the first vehicle is located, map information of the road segment where the first vehicle is located, historical traffic flow information of the road segment where the first vehicle is located, etc. This application embodiment does not limit this.
[0009] Optionally, the aforementioned dynamic information includes, but is not limited to, the movement information of dynamic obstacles in the road segment where the first vehicle is located. For example, the movement information of other vehicles in the road segment where the first vehicle is located, the movement information of pedestrians in the road segment where the first vehicle is located, the movement information of animals in the road segment where the first vehicle is located, etc. This application embodiment does not limit this.
[0010] Optionally, the aforementioned gears include, but are not limited to, parking gear (P), reverse gear (R), neutral gear (N), drive gear (D), etc., and the embodiments of this application do not limit this.
[0011] Optionally, the aforementioned target driving scenarios may include, but are not limited to, driving scenarios where the vehicle cannot leave when driving in single gear. For example, driving scenarios involving turning around in multiple gears, driving scenarios involving getting out of trouble in multiple gears, etc., and this application embodiment does not limit this.
[0012] In one possible implementation, the above-mentioned generation of a planned trajectory based on static and dynamic information can be achieved through methods including but not limited to: identifying the driving scenario in which the first vehicle is located; and, when the first vehicle is in a target driving scenario, generating a planned trajectory based on static and dynamic information. The target driving scenario includes driving scenarios in which the vehicle cannot leave when driving in single gear.
[0013] In this embodiment, a target driving scenario where the first vehicle cannot leave when driving in single gear can be identified. For such scenarios, a planned trajectory is generated by combining static and dynamic information about the environment in which the first vehicle is located. This generated trajectory comprehensively considers the dynamic interaction between the first vehicle and dynamic obstacles. As the first vehicle follows this planned trajectory to leave the target driving scenario in multiple gears, it can dynamically interact with the dynamic obstacles, changing dynamically according to the complex dynamic interaction environment to avoid conflicts with the movement trajectories of the obstacles. This reduces the probability of the first vehicle getting stuck due to a conflict with the obstacles, requiring premature manual intervention and ensuring the continuity of intelligent driving. Therefore, the trajectory planning method in this embodiment can rationally plan the vehicle's trajectory for driving scenarios where the vehicle cannot leave when driving in single gear, including but not limited to U-turns and various escape maneuvers, enabling smooth vehicle passage and improving traffic efficiency.
[0014] In one possible implementation, the identification of the driving scenario of the first vehicle can be achieved in ways including but not limited to the following: when the environment of the first vehicle meets the first and second conditions, the system identifies that the first vehicle needs to make a U-turn in multiple gears on the first road segment. The first condition includes that the first road segment is a U-turn segment; the second condition includes any one or more of the following: the duration for which the single-gear U-turn space corresponding to the first road segment is insufficient exceeds a first threshold; the duration for which the traffic trajectory of the first road segment is a multi-gear trajectory exceeds a second threshold; and the duration for which the single-gear U-turn trajectory corresponding to the first road segment poses a collision risk with an obstacle exceeds a third threshold.
[0015] In this embodiment, a method for recognizing driving scenarios involving U-turns in multiple gears is provided. When the environment in which the first vehicle is located meets the first and second conditions mentioned above, it can be considered that the first vehicle cannot make a U-turn by driving in a single gear and needs to drive in multiple gears to make a U-turn, thereby triggering the next step of multi-gear trajectory planning, so that the first vehicle can make a U-turn smoothly by driving in multiple gears according to the planned trajectory, thereby improving traffic efficiency.
[0016] In one possible implementation, the identification of the driving scenario of the first vehicle can be achieved in ways including but not limited to the following: when the environment of the first vehicle meets the third and fourth conditions, the system identifies that the first vehicle needs to escape from a difficult situation in the second road segment using multiple gears. The third condition includes the duration for which the first vehicle's speed is below a first threshold exceeding a fourth threshold; the fourth condition includes any one or more of the following: the duration for which obstacles exist around the first vehicle exceeding a fifth threshold; the duration for which the single-gear U-turn space corresponding to the second road segment is insufficient exceeding a sixth threshold; and the duration for which the single-gear U-turn trajectory corresponding to the second road segment poses a collision risk with an obstacle exceeding a seventh threshold.
[0017] In this embodiment, a method for recognizing driving scenarios that require multiple gears to escape from a difficult situation is provided. When the environment in which the first vehicle is located meets the third and fourth conditions mentioned above, it can be considered that the first vehicle cannot escape from a difficult situation by driving in a single gear and needs to drive in multiple gears to escape from a difficult situation. This triggers the next step of multi-gear trajectory planning, so that the first vehicle can successfully escape from a difficult situation by driving in multiple gears according to the planned trajectory, thereby improving traffic efficiency.
[0018] In one possible implementation, the above-mentioned generation of a planned trajectory based on static and dynamic information can be achieved in ways including but not limited to: generating one or more guide lines based on static information, and generating a planned trajectory based on dynamic information and one or more guide lines. The one or more guide lines include routes that may guide the first vehicle to leave the target driving scenario at multiple gears.
[0019] In this embodiment, a method for generating a planned trajectory is provided. First, one or more guide lines are generated based on static information about the environment in which the first vehicle is located. These guide lines guide the first vehicle to potentially leave the target driving scenario at multiple gears. However, during the departure process, conflicts may occur with the movement of dynamic obstacles. Therefore, dynamic information about the environment in which the first vehicle is located can also be incorporated, and the final planned trajectory is determined based on the one or more guide lines generated above. As the first vehicle leaves the target driving scenario at multiple gears according to the planned trajectory, it can dynamically interact with dynamic obstacles, changing dynamically according to the complex dynamic interaction environment. This avoids conflicts with the movement trajectories of dynamic obstacles, reduces the probability of the first vehicle stopping due to a conflict with dynamic obstacles, and thus reduces the probability of premature manual intervention, ensuring the continuity of intelligent driving and improving traffic efficiency.
[0020] Alternatively, the planned trajectory can be generated using a network model. For example, the aforementioned static and dynamic information can be input into a network model, which will then output the planned trajectory. Optionally, this network model can be trained using historical data, including but not limited to historical static and dynamic information and their corresponding generated historical planned trajectories.
[0021] In one possible implementation, the above-mentioned generation of one or more guide lines based on static information can be achieved in ways including but not limited to: generating a planning base map based on the road condition information of the road segment where the first vehicle is located, and generating one or more guide lines based on the planning base map and constraints. The constraints include any one or more of the following: historical traffic flow trajectory constraints, traffic element constraints of the road segment where the first vehicle is located, vehicle kinematic constraints, and static obstacle constraints of the road segment where the first vehicle is located.
[0022] In this embodiment, one or more guide lines can be generated based on the planning base map and the aforementioned constraints. These guide lines take into account the static information of the environment in which the first vehicle is located and the constraints formed by the static information. Thus, the first vehicle may leave the target driving scene in multiple gears according to these guide lines. In the process of leaving the target driving scene, it can avoid conflicts with static obstacles, reduce the probability of the first vehicle being stuck due to a conflict with a static obstacle, and thus ensure the continuity of intelligent driving.
[0023] Optionally, the planning base map may include, but is not limited to, occupancy maps, constrained delaunay triangulations (CDT) maps, etc., and the embodiments of this application do not impose any restrictions on this.
[0024] Optionally, the above-mentioned generation of one or more guide lines based on the planning base map and constraints can employ algorithms such as search, optimization, machine learning, or combinations thereof, such as A* algorithm, hybrid A* algorithm, etc. This application embodiment does not impose any limitations on this.
[0025] Alternatively, one or more guide lines can be generated using a network model. For example, the aforementioned static information can be input into a network model, which will output one or more guide lines. Optionally, this network model can be trained using historical data, including but not limited to historical static information, historical constraints, and the corresponding one or more historical guide lines generated.
[0026] In one possible implementation, the above-mentioned generation of a planned trajectory based on dynamic information and one or more guide lines can be achieved in ways including but not limited to the following: based on the motion information of dynamic obstacles in the road segment where the first vehicle is located, the game relationship between the first vehicle and the dynamic obstacles is obtained, and the planned trajectory is generated based on the game relationship and one or more guide lines.
[0027] In this embodiment, the final planned trajectory can be determined based on the game relationship between the first vehicle and the dynamic obstacle, using one or more guide lines generated above. Since the generated planned trajectory comprehensively considers the dynamic interaction between the first vehicle and the dynamic obstacle, the first vehicle can dynamically interact with the dynamic obstacle as it leaves the target driving scenario according to the planned trajectory in multiple gears. The trajectory changes dynamically according to the complex dynamic interaction environment to avoid conflicts with the movement trajectory of the dynamic obstacle, reducing the probability of the first vehicle being stuck due to a conflict with the dynamic obstacle and requiring premature manual intervention, thus ensuring the continuity of intelligent driving. Therefore, for scenarios including but not limited to vehicle U-turns and various escape scenarios, the vehicle's trajectory can be rationally planned to ensure smooth vehicle passage and improve traffic efficiency.
[0028] Optionally, the game relationship between the first vehicle and the dynamic obstacles can also be generated through a network model. For example, the aforementioned dynamic information and one or more guide lines are input into the network model, and the network model outputs the aforementioned game relationship. Optionally, the network model can be trained using historical data, including but not limited to historical dynamic information, historical guide lines, and their corresponding historical game relationships.
[0029] In one possible implementation, the planned trajectory carries speed information, which is obtained based on game theory relationships. The speed information includes the speed of the first vehicle traveling on each segment of the planned trajectory.
[0030] In this embodiment, a planned trajectory carrying speed information can be obtained based on the game relationship between the first vehicle and the dynamic obstacle. As the first vehicle drives away from the target driving scene at multiple speeds according to the planned trajectory, it can avoid conflicts with the movement trajectory of the dynamic obstacle, reduce the probability of the first vehicle being stuck due to conflict with the dynamic obstacle and requiring early manual intervention, and ensure the continuity of intelligent driving.
[0031] Optionally, the planned trajectory carrying speed information obtained based on the game relationship between the first vehicle and the dynamic obstacle can be obtained by using optimization, artificial intelligence (AI) algorithms or combinations thereof. This application embodiment does not limit this.
[0032] In one possible implementation, the planned trajectory includes at least three consecutive trajectories: trajectory A, trajectory B, and trajectory C. Trajectories A correspond to a forward gear, trajectory B corresponds to a reverse gear, and trajectory C corresponds to a forward gear.
[0033] In this embodiment, for scenarios where the first vehicle cannot make a U-turn when driving in single gear, the first vehicle can make a U-turn smoothly by driving in multiple gears according to the planned trajectory which includes at least continuous trajectories A, B, and C, thereby improving traffic efficiency.
[0034] In one possible implementation, the planned trajectory includes at least two continuous trajectories, D and E. Trajectories D correspond to the reverse gear, and trajectory E corresponds to the forward gear.
[0035] In this embodiment, for scenarios where the first vehicle cannot get out of trouble by driving in a single gear, the first vehicle can get out of trouble smoothly by driving in multiple gears according to the planned trajectory which includes at least continuous trajectories D and E, thereby improving traffic efficiency.
[0036] In one possible implementation, the planned trajectory includes at least two continuous trajectories, F and G. Trajectories F correspond to a forward gear, and trajectory G corresponds to a reverse gear.
[0037] In this embodiment, for scenarios where the first vehicle cannot get out of trouble by driving in a single gear, the first vehicle can get out of trouble smoothly by driving in multiple gears according to the planned trajectory which includes at least continuous trajectories F and G, thereby improving traffic efficiency.
[0038] In one possible implementation, the trajectory planning method described above further includes: displaying the planned trajectory.
[0039] In this embodiment, the planned trajectory can be displayed through devices including but not limited to the vehicle's display screen. The driver can be informed in a timely manner that if the first vehicle cannot leave the target driving scene when it is driving in single gear, the first vehicle will leave the target driving scene in multiple gears according to the displayed planned trajectory. The driver can also intervene in a timely manner to pause or terminate the multi-gear movement of the first vehicle, thereby improving the driver's intelligent driving perception and controllability of the first vehicle and ensuring the driving safety of the vehicle.
[0040] Optionally, the above-mentioned multi-gear planning trajectory including reverse gear can be presented in segments at different times or in multiple segments simultaneously; this application embodiment does not impose any restrictions on this. Optionally, the display colors corresponding to the trajectories of different gears in the above-mentioned multi-gear planning trajectory including reverse gear can be different or the same; this application embodiment does not impose any restrictions on this.
[0041] In one possible implementation, the trajectory planning method further includes: displaying the game relationship between the first vehicle and the dynamic obstacle.
[0042] In this embodiment, the interaction between the first vehicle and the dynamic obstacle can be displayed through devices including but not limited to the vehicle's infotainment display screen. The driver can promptly learn about the interaction intentions between the first vehicle and the dynamic obstacle as the first vehicle leaves the target driving scene in multiple gears according to the displayed planned trajectory. Specifically, the driver can determine whether to avoid the dynamic obstacle or not. The driver can also intervene in a timely manner to pause or terminate the interaction between the first vehicle and the dynamic obstacle, thereby improving the driver's intelligent driving perception and controllability of the first vehicle and ensuring the driving safety of the vehicle.
[0043] In one possible implementation, the trajectory planning method further includes controlling the first vehicle to leave the target driving scenario according to the planned trajectory.
[0044] In this embodiment, for driving scenarios where vehicles cannot leave when driving in single gear, including but not limited to U-turns and various escaping situations, the vehicle's trajectory can be rationally planned to control the first vehicle to leave the target driving scenario according to the planned trajectory, so that the vehicle can pass smoothly and improve traffic efficiency.
[0045] In one possible implementation, the trajectory planning method further includes issuing a prompt message when controlling the first vehicle to drive away from the target driving scenario in reverse along the planned trajectory.
[0046] In this embodiment, when controlling the first vehicle to drive away from the target driving scene in reverse along the planned trajectory, a prompt message can also be issued to remind the driver or surrounding vehicles and pedestrians that the vehicle is reversing, which can increase the attention of all parties to the vehicle reversing and ensure the driving safety of the vehicle.
[0047] Optionally, the prompt information may include, but is not limited to, voice broadcast, reversing image, reversing prompt sound, etc., and this application embodiment does not limit this.
[0048] Secondly, embodiments of this application provide a trajectory planning apparatus, which includes a unit for performing the method as described in any of the first aspects.
[0049] In one possible design, the device includes:
[0050] The processing unit is used to acquire static and dynamic information of the environment in which the first vehicle is located. The static information includes road condition information of the road segment in which the first vehicle is located, and the dynamic information includes the motion information of dynamic obstacles in the road segment in which the first vehicle is located.
[0051] The processing unit is also used to generate a planned trajectory based on static and dynamic information; wherein the planned trajectory includes at least a first trajectory and a second trajectory, the gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory, the planned trajectory is used to instruct the first vehicle to leave the target driving scene in multiple gears, and the planned trajectory does not conflict with the movement trajectory of the dynamic obstacle.
[0052] In one possible implementation, the device further includes a communication unit.
[0053] The processing unit is specifically used to acquire static and dynamic information about the environment in which the first vehicle is located through the communication unit.
[0054] Regarding the processing unit and communication unit described in the second aspect and any possible implementation, the steps performed thereon can be referred to the corresponding implementations in the first aspect.
[0055] For the technical effects of the second aspect and any possible implementation, please refer to the description of the technical effects corresponding to the first aspect and the corresponding implementation.
[0056] Optionally, in the trajectory planning apparatus described in the second aspect above and any possible implementation:
[0057] In one implementation, the trajectory planning device is a trajectory planning equipment. When the trajectory planning device is a trajectory planning equipment, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.
[0058] In another implementation, the trajectory planning device is a chip (system) or circuit used in a trajectory planning device. When the trajectory planning device is a chip (system) or circuit used in a trajectory planning device, the communication unit can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pins, or related circuits on the chip (system) or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.
[0059] Thirdly, embodiments of this application provide a trajectory planning device, which includes a processor. The processor is coupled to a memory and can be used to execute instructions in the memory to implement the methods of any one of the first to second aspects and any possible implementations described above. Optionally, the trajectory planning device further includes a memory. Optionally, the trajectory planning device further includes a communication interface, and the processor is coupled to the communication interface.
[0060] Fourthly, embodiments of this application provide a chip, including: logic circuitry and a communication interface. The communication interface is used to receive or send information; the logic circuitry is used to receive or send information through the communication interface, causing the chip to execute the methods described in the first aspect and any of the possible implementations.
[0061] Fifthly, embodiments of this application provide a computer-readable storage medium for storing a computer program (also referred to as code or instructions); when the computer program is run on a computer, the methods described in the first aspect and any possible implementation are implemented.
[0062] Sixthly, embodiments of this application provide a computer program product, the computer program product comprising: a computer program (also referred to as code or instructions); and, when the computer program is run, causing a computer to perform the methods described in the first aspect and any possible implementation thereof.
[0063] In a seventh aspect, embodiments of this application provide a terminal, the terminal including at least one trajectory planning device as described in the second aspect, or the trajectory planning device as described in the third aspect, or the chip as described in the fourth aspect.
[0064] Optionally, the terminal can be a means of transportation, such as a car, truck, aircraft, drone, slow transport vehicle, spacecraft, or ship, or any other possible means of transportation used in any possible scenario. This application embodiment does not limit this.
[0065] Optionally, the terminal is used to implement the method described in the first aspect and any possible implementation.
[0066] Furthermore, in the process of performing the method described in the first aspect and any possible implementation above, the processes related to sending and / or receiving information in the above methods can be understood as the process of the processor outputting information, and / or the process of the processor receiving input information. When outputting information, the processor can output the information to a transceiver (or communication interface, or transmitting module) so that the transceiver can transmit it. After the information is output by the processor, it may need to undergo other processing before reaching the transceiver. Similarly, when the processor receives input information, the transceiver (or communication interface, or transmitting module) receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, the information may need to undergo other processing before being input to the processor.
[0067] Based on the above principles, for example, the information sent mentioned in the aforementioned method can be understood as information output by the processor. Similarly, the information received can be understood as information received by the processor from input.
[0068] Optionally, unless otherwise specified, or unless they contradict their actual function or internal logic in the relevant description, the operations of the processor, such as transmitting, sending, and receiving, can be more generally understood as processor output and receiving, input, and other operations.
[0069] Optionally, in performing the methods described in the first aspect and any possible implementation above, the processor may be a processor specifically designed to perform these methods, or it may be a processor that performs these methods by executing computer instructions stored in memory, such as a general-purpose processor. The memory may be a non-transitory memory, such as read-only memory (ROM), which may be integrated with the processor on the same chip or disposed on different chips. This application does not limit the type of memory or the arrangement of the memory and processor.
[0070] In one possible implementation, at least one of the aforementioned memories is located outside the device.
[0071] In yet another possible implementation, at least one of the aforementioned memories is located within the device.
[0072] In another possible implementation, a portion of the memory of the at least one memory is located inside the device, while another portion is located outside the device.
[0073] In this application, the processor and memory may also be integrated into a single device, that is, the processor and memory can be integrated together. Attached Figure Description
[0074] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0075] Figure 1A is a schematic diagram of a U-turn scenario at an intersection provided in an embodiment of this application;
[0076] Figure 1B is a schematic diagram of another U-turn scenario at an intersection provided in an embodiment of this application;
[0077] Figure 2 is a schematic diagram of a roadside start-up and get-out-of-trouble scenario provided by an embodiment of this application;
[0078] Figure 3 is a flowchart illustrating a trajectory planning method provided in an embodiment of this application;
[0079] Figure 4 is a schematic diagram of a trajectory planning scenario provided in an embodiment of this application;
[0080] Figure 5 is a schematic diagram of another trajectory planning scenario provided by an embodiment of this application;
[0081] Figure 6 is a schematic diagram of a trajectory planning device provided in an embodiment of this application;
[0082] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;
[0083] Figure 8 is a schematic diagram of the structure of a chip provided in an embodiment of this application. Detailed Implementation
[0084] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described below with reference to the accompanying drawings.
[0085] The terms "first" and "second," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0086] The term "embodiment" as used herein means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the various embodiments of this application are consistent and can be mutually referenced, and technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0087] It should be understood that in this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.
[0088] It should be noted that, in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.
[0089] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a correlation between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various information, thereby reducing instruction overhead to some extent. The information to be instructed can be sent as a whole or divided into multiple sub-information units, and the sending period and / or timing of these sub-information units can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information units can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.
[0090] It should be noted that in this application, "send" can be understood as "output" and "receive" can be understood as "input". "Send information to A", where "to A" simply indicates the direction of information transmission, and A is the destination, does not limit "send information to A" to a direct transmission over the air interface. "Send information to A" includes sending information directly to A, as well as sending information indirectly to A through a transmitter. Therefore, "send information to A" can also be understood as "outputting information destined for A". Similarly, "receive information from A" indicates that the source of the information is A, including receiving information directly from A, as well as receiving information indirectly from A through a receiver. Therefore, "receive information from A" can also be understood as "inputting information from A".
[0091] This application provides a trajectory planning method and related apparatus, applied in the field of vehicle control technology, such as vehicle trajectory planning for vehicle U-turns and various obstacle avoidance scenarios. To better understand the technical solution of this application, the relevant terms and concepts that may be involved in the embodiments of this application are introduced below.
[0092] Vehicle gears: used to adjust the vehicle's speed and traction (torque).
[0093] Generally, vehicle gears include, but are not limited to, parking gear (also known as parking gear, parking gear, P gear), reverse gear (R gear), neutral gear (N gear), drive gear (also known as drive gear, D gear), etc., and the embodiments of this application do not limit this.
[0094] The P gear is used for parking, using a mechanical device to lock the rotating parts of the vehicle, preventing it from moving. The R gear is used when reversing. The N gear can be used when starting the vehicle, towing, or temporarily stopping (such as at a red light). To prevent the vehicle from rolling on a slope, the brake pedal must be pressed when the vehicle is in N gear. The D gear includes multiple speed settings; the lower the gear, the slower the speed but the greater the traction (torque), and the higher the gear, the faster the speed but the less traction (torque). You can switch between gears to adjust the vehicle speed.
[0095] Multi-gear driving trajectory planning: This refers to a planned trajectory that includes segments of driving in two or more gears. For example, one segment of the trajectory is for driving in D gear, and another segment is for driving in R gear.
[0096] In the context of autonomous driving and assisted driving, U-turns and various obstacle-avoidance scenarios are key connecting scenarios for road navigation. For example, in U-turn scenarios on narrow roads, dead ends, or where there are other obstacles, the vehicle's turning ability limits its ability to pass through in one go using a single gear. Similarly, in obstacle-avoidance scenarios such as passing through narrow turnstiles or starting from a roadside parking space, it is impossible to pass through in one go using a single gear.
[0097] Currently, in the aforementioned scenarios of vehicle U-turns and various escape routes, unreasonable planning of vehicle trajectories can lead to vehicles being unable to pass or getting stuck, resulting in low traffic efficiency.
[0098] For details, please refer to Figures 1A and 1B. Figure 1A is a schematic diagram of a U-turn scenario at an intersection provided by an embodiment of this application, and Figure 1B is a schematic diagram of another U-turn scenario at an intersection provided by an embodiment of this application.
[0099] As shown in Figure 1A, in the scenario of a vehicle making a U-turn at an intersection, four trajectories (trajectory 1, trajectory 2, trajectory 3, and trajectory 4) are planned to achieve the U-turn at the intersection.
[0100] The turning radius R1 of track 1 is 1.5m-2.0m, the turning radius R2 of track 2 is 3.0m-4.0m, the turning radius R3 of track 3 is 4.5m-6.0m, and the turning radius R4 of track 4 is 6.0m-8.0m.
[0101] It can be seen that the turning radii of trajectories 1 and 2 are too small and the turning curvature is too large, exceeding the vehicle's maneuverability. Therefore, trajectories 1 and 2 have unreasonable planning issues, which will result in the vehicle being unable to make a U-turn. Although the turning curvature of trajectories 3 and 4 is in line with the vehicle's maneuverability, the turning radii are too large, which may cause the vehicle to get stuck due to the influence of oncoming vehicles, resulting in low traffic efficiency and even conflicts with oncoming vehicles, thus reducing the safety of intelligent driving and requiring early manual intervention.
[0102] As shown in Figure 1B, in the scenario of a vehicle making a U-turn at an intersection, two trajectories (trajectory 5 and trajectory 6) are planned to achieve the U-turn.
[0103] As can be seen, the turning radius of trajectory 5 is too small and the turning curvature is too large, exceeding the vehicle's maneuverability. Therefore, trajectory 5 has a problem with unreasonable planning, which will cause the vehicle to be unable to make a U-turn. Although the turning curvature of trajectory 6 is in line with the vehicle's maneuverability, the turning radius is too large. Due to the limited turning space, there will be a collision point with the obstacle, causing the vehicle to get stuck and resulting in low traffic efficiency.
[0104] For details, please refer to Figure 2, which is a schematic diagram of a roadside starting and getting out of trouble scenario provided by an embodiment of this application.
[0105] As shown in Figure 2, in a driving scenario where a vehicle is trying to start and get out of trouble on the roadside, it is blocked by another vehicle (or other obstacles) in front of it and cannot start moving onto the road, remaining stuck in place. Two trajectories (trajectory 7 and trajectory 8) are planned to help the vehicle start and get out of trouble.
[0106] As can be seen, trajectory 7 has a collision point with another vehicle (or other obstacle) ahead, which will cause the vehicle to get stuck and unable to start moving and get out of trouble. Although trajectory 8 does not have a collision point with another vehicle (or other obstacle) ahead, the curvature of the directional rotation is too large, exceeding the vehicle's movement capability, and the vehicle cannot actually start moving and get out of trouble.
[0107] It should be understood that Figures 1A, 1B, and 2 above are merely examples illustrating various driving scenarios where the vehicle cannot leave when driving in single gear, and should not be construed as limiting the embodiments of this application.
[0108] In view of this, this application provides a trajectory planning method that is applied to the field of vehicle control technology. For example, for vehicle trajectory planning in scenarios such as vehicle U-turns and various escape scenarios, the method can reasonably plan the vehicle trajectory, enabling the vehicle to pass smoothly and improving traffic efficiency.
[0109] Please refer to Figure 3, which is a flowchart illustrating a trajectory planning method provided in an embodiment of this application. This trajectory planning method is applied in the field of vehicle control technology, including but not limited to vehicle trajectory planning in various driving scenarios where the vehicle cannot leave when driving in single gear, such as vehicle U-turns shown in Figures 1A and 1B above, and vehicle trajectory planning in roadside start-up and escape scenarios shown in Figure 2 above.
[0110] Specifically, the trajectory planning method includes, but is not limited to, the following steps:
[0111] S301: The trajectory planning device acquires static and dynamic information about the environment in which the first vehicle is located.
[0112] It is understood that the trajectory planning device in this application embodiment may be a device equipped with a processor / chip that can execute computer execution instructions, or it may be a processor / chip that can execute computer execution instructions. Optionally, the trajectory planning device may be an electronic device, or it may be a processor / chip within an electronic device, used to execute the trajectory planning method in this application embodiment, so as to reasonably plan the trajectory of the vehicle for vehicle U-turns and various escape scenarios, so as to enable the vehicle to pass smoothly and improve traffic efficiency.
[0113] Optionally, the trajectory planning device and trajectory planning method in this application embodiment can be applied to, but are not limited to, vehicle systems. The vehicle equipped with the vehicle system is an intelligent driving vehicle and can be replaced by a terminal device. The terminal device can be, but is not limited to, vehicles such as commercial vehicles, passenger cars, trains, industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), robots, etc. This application embodiment does not specifically limit this.
[0114] Optionally, the trajectory planning device in this application embodiment can be deployed on a vehicle, whereby the vehicle generates the planned trajectory and performs corresponding vehicle control operations according to the planned trajectory. Alternatively, it can be deployed in the cloud, whereby the cloud generates the planned trajectory and then sends it to the vehicle, which then performs corresponding vehicle control operations according to the planned trajectory. This application embodiment does not impose any restrictions on this.
[0115] Optionally, the static information of the environment in which the first vehicle is located includes, but is not limited to, the road condition information of the road segment in which the first vehicle is located.
[0116] For example: road condition perception information of the road segment where the first vehicle is located (road boundaries, lane lines, road signs, road guide lines, static obstacles, etc.), traffic light information of the road segment where the first vehicle is located, map information of the road segment where the first vehicle is located, historical traffic flow information of the road segment where the first vehicle is located, etc. This application embodiment does not limit these.
[0117] Optionally, the aforementioned dynamic information includes, but is not limited to, the motion information of dynamic obstacles in the road segment where the first vehicle is located.
[0118] For example, the movement information of other vehicles on the road segment where the first vehicle is located, the movement information of pedestrians on the road segment where the first vehicle is located, the movement information of animals on the road segment where the first vehicle is located, etc. This application embodiment does not limit this.
[0119] S302: The trajectory planning device generates a planned trajectory based on static and dynamic information.
[0120] The planned trajectory includes at least a first trajectory and a second trajectory, and the gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory.
[0121] The planned trajectory is used to instruct the first vehicle to leave the target driving scene in multiple gears, and the planned trajectory does not conflict with the movement trajectory of the dynamic obstacle.
[0122] Optionally, the aforementioned gears include, but are not limited to, parking gear (P), reverse gear (R), neutral gear (N), drive gear (D), etc., and the embodiments of this application do not limit this.
[0123] Optionally, the aforementioned target driving scenarios may include, but are not limited to, driving scenarios in which the vehicle cannot leave when driving in single gear.
[0124] For example, the driving scenarios in Figures 1A and 1B above where it is impossible to turn around when driving in single gear, the driving scenarios in Figure 2 above where it is impossible to get out of trouble when driving in single gear, etc., are not limited in this application embodiment.
[0125] Understandably, for the first vehicle in the aforementioned target driving scenario, a planned trajectory can be generated by combining static and dynamic information of the environment in which the first vehicle is located. This makes the generated planned trajectory more human-like and comprehensively considers the dynamic interaction between the first vehicle and dynamic obstacles. Thus, as the first vehicle leaves the target driving scenario in multiple gears according to the planned trajectory, it can dynamically interact with dynamic obstacles. This allows it to dynamically change according to the complex dynamic interaction environment, avoiding conflicts with the movement trajectories of dynamic obstacles. This reduces the probability of the first vehicle getting stuck due to trajectory conflicts with dynamic obstacles, thus ensuring the continuity and integrity of intelligent driving.
[0126] Therefore, the trajectory planning method in this application embodiment can reasonably plan the trajectory of a vehicle for scenarios including but not limited to U-turns and various escape scenarios, so that the vehicle can pass smoothly, improve traffic efficiency, and alleviate traffic congestion.
[0127] In one possible embodiment, the generation of the planned trajectory based on static and dynamic information in step S302 above can be implemented in ways including but not limited to the following:
[0128] Identify the driving scenario of the first vehicle, and generate a planned trajectory based on static and dynamic information when the first vehicle is in the target driving scenario.
[0129] The target driving scenario includes driving scenarios where the vehicle cannot leave when driving in single gear.
[0130] Understandably, for a target driving scenario where the first vehicle cannot leave when driving in single gear, a planned trajectory can be generated by combining static and dynamic information of the environment in which the first vehicle is located. This generated planned trajectory comprehensively considers the dynamic interaction between the first vehicle and dynamic obstacles. As the first vehicle leaves the target driving scenario in multiple gears according to the planned trajectory, it can dynamically interact with dynamic obstacles. This allows it to dynamically change according to the complex dynamic interaction environment, avoiding conflicts with the movement trajectory of dynamic obstacles. This reduces the probability of the first vehicle getting stuck due to a conflict with dynamic obstacles, thus ensuring the continuity of intelligent driving.
[0131] Therefore, the trajectory planning method in this application embodiment can reasonably plan the vehicle's trajectory for driving scenarios that cannot be driven away when using single gear, including but not limited to vehicle U-turns and various escape situations, so that the vehicle can pass smoothly and improve traffic efficiency.
[0132] Optionally, the driving scenario of the first vehicle can be identified, which may include, but is not limited to, the following:
[0133] Scenario 1:
[0134] Identify driving scenarios involving U-turns using multiple gears.
[0135] If the environment in which the first vehicle is located meets the first and second conditions, it is determined that the first vehicle needs to make a U-turn in multiple gears on the first road segment.
[0136] The first condition includes that the first road segment is a U-turn section.
[0137] The second condition includes any one or more of the following: the duration for which the single-gear U-turn space corresponding to the first road segment is insufficient exceeds the first threshold; the duration for which the traffic flow trajectory of the first road segment is a multi-gear trajectory exceeds the second threshold; and the duration for which the single-gear U-turn trajectory corresponding to the first road segment poses a collision risk with an obstacle exceeds the third threshold.
[0138] Optionally, the first threshold, the second threshold, and the third threshold are not fixed values and can be adjusted according to different application scenarios. This application embodiment does not impose any restrictions on this.
[0139] Optionally, the above second condition can be understood as any one or more of the following conditions being met for a certain number of frames: the single-gear U-turn space corresponding to the first road segment is insufficient for a certain number of frames, the traffic flow trajectory of the first road segment is a multi-gear trajectory for a certain number of frames, and the single-gear U-turn trajectory corresponding to the first road segment has a collision risk with an obstacle for a certain number of frames.
[0140] It is understandable that if the environment in which the first vehicle is located meets the first and second conditions mentioned above, it can be assumed that the first vehicle cannot make a U-turn by driving in single gear (such as the driving scenarios shown in Figures 1A and 1B above), and needs to drive in multiple gears to make a U-turn, thereby triggering the next step of multi-gear trajectory planning, so that the first vehicle can make a U-turn smoothly by driving in multiple gears according to the planned trajectory, thereby improving traffic efficiency.
[0141] Scenario 2:
[0142] Identify driving scenarios where multiple gears are used to escape difficult situations.
[0143] If the environment in which the first vehicle is located meets the third and fourth conditions, it is determined that the first vehicle needs to get out of trouble in the second section of the road using multiple gears.
[0144] The third condition includes the duration during which the speed of the first vehicle is below the first threshold exceeding the fourth threshold.
[0145] The fourth condition includes any one or more of the following: the duration for which obstacles exist around the first vehicle continuously exceeds the fifth threshold; the duration for which the single-gear U-turn space corresponding to the second road segment is insufficient continuously exceeds the sixth threshold; and the duration for which the single-gear U-turn trajectory corresponding to the second road segment poses a collision risk with the obstacle continuously exceeds the seventh threshold.
[0146] Optionally, the fourth, fifth, sixth, and seventh thresholds mentioned above are not fixed values and can be adjusted according to different application scenarios. This application embodiment does not impose any restrictions on this.
[0147] Optionally, the fourth condition above can be understood as any one or more of the following conditions being met for a certain number of frames: the presence of obstacles around the first vehicle for a certain number of frames, insufficient space for a single-gear U-turn in the second road segment for a certain number of frames, and a risk of collision between the single-gear U-turn trajectory and the obstacle in the second road segment for a certain number of frames.
[0148] Understandably, if the environment in which the first vehicle is located meets the third and fourth conditions mentioned above, it can be assumed that the first vehicle cannot get out of trouble by driving in single gear and needs to drive in multiple gears to get out of trouble, thereby triggering the next step of multi-gear trajectory planning, so that the first vehicle can get out of trouble smoothly by driving in multiple gears according to the planned trajectory, thus improving traffic efficiency.
[0149] It should be understood that the above two scenarios are merely examples to illustrate the driving scenario in which the first vehicle is located, and should not be construed as limiting the embodiments of this application.
[0150] It should be understood that any new embodiments obtained by reasonable modifications or additions to the above-described situations one and two are all within the protection scope of the embodiments of this application.
[0151] In one possible embodiment, the generation of the planned trajectory based on static and dynamic information in step S302 above can be implemented in ways including but not limited to the following:
[0152] Generate one or more guide lines based on static information.
[0153] Based on dynamic information and one or more guide lines, a planned trajectory is generated.
[0154] Among them, the one or more guide lines include routes that guide the first vehicle to potentially leave the target driving scenario in multiple gears.
[0155] It is understood that in this embodiment, one or more guide lines are first generated based on the static information of the environment in which the first vehicle is located, to guide the first vehicle to leave the target driving scene at multiple gears. However, during the departure process, it may conflict with the movement of dynamic obstacles. Therefore, the dynamic information of the environment in which the first vehicle is located (optionally, and also combined with the static information of the environment in which the first vehicle is located) can be combined to determine the final planned trajectory based on the one or more guide lines generated above. This planned trajectory can be understood as a trajectory optimized by combining dynamic information (optionally, and static information) with the one or more guide lines above, which conforms to vehicle kinematics and is more human-like, resulting in higher traffic efficiency.
[0156] Therefore, as the first vehicle leaves the target driving scenario in multiple gears according to the planned trajectory, it can dynamically interact with dynamic obstacles and change dynamically according to the complex dynamic interaction environment. This can avoid conflicts with the movement trajectory of dynamic obstacles, reduce the probability of the first vehicle getting stuck due to conflict with dynamic obstacles and requiring early manual intervention, ensure the continuity of intelligent driving, and improve traffic efficiency.
[0157] Alternatively, the planned trajectory can also be generated using a network model.
[0158] For example, by inputting the above static and dynamic information into the network model, the network model outputs the above planned trajectory.
[0159] Optionally, the network model can be trained using historical data, including but not limited to historical static information and historical dynamic information and their corresponding generated historical planning trajectories.
[0160] Optionally, the above-mentioned generation of one or more guide lines based on static information can be achieved in ways including but not limited to the following:
[0161] A planning base map is generated based on the road condition information of the road segment where the first vehicle is located.
[0162] Based on the planning base map and constraints, generate one or more guide lines.
[0163] The constraints include one or more of the following: historical traffic flow trajectory constraints, traffic element constraints of the road segment where the first vehicle is located, vehicle kinematic constraints, and static obstacle constraints of the road segment where the first vehicle is located.
[0164] Optionally, the planning base map may include, but is not limited to, occupancy maps, constrained delaunay triangulations (CDT) maps, etc., and the embodiments of this application do not impose any restrictions on this.
[0165] Understandably, based on the planning base map, one or more more human-like guide lines can be generated according to the above constraints. These one or more guide lines take into account the static information of the environment in which the first vehicle is located and the constraints formed by the static information. Thus, the first vehicle may drive away from the target driving scene in multiple gears according to these one or more guide lines. In the process of leaving the target driving scene, it can avoid conflicts with static obstacles, reduce the probability of the first vehicle being stuck due to conflicts with static obstacles and requiring early manual intervention, and ensure the continuity of intelligent driving.
[0166] Optionally, the above-mentioned generation of one or more guide lines based on the planning base map and constraints can employ algorithms such as search, optimization, machine learning, or combinations thereof, such as A* algorithm, hybrid A* algorithm, etc. This application embodiment does not impose any limitations on this.
[0167] Alternatively, one or more guide lines can be generated using a network model.
[0168] For example, the static information described above is input into a network model, which then outputs one or more of the aforementioned guiding lines.
[0169] Optionally, the network model can be trained using historical data, which includes, but is not limited to, historical static information and historical constraints and the one or more historical guide lines generated accordingly.
[0170] Optionally, the above-mentioned generation of the planned trajectory based on dynamic information and one or more guide lines can be achieved in ways including but not limited to the following:
[0171] Based on the motion information of dynamic obstacles in the road segment where the first vehicle is located, the game relationship between the first vehicle and the dynamic obstacles is obtained.
[0172] Based on this game theory relationship and one or more guiding lines, a planned trajectory is generated.
[0173] Optionally, the game relationship may include, but is not limited to: the first vehicle avoiding the dynamic obstacle, the first vehicle passing the dynamic obstacle first, the first vehicle waiting for the dynamic obstacle to pass first and the waiting time being less than a certain threshold, etc., and the embodiments of this application do not limit this.
[0174] Understandably, the final planned trajectory can be determined based on one or more guide lines generated above, based on the game relationship between the first vehicle and the dynamic obstacle (optionally, and based on the position, shape, type, predicted trajectory, etc. of the dynamic obstacle). Since the generated planned trajectory comprehensively considers the dynamic interaction between the first vehicle and the dynamic obstacle, the first vehicle can dynamically interact with the dynamic obstacle as it leaves the target driving scenario in multiple gears according to the planned trajectory. This dynamic interaction adapts to changes in the complex dynamic interaction environment to avoid conflicts with the movement trajectories of the dynamic obstacle, reducing the probability of premature manual intervention due to the first vehicle stopping due to a conflict with the dynamic obstacle, and ensuring the continuity of intelligent driving.
[0175] Optionally, in addition to the game theory relationships mentioned above (optionally, and also based on the location, shape, type, and predicted trajectory of dynamic obstacles), the planned trajectory can also be generated based on the static information mentioned above, the constraints mentioned above (including but not limited to historical traffic flow trajectory constraints, traffic element constraints of the road segment where the first vehicle is located, vehicle kinematic constraints, and static obstacle constraints of the road segment where the first vehicle is located), and one or more guide lines. This planned trajectory can be understood as a trajectory optimized from one or more guide lines by combining dynamic information, static information, and constraints. It conforms to vehicle kinematics and is more human-like, enabling the first vehicle to successfully escape difficulties by driving in multiple gears along the planned trajectory, thus improving traffic efficiency.
[0176] Therefore, for scenarios including but not limited to vehicle U-turns and various obstacle avoidance situations, the vehicle's trajectory can be rationally planned to ensure smooth passage and improve traffic efficiency.
[0177] Alternatively, the game relationship between the first vehicle and dynamic obstacles can be generated through a network model.
[0178] For example, by inputting the aforementioned dynamic information and one or more guiding lines into a network model, the network model outputs the aforementioned game relationship.
[0179] Optionally, the network model can be trained using historical data, including but not limited to historical dynamic information and historical guiding lines and their corresponding historical game relationships.
[0180] Optionally, the generated planned trajectory can also carry speed information.
[0181] The speed information includes the speed of the first vehicle on each segment of the planned trajectory. The first vehicle can leave the target driving scene at multiple speeds according to the planned trajectory.
[0182] Optionally, this speed information can be obtained based on the aforementioned game theory relationship.
[0183] For example, when a certain segment of the planned trajectory corresponds to a game relationship where the first vehicle passes before the dynamic obstacle, the speed of that segment of the trajectory is relatively fast.
[0184] For example, when a certain segment of the planned trajectory corresponds to a game relationship where the first vehicle avoids a dynamic obstacle, the speed of that segment is relatively slow.
[0185] Optionally, the planned trajectory carrying speed information obtained based on the game relationship between the first vehicle and the dynamic obstacle can be obtained by using optimization, artificial intelligence (AI) algorithms or combinations thereof. This application embodiment does not limit this.
[0186] Understandably, based on the game relationship between the first vehicle and the dynamic obstacle, a planned trajectory carrying speed information can be obtained. Thus, as the first vehicle drives away from the target driving scene at multiple speeds according to the planned trajectory, it can avoid conflicts with the movement trajectories of the dynamic obstacle, reduce the probability of the first vehicle being stuck due to a conflict with the dynamic obstacle, and ensure the continuity of intelligent driving.
[0187] Optionally, in addition to the aforementioned game theory relationships (optionally, and based on the position, shape, type, and predicted trajectory of dynamic obstacles), the speed information can also be generated based on the aforementioned static information and constraints (including but not limited to historical traffic flow trajectory constraints, traffic element constraints of the road segment where the first vehicle is located, vehicle kinematic constraints, and static obstacle constraints of the road segment where the first vehicle is located). The planned trajectory carrying this speed information can be understood as an optimization of the aforementioned planned trajectory by combining dynamic information, static information, and constraints, enabling the first vehicle to smoothly leave the target driving scenario at multiple speed levels according to the planned trajectory, thereby improving traffic efficiency.
[0188] Optionally, if the planned trajectory fails to be generated through the above optimization, the constraints can be relaxed and the planned trajectory can be regenerated. This allows the first vehicle to refresh its planned trajectory when a dynamic obstacle with interactive actions obscures the first vehicle's movement trajectory. The first vehicle can then stably provide a turning or escape trajectory by means of slow braking, temporary stopping, or obstacle avoidance, and complete the predetermined movement goal after avoiding the obscured dynamic obstacle.
[0189] Optionally, due to limitations in sensor range or actual wall / obstacle occlusion in real-world scenarios, the initially generated planned trajectories may not all be feasible trajectories. Based on the above trajectory planning method, constraints can be relaxed and replanned to ensure the effectiveness of trajectory planning.
[0190] In one possible embodiment, the trajectory planning method described above may also perform the following steps, including but not limited to:
[0191] The generated planning trajectory is displayed.
[0192] Optionally, the planned trajectory can be displayed through devices including but not limited to vehicle-mounted displays.
[0193] Optionally, the above-mentioned multi-gear planning trajectory including reverse gear can be presented in stages for each segment of the trajectory corresponding to each gear, or in stages for each segment of the trajectory corresponding to each gear. This application embodiment does not limit this.
[0194] Optionally, the above-mentioned multi-gear planning trajectory including reverse gear may have different or the same display color for the trajectory corresponding to different gears, and this application embodiment does not limit this.
[0195] Understandably, if the driver can promptly learn that the first vehicle is unable to leave the target driving scenario while driving in single gear, it intends to leave the target driving scenario in multiple gears according to the displayed planned trajectory. The driver can also intervene in a timely manner to pause or terminate the first vehicle's multi-gear movement, thereby improving the driver's intelligent driving perception and controllability of the first vehicle and ensuring driving safety.
[0196] In one possible embodiment, the trajectory planning method described above may also perform the following steps, including but not limited to:
[0197] This shows the game-like relationship between the first vehicle and dynamic obstacles.
[0198] Optionally, the game relationship between the first vehicle and the dynamic obstacle can be displayed through devices including but not limited to vehicle-mounted displays.
[0199] Understandably, the driver can promptly learn about the interaction intentions between the first vehicle and dynamic obstacles as the first vehicle leaves the target driving scenario in multiple gears according to the displayed planned trajectory. Specifically, the driver can determine whether to avoid the dynamic obstacle or pass it first. The driver can also intervene in a timely manner to pause or terminate the interaction between the first vehicle and the dynamic obstacle, thereby improving the driver's intelligent driving perception and controllability of the first vehicle and ensuring the driving safety of the vehicle.
[0200] In one possible embodiment, the trajectory planning method described above may also perform the following steps, including but not limited to:
[0201] Control the first vehicle to drive away from the target driving scenario according to the planned trajectory.
[0202] Understandably, for driving scenarios where vehicles cannot leave when using single gear, including but not limited to U-turns and various escaping situations, the vehicle's trajectory can be rationally planned to control the first vehicle to leave the target driving scenario according to the planned trajectory, enabling vehicles to pass smoothly and improving traffic efficiency.
[0203] Optionally, when controlling the first vehicle to drive away from the target driving scenario in reverse along the planned trajectory, a prompt message can also be issued.
[0204] Optionally, the prompt information may include, but is not limited to, voice broadcast, reversing image, reversing prompt sound, etc., and this application embodiment does not limit this.
[0205] Understandably, when controlling the first vehicle to reverse away from the target driving scenario according to the planned trajectory, a prompt message can also be issued to alert the driver or surrounding vehicles and pedestrians that the vehicle is reversing. This can increase the attention of all parties to the vehicle reversing and ensure driving safety.
[0206] Optionally, after controlling the first vehicle to leave the target driving scenario in multiple gears according to the planned trajectory, the first vehicle can be controlled to enter normal cruise mode and continue normal driving in single gear.
[0207] Optionally, the trajectory planning method in the embodiments of this application can also be described in conjunction with the driving scenarios shown in Figures 1B and 2 above.
[0208] For details, please refer to Figure 4, which is a schematic diagram of a trajectory planning scenario provided by an embodiment of this application.
[0209] As shown in Figure 4, for scenarios where a U-turn cannot be achieved by driving in single gear, a multi-gear planning trajectory can be generated based on the trajectory planning method described above. This planning trajectory includes at least continuous trajectories A, B, and C.
[0210] In this diagram, trajectory A corresponds to the forward gear, trajectory B corresponds to the reverse gear, and trajectory C corresponds to the forward gear.
[0211] Understandably, in scenarios where the first vehicle cannot make a U-turn while driving in single gear, the first vehicle can make a U-turn smoothly by driving in multiple gears according to the planned trajectory, which includes at least continuous trajectories A, B, and C, thereby improving traffic efficiency.
[0212] Optionally, the planned trajectory can be displayed through devices including but not limited to vehicle-mounted displays.
[0213] Optionally, the above-mentioned trajectories A, B, and C can be presented in segments at different times or simultaneously. This application embodiment does not impose any restrictions on this.
[0214] Optionally, the display colors of the tracks A, B, and C at different gear levels can be different or the same, and this application embodiment does not impose any restrictions on this.
[0215] For example, tracks A and C (both in forward gear) are displayed in red, while track B (in reverse gear) is displayed in blue.
[0216] For further details, please refer to Figure 5, which is a schematic diagram of another trajectory planning scenario provided by an embodiment of this application.
[0217] As shown in Figure 5, for scenarios where it is impossible to start and get out of trouble on the roadside using a single gear, a multi-gear planning trajectory can be generated based on the trajectory planning method mentioned above. This planning trajectory includes at least continuous trajectories D and E.
[0218] In this context, trajectory D corresponds to the reverse gear, and trajectory E corresponds to the forward gear.
[0219] Understandably, in scenarios where the first vehicle cannot start and escape from a roadside stalemate by driving in single gear, the first vehicle can start and escape from a stalemate by driving in multiple gears according to the planned trajectory, which includes at least continuous trajectories D and E, thereby improving traffic efficiency.
[0220] Optionally, the planned trajectory can be displayed through devices including but not limited to vehicle-mounted displays.
[0221] Optionally, the above-mentioned trajectories D and E can be presented in segments at different times or in segments simultaneously. This application embodiment does not impose any restrictions on this.
[0222] Optionally, the display colors of the tracks D and E corresponding to different gear levels can be different or the same, and this application embodiment does not impose any restrictions on this.
[0223] For example, track D (reverse gear) is displayed in blue, and track E (forward gear) is displayed in red.
[0224] Optionally, for scenarios where starting from the roadside and getting out of trouble cannot be achieved by driving in a single gear, a multi-gear planning trajectory can be generated based on the trajectory planning method described above. This planning trajectory includes at least continuous trajectories F and G.
[0225] In this context, trajectory F corresponds to the forward gear, and trajectory G corresponds to the reverse gear.
[0226] It is understandable that, in the scenario where the first vehicle cannot start and get out of trouble on the roadside when driving in a single gear, the first vehicle can start and get out of trouble smoothly by driving in multiple gears according to the planned trajectory which includes at least continuous trajectories F and G, thereby improving traffic efficiency.
[0227] The methods of the embodiments of this application have been described in detail above. The following provides an apparatus for implementing any one of the methods in the embodiments of this application. For example, an apparatus is provided that includes a unit (or means) for implementing the steps performed by the device in any of the above methods.
[0228] Please refer to Figure 6, which is a schematic diagram of the structure of a trajectory planning device provided in an embodiment of this application.
[0229] As shown in Figure 6, the trajectory planning device 60 may include a communication unit 601 and a processing unit 602. The communication unit 601 and the processing unit 602 may be software, hardware, or a combination of both.
[0230] The communication unit 601 can implement sending and / or receiving functions, and can also be described as a transceiver unit. The communication unit 601 can also be a unit integrating an acquisition unit and a sending unit, wherein the acquisition unit is used to implement the receiving function, and the sending unit is used to implement the sending function. Optionally, the communication unit 601 can be used to receive information sent by other devices, and can also be used to send information to other devices.
[0231] In one possible design, the trajectory planning device 60 may correspond to the trajectory planning device in the method embodiment shown in FIG3 above. For example, the trajectory planning device 60 may be an electronic device or a chip within an electronic device. The trajectory planning device 60 may include units for performing the operations performed by the trajectory planning device in the method embodiment shown in FIG3 above, and each unit in the trajectory planning device 60 is for implementing the operations performed by the trajectory planning device in the method embodiment shown in FIG3 above. The descriptions of each unit are as follows:
[0232] The processing unit 602 is used to acquire static and dynamic information of the environment in which the first vehicle is located. The static information includes road condition information of the road segment in which the first vehicle is located, and the dynamic information includes motion information of dynamic obstacles in the road segment in which the first vehicle is located.
[0233] The processing unit 602 is also used to generate a planned trajectory based on static information and dynamic information; wherein the planned trajectory includes at least a first trajectory and a second trajectory, the gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory, the planned trajectory is used to instruct the first vehicle to leave the target driving scene in multiple gears, and the planned trajectory does not conflict with the movement trajectory of the dynamic obstacle.
[0234] In one possible implementation, the device further includes a communication unit 601.
[0235] The processing unit 602 is specifically used to obtain static and dynamic information of the environment in which the first vehicle is located through the communication unit 601.
[0236] Regarding the communication unit 601 and processing unit 602 described in this design, the steps they perform can be referred to the implementation method corresponding to the trajectory planning device in the method embodiment shown in Figure 3 above.
[0237] Regarding the technical effects of the implementation methods performed by the communication unit 601 and the processing unit 602 described in this design, please refer to the description of the technical effects corresponding to the method embodiment shown in FIG3 above.
[0238] According to embodiments of this application, the various units in the device shown in FIG6 can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effect of the embodiments of this application. The above units are based on logical function division. In practical applications, the function of one unit can also be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the electronic device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.
[0239] It should be noted that the implementation of each unit can also refer to the corresponding description of the method embodiment shown in Figure 3 above.
[0240] In the trajectory planning device 60 described in Figure 6, the trajectory of the vehicle can be reasonably planned for vehicle U-turns and various escape scenarios, so that the vehicle can pass smoothly and improve traffic efficiency.
[0241] If the trajectory planning device 60 mentioned above can be an electronic device, please refer to the structural schematic diagram of the electronic device shown in Figure 7.
[0242] It should be understood that the electronic device 70 shown in FIG7 is only an example. The electronic device in the embodiments of this application may also include other components, or include components with functions similar to the various components in FIG7, or may not include all the components in FIG7.
[0243] Electronic device 70 includes a transceiver interface 701 and at least one processor 702.
[0244] The electronic device 70 can correspond to a trajectory planning device. The transceiver interface 701 is used for transmitting and receiving signals, and at least one processor 702 executes program instructions, causing the electronic device 70 to implement the corresponding process of the method executed by the corresponding device in the above method embodiments.
[0245] In one possible design, the electronic device 70 may correspond to the trajectory planning device in the method embodiment shown in FIG3 above. For example, the electronic device 70 may be a trajectory planning device or a chip within the trajectory planning device. The electronic device 70 may include components for performing the operations performed by the trajectory planning device in the above method embodiment, and each component in the electronic device 70 is specifically designed to implement the operations performed by the trajectory planning device in the above method embodiment. Specifically, it may be as follows:
[0246] The processor 702 is used to acquire static and dynamic information of the environment in which the first vehicle is located. The static information includes road condition information of the road segment in which the first vehicle is located, and the dynamic information includes motion information of dynamic obstacles in the road segment in which the first vehicle is located.
[0247] The processor 702 is also used to generate a planned trajectory based on static and dynamic information; wherein the planned trajectory includes at least a first trajectory and a second trajectory, the gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory, the planned trajectory is used to instruct the first vehicle to leave the target driving scene in multiple gears, and the planned trajectory does not conflict with the movement trajectory of the dynamic obstacle.
[0248] In one possible implementation, the electronic device further includes a transceiver interface 701.
[0249] The processor 702 is specifically used to obtain static and dynamic information about the environment in which the first vehicle is located through the transceiver interface 701.
[0250] Regarding the transceiver interface 701 and at least one processor 702 described in this design, the steps they perform can be referred to the implementation corresponding to the trajectory planning device in the method embodiment shown in Figure 3 above.
[0251] For the technical effects of the implementation methods performed by the transceiver interface 701 and at least one processor 702 described in this design, please refer to the description of the technical effects corresponding to the method embodiment shown in FIG3 above.
[0252] In the electronic device 70 described in Figure 7, the trajectory of the vehicle can be reasonably planned for vehicle U-turns and various escape scenarios, so that the vehicle can pass smoothly and improve traffic efficiency.
[0253] If the trajectory planning device 60 mentioned above can be a chip or a chip system, please refer to the schematic diagram of the chip structure shown in Figure 8.
[0254] As shown in Figure 8, chip 80 includes a processor 801 and an interface 802. The number of processors 801 can be one or more, and the number of interfaces 802 can be multiple. It should be noted that the functions of the processor 801 and interface 802 can be implemented through hardware design, software design, or a combination of both; no restrictions are placed here.
[0255] Optionally, chip 80 may also include memory 803 for storing necessary program instructions and data.
[0256] In this application, processor 801 can be used to call the implementation program of the trajectory planning method provided in one or more embodiments of this application in a trajectory planning device from memory 803, and execute the instructions included in the program. Interface 802 can be used to output the execution result of processor 801. In this application, interface 802 can be specifically used to output various messages or information of processor 801.
[0257] For the trajectory planning method provided by one or more embodiments of this application, please refer to the various embodiments shown in Figure 3 above, which will not be repeated here.
[0258] The processor in this application embodiment can be a central processing unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.
[0259] The memory in this application embodiment is used to provide storage space, in which data such as operating system and computer programs can be stored. The memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).
[0260] According to the method provided in the embodiments of this application, the embodiments of this application also provide a computer-readable storage medium storing a computer program. When the computer program is run on one or more processors, it can implement the method shown in FIG3.
[0261] According to the method provided in the embodiments of this application, the embodiments of this application also provide a computer program product, which includes a computer program. When the computer program runs on a processor, it can implement the method shown in FIG3.
[0262] According to the method provided in the embodiments of this application, the embodiments of this application also provide a trajectory planning system, which includes: a trajectory planning device and a first vehicle; wherein, the trajectory planning device is used to execute the method executed by the trajectory planning device above to control the movement of the first vehicle.
[0263] This application also provides a terminal, which includes at least one trajectory planning device 60, or electronic device 70, or chip 80.
[0264] Optionally, the terminal can be a means of transportation, such as a car, truck, aircraft, drone, slow transport vehicle, spacecraft, or ship, or any other possible means of transportation used in any possible scenario. This application embodiment does not limit this.
[0265] Optionally, the terminal is used to implement the method shown in Figure 3 above.
[0266] This application also provides a processing apparatus, including a processor and an interface; the processor is used to execute the method in any of the above method embodiments.
[0267] It should be understood that the above-described processing device can be a chip. The units in the various device embodiments and the electronic devices in the method embodiments correspond completely, with corresponding modules or units executing corresponding steps. For example, the communication unit (transceiver) executes the receiving or sending steps in the method embodiments, while other steps besides sending and receiving can be executed by the processing unit (processor). The specific functions of each unit can be found in the corresponding method embodiments. There can be one or more processors.
[0268] It is understood that in the embodiments of this application, the electronic device may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to perform all the operations in the embodiments of this application.
[0269] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0270] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0271] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0272] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the contributing part, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0273] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A trajectory planning method, characterized in that, Applied to the first vehicle, the trajectory planning method includes: The static and dynamic information of the environment in which the first vehicle is located are obtained. The static information includes the road condition information of the road segment in which the first vehicle is located, and the dynamic information includes the motion information of dynamic obstacles in the road segment in which the first vehicle is located. Based on the static information and the dynamic information, a planned trajectory is generated; wherein, the planned trajectory includes at least a first trajectory and a second trajectory, the gear corresponding to the first trajectory is different from the gear corresponding to the second trajectory, the planned trajectory is used to instruct the first vehicle to leave the target driving scene in multiple gears, and the planned trajectory does not conflict with the movement trajectory of the dynamic obstacle.
2. The trajectory planning method according to claim 1, characterized in that, The step of generating a planned trajectory based on the static information and the dynamic information includes: Identify the driving scenario in which the first vehicle is located; When the first vehicle is in the target driving scenario, the planned trajectory is generated based on the static information and the dynamic information. The target driving scenario includes driving scenarios that cannot be left when driving in single gear.
3. The trajectory planning method according to claim 2, characterized in that, The identification of the driving scenario of the first vehicle includes: If the environment in which the first vehicle is located meets the first condition and the second condition, the system identifies that the first vehicle needs to make a U-turn in multiple gears on the first road segment. The first condition includes that the first road segment is a U-turn segment, and the second condition includes any one or more of the following: the duration for which the single-gear U-turn space corresponding to the first road segment is insufficient exceeds a first threshold; the duration for which the traffic flow trajectory of the first road segment is a multi-gear trajectory exceeds a second threshold; and the duration for which the single-gear U-turn trajectory corresponding to the first road segment has a collision risk with an obstacle exceeds a third threshold.
4. The trajectory planning method according to claim 2, characterized in that, The identification of the driving scenario of the first vehicle includes: If the environment in which the first vehicle is located meets the third and fourth conditions, it is identified that the first vehicle needs to get out of trouble in the second road section using multiple gears; The third condition includes the duration for which the speed of the first vehicle is below the first threshold continuously exceeds the fourth threshold. The fourth condition includes any one or more of the following: the duration for which there are obstacles around the first vehicle continuously exceeds the fifth threshold; the duration for which the single-gear U-turn space corresponding to the second road segment is insufficient continuously exceeds the sixth threshold; and the duration for which the single-gear U-turn trajectory corresponding to the second road segment poses a collision risk with the obstacle continuously exceeds the seventh threshold.
5. The trajectory planning method according to any one of claims 1 to 4, characterized in that, The step of generating a planned trajectory based on the static information and the dynamic information includes: Based on the static information, one or more guide lines are generated, and the one or more guide lines include routes that may guide the first vehicle to leave the target driving scenario in multiple gears; The planned trajectory is generated based on the dynamic information and the one or more guide lines.
6. The trajectory planning method according to claim 5, characterized in that, The step of generating one or more guide lines based on the static information includes: Based on the road condition information of the road segment where the first vehicle is located, a planning base map is generated; Based on the planning base map and constraints, one or more guide lines are generated; wherein the constraints include any one or more of the following: historical traffic flow trajectory constraints, traffic element constraints of the road segment where the first vehicle is located, vehicle kinematic constraints, and static obstacle constraints of the road segment where the first vehicle is located.
7. The trajectory planning method according to claim 5, characterized in that, The step of generating the planned trajectory based on the dynamic information and the one or more guide lines includes: Based on the motion information of the dynamic obstacles in the road segment where the first vehicle is located, the game relationship between the first vehicle and the dynamic obstacles is obtained. The planned trajectory is generated based on the game relationship and the one or more guiding lines.
8. The trajectory planning method according to claim 7, characterized in that, The planned trajectory carries speed information, which is obtained based on the game relationship. The speed information includes the speed of the first vehicle traveling on each segment of the planned trajectory.
9. The trajectory planning method according to any one of claims 1 to 8, characterized in that, The planned trajectory includes at least three consecutive trajectories: trajectory A, trajectory B, and trajectory C. Wherein, the gear corresponding to trajectory A is forward gear, the gear corresponding to trajectory B is reverse gear, and the gear corresponding to trajectory C is forward gear.
10. The trajectory planning method according to any one of claims 1 to 8, characterized in that, The planned trajectory includes at least two continuous trajectories, D and E; Wherein, the gear corresponding to trajectory D is reverse gear, and the gear corresponding to trajectory E is forward gear.
11. The trajectory planning method according to any one of claims 1 to 10, characterized in that, The trajectory planning method also includes: The planned trajectory is displayed.
12. The trajectory planning method according to any one of claims 1 to 11, characterized in that, The trajectory planning method also includes: This displays the game-theoretic relationship between the first vehicle and the dynamic obstacle.
13. The trajectory planning method according to any one of claims 1 to 12, characterized in that, The trajectory planning method also includes: Control the first vehicle to leave the target driving scenario according to the planned trajectory.
14. The trajectory planning method according to any one of claims 1 to 13, characterized in that, The trajectory planning method also includes: When controlling the first vehicle to drive away from the target driving scenario in reverse along the planned trajectory, a prompt message is issued.
15. A trajectory planning device, characterized in that, Includes units for performing the method as described in any one of claims 1 to 14.
16. A trajectory planning device, characterized in that, Includes a processor for performing the method as described in any one of claims 1 to 14.
17. A chip, characterized in that, It includes logic circuits and interfaces, wherein the logic circuits and the interfaces are coupled; The interface is used for inputting and / or outputting information, and the logic circuit is used for performing the method as described in any one of claims 1 to 14.
18. A terminal, characterized in that, Includes the trajectory planning device as described in claim 15, or the trajectory planning device as described in claim 16, or the chip as described in claim 17.
19. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed, performs the method as described in any one of claims 1 to 14.
20. A computer program product, characterized in that, The computer program product includes a computer program, which, when executed, performs the method as described in any one of claims 1 to 14.