Trajectory determination method, apparatus, device, and autonomous vehicle
By combining deep learning models and perception data, and utilizing target interaction conditions and historical intent ratios, the trajectory of obstacles can be accurately predicted, solving the safety issues in scenarios where obstacles cross pedestrian crossings or turn towards exit lanes, and improving the safety and responsiveness of autonomous vehicles.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING BAIDU NETCOM SCI & TECH CO LTD
- Filing Date
- 2023-01-31
- Publication Date
- 2026-06-16
AI Technical Summary
Existing technologies struggle to accurately predict the intentions of obstacles when determining their trajectories, especially when they cross pedestrian crossings or turn toward exit lanes, thus jeopardizing vehicle safety.
By combining trained deep learning or machine learning models with perception data and vehicle status data, the future trajectory of obstacles can be determined. By utilizing target interaction conditions such as crossing a pedestrian crossing or turning towards an exit lane, and combining historical intent ratios and spline interpolation, the trajectory of obstacles can be accurately predicted.
It improves the accuracy and timeliness of obstacle trajectory prediction, enhancing the safety and responsiveness of autonomous vehicles in complex scenarios.
Smart Images
Figure CN122219447A_ABST
Abstract
Description
[0001] This disclosure is a divisional application. The parent application number is 202310119127.4, the parent application date is January 31, 2023, and the parent invention is entitled "Trajectory Determination Method, Apparatus, Device and Autonomous Vehicle". Technical Field
[0002] This disclosure relates to the field of computer technology, and more particularly to the fields of autonomous driving and intelligent transportation technology, specifically to a trajectory determination method, apparatus, device, storage medium, program product, and autonomous vehicle. Background Technology
[0003] Autonomous driving is an application branch of artificial intelligence technology. How to improve vehicle driving safety by determining the movement trajectory of obstacles is a major challenge we are currently facing.
[0004] When determining the planned trajectory of a vehicle, the movement trajectory of obstacles needs to be considered. For example, obstacles crossing pedestrian crossings or turning can affect vehicle driving safety. How to improve vehicle driving safety by predicting the movement trajectory of obstacles is a technical problem that urgently needs to be solved. Summary of the Invention
[0005] This disclosure provides a trajectory determination method, apparatus, device, storage medium, program product, and autonomous vehicle.
[0006] According to one aspect of this disclosure, a trajectory determination method is provided, comprising: determining a target obstacle that satisfies target interaction conditions with the target vehicle based on perception data of the target vehicle. The target interaction conditions include at least one of a first interaction condition and a second interaction condition, wherein the first interaction condition characterizes a scenario where the obstacle crosses a pedestrian crossing, and the second interaction condition characterizes a scenario where the obstacle turns toward an exit lane. Based on obstacle state data of the target obstacle and vehicle state data of the target vehicle, the motion trajectory of the obstacle for a future target time period is determined.
[0007] According to another aspect of this disclosure, a trajectory determination device is provided, comprising: a target obstacle determination module, configured to determine a target obstacle that satisfies target interaction conditions with the target vehicle based on perception data of a target vehicle, the target interaction conditions including at least one of a first interaction condition and a second interaction condition, the first interaction condition representing a scenario where the obstacle crosses a pedestrian crossing, and the second interaction condition representing a scenario where the obstacle turns toward an exit lane; and a motion trajectory determination module, configured to determine the motion trajectory of the target obstacle for a future target time period based on obstacle state data of the target obstacle and vehicle state data of the target vehicle.
[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the methods of embodiments of this disclosure.
[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods of embodiments of this disclosure.
[0010] According to another aspect of this disclosure, a computer program product is provided, including a computer program stored on at least one of a readable storage medium and an electronic device, wherein the computer program, when executed by a processor, implements the methods of embodiments of this disclosure.
[0011] According to another aspect of this disclosure, an autonomous vehicle is provided, including electronic devices according to embodiments of this disclosure.
[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0013] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:
[0014] Figure 1 A schematic diagram illustrating the system architecture of a trajectory determination method and apparatus according to embodiments of the present disclosure is shown.
[0015] Figure 2 A flowchart illustrating a trajectory determination method according to an embodiment of the present disclosure is shown schematically.
[0016] Figure 3A A schematic diagram of a trajectory determination method according to another embodiment of the present disclosure is shown;
[0017] Figure 3B The diagram illustrates a target obstacle that meets the first interaction condition in multiple historical video frames.
[0018] Figure 3C A schematic diagram of a trajectory determination method according to yet another embodiment of the present disclosure is shown;
[0019] Figure 4 A schematic diagram of a trajectory determination method according to yet another embodiment of the present disclosure is shown;
[0020] Figure 5 A block diagram of a trajectory determination apparatus according to an embodiment of the present disclosure is schematically shown; and
[0021] Figure 6 A block diagram of an electronic device that can implement the trajectory determination method of embodiments of the present disclosure is shown schematically. Detailed Implementation
[0022] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.
[0024] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.
[0025] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).
[0026] Autonomous driving is an application branch of artificial intelligence technology. How to improve vehicle driving safety by determining the movement trajectory of obstacles is a major challenge we are currently facing.
[0027] When determining the planned trajectory of a vehicle, the movement trajectory of obstacles needs to be considered. For example, scenarios such as obstacles crossing pedestrian crossings or turning towards exit lanes all affect vehicle driving safety. How to improve vehicle driving safety by predicting the movement trajectory of obstacles is a technical problem that urgently needs to be solved.
[0028] Some implementations predict the trajectory of obstacles using trained deep learning or machine learning models. However, this approach relies on model performance; for example, uncontrollable model behavior may result in the given obstacle trajectory failing to accurately represent the obstacle's intent. This is especially true in scenarios involving obstacle turning, such as when an obstacle crosses a pedestrian crossing or turns towards an exit lane. Failure to predict the obstacle's intent accurately in a timely manner poses a significant threat to vehicle safety.
[0029] Figure 1 The schematic illustration shows the system architecture of a trajectory determination method and apparatus according to an embodiment of the present disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.
[0030] like Figure 1 As shown, the application scenario 100 of this disclosure includes multiple vehicles 101, 102, and 103, and a server 104. Vehicles 101, 102, and 103 can be autonomous vehicles.
[0031] In one embodiment, vehicles 101, 102, and 103 can interact with server 104. For example, vehicles 101, 102, and 103 can transmit sensing data to server 104, which can then perform calculations based on the sensing data to obtain the trajectory of the obstacle. The current vehicle can be any one of vehicles 101, 102, and 103.
[0032] In another example, vehicles 101, 102, and 103 can perform data processing. Specifically, the vehicle's infotainment system can have data processing capabilities, allowing it to perform calculations based on the information provided by the vehicle to obtain the trajectory of the obstacle.
[0033] For example, the vehicle includes electronic devices, which include, but are not limited to, vehicle infotainment systems. These electronic devices can perform the trajectory determination method according to embodiments of this disclosure. The vehicle infotainment system may include a chassis-based drive-by-wire system.
[0034] The vehicle can be an autonomous vehicle.
[0035] It should be understood that Figure 1 The number of vehicles and servers shown is merely illustrative. Any number of vehicles and servers can be used depending on implementation needs.
[0036] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0037] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.
[0038] This disclosure provides a trajectory determination method, which is described below in conjunction with... Figure 1 The system architecture, referencing Figures 2-4 This describes a trajectory determination method according to exemplary embodiments of the present disclosure. The trajectory determination method of the embodiments of the present disclosure may, for example, be derived from... Figure 1 The server 104 shown is used to execute this.
[0039] Figure 2 A flowchart illustrating a trajectory determination method according to an embodiment of the present disclosure is shown schematically.
[0040] like Figure 2 As shown, the trajectory determination method 200 of this embodiment may include, for example, operations S210 to S220.
[0041] In operation S210, based on the perception data of the target vehicle, target obstacles that meet the target interaction conditions with the target vehicle are identified.
[0042] The perception data of the target vehicle can be obtained, for example, by image acquisition devices, radar, and other components installed on the target vehicle. The surrounding environment of the target vehicle can be obtained through the perception data of the target vehicle.
[0043] Target interaction conditions, for example, characterize the conditions under which there is an interaction risk between the target vehicle and the obstacle, such as the risk of collision between the target obstacle and the target vehicle.
[0044] The target interaction condition includes at least one of a first interaction condition and a second interaction condition. The first interaction condition represents a scenario where an obstacle crosses a pedestrian crossing, and the second interaction condition represents a scenario where an obstacle turns toward an exit lane.
[0045] In operation S220, the movement trajectory of the obstacle in the future target time period is determined based on the obstacle status data of the target obstacle and the vehicle status data of the target vehicle.
[0046] The future time period could be, for example, 8 seconds from the current moment.
[0047] According to the trajectory determination method of this disclosure, target obstacles that meet the target interaction conditions with the target vehicle can be accurately determined by using the perception data of the target vehicle. When determining the trajectory of the obstacle over a future target time period, in addition to using the obstacle's state data as a factor in determining its trajectory, the target vehicle's state data is also used. This ensures that the obstacle's trajectory over the future target time period is an accurate trajectory indicating a potential collision risk with the target vehicle within that time period.
[0048] For example, target control data for controlling the driving of the target vehicle can be determined based on the movement trajectory of the obstacle over a future target time period and the vehicle state data of the target vehicle. By using the target control data to control the driving of the target vehicle, the target vehicle can use the future target time period as a buffer time to make decisions such as trajectory planning to avoid collisions with the target obstacle, thereby improving the safety of autonomous driving.
[0049] According to the trajectory determination method of this disclosure, by using target interaction conditions such as first interaction conditions and second interaction conditions, the accurate target obstacle and the trajectory of the target obstacle can be determined by the target vehicle in scenarios where the obstacle crosses a pedestrian crossing or the obstacle turns towards the exit lane, using accurate logical processing. The target vehicle can then respond accurately (accurately reflected in the accurate trajectory) and promptly (based on the buffer time of the future target time period) to perform trajectory planning. With the corresponding model prediction method, the target interaction conditions can be set according to requirements, and the logic of the target interaction conditions is more explicit and has higher controllability, making it suitable for scenarios with higher requirements for the target vehicle's driving safety and driving response speed, such as when the obstacle crosses a pedestrian crossing or the obstacle turns towards the exit lane.
[0050] Figure 3A A schematic diagram of a trajectory determination method according to another embodiment of the present disclosure is shown.
[0051] like Figure 3AAs shown, according to another embodiment of the trajectory determination method of this disclosure, when the target interaction conditions include a first interaction condition, the following specific example can be used to determine a target obstacle that satisfies the target interaction conditions with the target vehicle based on the target vehicle's perception data: Based on map perception data, a target pedestrian crossing located in the target vehicle's driving direction and satisfying a first distance threshold with respect to the target vehicle's current position is determined. Based on obstacle perception data, obstacles that satisfy a first angle range with respect to the lane direction of the target vehicle and a second distance threshold with respect to the boundary along the lane direction are determined as candidate obstacles. Based on the candidate obstacles and the intention masking condition, the target obstacle is determined.
[0052] The perception data includes map perception data and obstacle perception data.
[0053] The first interaction condition characterizes the obstacle's intention to cross the target pedestrian crossing. This first interaction condition is related to a first distance threshold, a second distance threshold, a first angle range, and an intention masking condition. The intention masking condition characterizes the candidate obstacle's intention to move away from the target pedestrian crossing.
[0054] exist Figure 3A The example schematically shows the target vehicle Vt, the target pedestrian crosswalk, obstacles Obs-1 and Obs-2, and the lower boundary Obs of obstacle Obs-1. s The upper boundary of the target pedestrian crossing CrossWalk along the longitudinal direction S is also schematically shown. s , lower boundary start s , along the left boundary Cross Walk-R2 and the right boundary Cross Walk-R1 of the horizontal R. Figure 3A An example of the angle α1 between obstacle Obs-1 and the lane direction S of the target vehicle Vt is also shown.
[0055] For example, the first distance threshold can be in the range of 50m-120m.
[0056] The second distance threshold can be taken in the range of 3m-10m. Taking a second distance threshold of 5m as an example, obstacles that meet the second distance threshold can be characterized by the following formula (1):
[0057] start s -5< Obs s <end s +5 (1)
[0058] For example, the first angle range can be, for instance, 40° to 140°. An obstacle satisfying the first angle range can be characterized, for example, by the following formula (2):
[0059] 40°<|α1|<140° (2)
[0060] For example, the intention masking condition can also be characterized by the following formulas (3) and (4):
[0061] Obs s >end s And |α1|<90° (3)
[0062] Obs s <end s And |α1|>90° (4)
[0063] According to the trajectory determination method of this disclosure, the first interaction condition is for the scenario of an obstacle crossing a pedestrian crossing. The first interaction condition can characterize a clear logical condition indicating whether the obstacle intends to cross the pedestrian crossing, thus offering higher controllability. By using map perception data, a target pedestrian crossing located in the driving direction of the target vehicle and satisfying a first distance threshold with respect to the target vehicle's current position is determined, making the determined target pedestrian crossing an obstacle that affects the target vehicle's driving safety in the future. By using obstacle perception data, a first angle range, a second distance threshold, and an intent masking condition, the conditions for the obstacle's intention to cross the pedestrian crossing can be comprehensively and accurately expressed from dimensions such as distance, angle, and intent. Through the first interaction condition, target obstacles with the intention to cross the target pedestrian crossing can be accurately and efficiently determined. The target obstacle has a higher risk of collision with the target vehicle in the future, and the motion trajectory determined based on the target obstacle can be used as a reference for the target vehicle's planned trajectory.
[0064] For example, the trajectory determination method according to another embodiment of the present disclosure further includes: updating the target obstacle based on the proportion of historical travel intentions.
[0065] For example, target obstacles can be updated by filtering out those with a historical traversal intent ratio that is less than a set threshold.
[0066] The historical traversal intention ratio is M / N, where N represents the number of historical video frames related to the target obstacle, and M represents the number of historical video frames corresponding to the target obstacle that satisfies the first interaction condition.
[0067] For example, this can also be achieved by tracking the motion trajectory (position and direction) of 10 recent, consecutive historical video frames of the target obstacle. If there are 10 consecutive historical video frames in which the target obstacle moves laterally toward the target pedestrian crossing and its velocity direction gradually moves toward the target pedestrian crossing, then it can be determined that the target obstacle has the intention to cross the target pedestrian crossing.
[0068] For example, the historical travel intent ratio can be in the range of 0.6-1, and N can be in the range of 3-15.
[0069] According to the trajectory determination method of this disclosure, by updating the target obstacle based on the proportion of historical crossing intentions, the target obstacle can be filtered (updated) from the dimension of the proportion of historical crossing intentions, which can more accurately determine the target obstacle, and the probability of the target obstacle being a target pedestrian crossing is also higher.
[0070] Figure 3B The diagram illustrates the target obstacle Obs that meets the first interaction condition in three historical video frames.
[0071] Figure 3C A schematic diagram of a trajectory determination method according to yet another embodiment of the present disclosure is shown.
[0072] like Figure 3C As shown, according to another embodiment of the trajectory determination method of this disclosure, for example, the following specific example can be used to determine the motion trajectory of an obstacle in a future target time period based on obstacle state data of the target obstacle and vehicle state data of the target vehicle: A first constraint point, point1, is determined based on the obstacle's position and speed direction. A second constraint point, point2, is determined on the target pedestrian crossing that is collinear with the vehicle's speed direction. A third constraint point, point3, is determined based on the boundary of the target pedestrian crossing. The crossing conflict result for the target pedestrian crossing in the future target time period is determined based on the obstacle's speed value and the vehicle's speed value at the current moment. If the crossing conflict result indicates that there is a crossing conflict between the target obstacle and the target vehicle for the target pedestrian crossing, the motion trajectory Lo is determined based on the first constraint point1, the second constraint point2, and the third constraint point3.
[0073] Obstacle status data includes obstacle position, obstacle velocity direction, and obstacle velocity value; target vehicle status data includes vehicle velocity direction and vehicle velocity value.
[0074] According to the trajectory determination method of this disclosure, the current obstacle position and obstacle velocity direction can be used as the first constraint point, and a second constraint point (point2) can be determined on the target pedestrian crossing that is collinear with the vehicle velocity direction. A third constraint point (point3) is determined based on the boundary of the target pedestrian crossing. Using these three constraint points as constraints on the trajectory, a trajectory tending towards the obstacle crossing the pedestrian crossing can be obtained. It is understood that since the target vehicle will pass through the target pedestrian crossing in the future, this tendency may affect the driving safety of the target vehicle.
[0075] There are situations where, although the target obstacle's current velocity direction is towards the target pedestrian crossing, its current velocity magnitude is relatively small. Based on calculations of the target time period and the obstacle's velocity magnitude, it is determined that the obstacle will not reach the boundary of the target pedestrian crossing (when the velocity is small) or will completely cross the target pedestrian crossing (when the velocity is large). This indicates that within the target time period, the target vehicle will not collide with the target obstacle when passing through the target pedestrian crossing.
[0076] According to the trajectory determination method of this disclosure, by determining the crossing conflict result of the target pedestrian crossing in the future target time period based on the obstacle speed value and vehicle speed value at the current moment, and in the case where the crossing conflict result indicates that there is a crossing conflict between the target obstacle and the target vehicle for the target pedestrian crossing, the motion trajectory Lo determined based on the first constraint point 1, the second constraint point 2 and the third constraint point 3 can exclude the case where the target vehicle and the target obstacle do not conflict, as mentioned above, thereby improving the efficiency of determining the obstacle trajectory.
[0077] For example, the following embodiment can be used to implement a specific example of determining the motion trajectory for a future target time period based on a first constraint point, a second constraint point, and a third constraint point: The constraint point boundaries are determined based on the first, second, and third constraint points. The range of the constraint trajectory between the constraint point boundaries is divided into multiple constraint trajectory segments using spline interpolation. The motion trajectory is determined based on the spline interpolation equation solution for each constraint trajectory segment.
[0078] According to the trajectory determination method of this disclosure, a smooth motion trajectory of the target obstacle can be obtained on the path constrained by the first constraint point, the second constraint point, and the third constraint point through spline interpolation.
[0079] In addition to the scenario of crossing a pedestrian crossing, the trajectory determination method of this disclosure also addresses obstacle turning scenarios, such as obstacles turning towards the exit lane.
[0080] Figure 4 A schematic diagram of a trajectory determination method according to yet another embodiment of the present disclosure is shown.
[0081] like Figure 4As shown, according to another embodiment of the trajectory determination method of this disclosure, when the target interaction conditions include a second interaction condition, the following specific example can be used to determine a target obstacle that satisfies the target interaction conditions with the target vehicle based on the target vehicle's perception data: Based on map perception data, an obstacle whose distance from the target vehicle in the target vehicle's driving direction satisfies a third distance threshold and whose distance from the target vehicle in the lateral direction satisfies a fourth distance threshold is identified as a first obstacle. Based on obstacle perception data, the first obstacle whose lane direction relative to the target vehicle's lane satisfies a second angle range is identified as a target obstacle.
[0082] The perception data includes map perception data and obstacle perception data.
[0083] The second interaction condition characterizes the obstacle's turning intention, and the second interaction condition is related to the third distance threshold, the fourth distance threshold, and the second angle range.
[0084] For example, the third distance threshold can be in the range of 10m-25m. The fourth distance threshold can be in the range of 3m-8m.
[0085] For example, the range of the second angle can be, for instance, |α1| greater than 3°.
[0086] According to the trajectory determination method of this disclosure, the second interaction condition is for obstacle turning scenarios such as obstacles turning towards the exit lane. The second interaction condition can characterize a clear logical condition indicating whether the obstacle has a turning intention, thus offering higher controllability. Based on map perception data, obstacles whose distance from the target vehicle in the target vehicle's driving direction meets a third distance threshold and whose distance from the target vehicle in the side of the target vehicle meets a fourth distance threshold are identified as first obstacles. The first obstacle is located in front of and to the side of the target vehicle. When the first obstacle has a turning intention, it will affect the driving safety of the target vehicle in the future. By using obstacle perception data and a second angle range, target obstacles with turning intentions can be accurately and efficiently determined. The target obstacle has a higher risk of collision with the target vehicle in the future. The motion trajectory determined subsequently based on the target obstacle can be used as a reference for the target vehicle's planned trajectory.
[0087] For example, the trajectory determination method according to another embodiment of the present disclosure further includes: updating the target obstacle based on the proportion of historical turning intentions.
[0088] The historical turning intention ratio is P / Q, where Q represents the number of historical video frames associated with the target obstacle, and P represents the number of historical video frames corresponding to the target obstacle that satisfies the second interaction condition and the historical turning intention condition. The historical turning intention condition represents at least one of the following: the target obstacle decelerates, the target obstacle issues a turning signal, and the target obstacle's speed direction moves toward the exit lane.
[0089] For example, the target obstacle may emit a turning signal, such as a vehicle's turn signal.
[0090] For example, the historical turning intention ratio can also be in the range of 0.6-1, and Q can be in the range of 3-15.
[0091] According to the trajectory determination method of this disclosure, by updating the target obstacle based on the proportion of historical turning intentions, the target obstacle can be filtered (updated) from the dimension of the proportion of historical turning intentions, resulting in a more accurate target obstacle and a higher probability that the target obstacle has a turning intention.
[0092] For example, in another embodiment of the trajectory determination method according to this disclosure, the obstacle state data includes the obstacle position, the obstacle velocity direction, and the obstacle velocity value. The target vehicle's vehicle state data includes the vehicle velocity direction and the vehicle velocity value.
[0093] like Figure 4 As shown, for example, the following embodiment can be used to determine the motion trajectory of an obstacle for a future target time period based on the obstacle state data of the target obstacle and the vehicle state data of the target vehicle: A first constraint point, point1, is determined based on the obstacle's position and speed direction. A second constraint point, point2, is determined in the exit lane Lane-o. The steering conflict result for the future target time period is determined based on the obstacle's speed value and the vehicle's speed value at the current moment. When the steering conflict result indicates a conflict between the target obstacle Obs and the target vehicle Vt regarding the exit lane, the motion trajectory Lo for the future target time period is determined based on the first constraint point1 and the second constraint point2.
[0094] According to the trajectory determination method of this disclosure, the current obstacle position and obstacle velocity direction can be used as first constraint points to determine a second constraint point in the exit lane. Using these two constraint points as constraints on the trajectory, a trajectory can be obtained where the obstacle tends to turn towards the exit lane. When a lateral obstacle turns towards the exit lane, it will pass in front of the target vehicle, which may affect the driving safety of the target vehicle.
[0095] There are situations where, although the target obstacle's current speed direction is towards the exit lane, its current speed is relatively low. Based on calculations of the target time period and the obstacle's speed, it is determined that the obstacle will not reach the target vehicle's lane (when the speed is low) or will completely cross the target vehicle's lane (when the speed is high). This indicates that within the target time period, the target vehicle will not collide with the target obstacle when crossing the target pedestrian crossing.
[0096] According to the trajectory determination method of this disclosure, the turning conflict result for a future target time period is determined based on the obstacle speed value and the vehicle speed value at the current moment. When the turning conflict result indicates a conflict between the target obstacle and the target vehicle regarding the exit lane, the motion trajectory for the future target time period is determined based on the first constraint point and the second constraint point. This can eliminate situations where, for example, the target vehicle and the target obstacle do not conflict, thereby improving the efficiency of determining the obstacle trajectory.
[0097] For example, the following embodiment can be used to implement a specific example of determining the motion trajectory for a future target time period based on a first constraint point and a second constraint point: The constraint point boundaries are determined based on the first and second constraint points. The range of the constraint trajectory between the constraint point boundaries is divided into multiple constraint trajectory segments using spline interpolation. The motion trajectory for the future target time period is determined based on the spline interpolation equation solution for each constraint trajectory segment.
[0098] The trajectory of motion can, for example, converge toward the centerline of the exit lane.
[0099] According to the trajectory determination method of this disclosure, a smooth motion trajectory of the target obstacle can be obtained on the path constrained by the first constraint point, the second constraint point, and the third constraint point through spline interpolation.
[0100] It should also be noted that there are target obstacles that satisfy either the first or second interaction condition with the target vehicle. The scenarios corresponding to each interaction condition have been described in the above embodiments and will not be repeated here. There are also target obstacles that satisfy both the first and second interaction conditions with the target vehicle. For example, if there is a target pedestrian crossing in front of the target vehicle, and a target obstacle near the target pedestrian crossing that crosses the target pedestrian crossing is located to the side of the target vehicle and has the intention to turn towards the exit lane, then this target obstacle can satisfy both the first and second interaction conditions with the target vehicle.
[0101] Figure 5 A block diagram of a trajectory determination apparatus according to an embodiment of the present disclosure is shown schematically.
[0102] like Figure 5As shown, the trajectory determination device 500 of this embodiment includes, for example, a target obstacle determination module 510 and a motion trajectory determination module 520.
[0103] The target obstacle determination module 510 is used to determine target obstacles that meet target interaction conditions with the target vehicle based on the target vehicle's perception data. The target interaction conditions include at least one of a first interaction condition and a second interaction condition, wherein the first interaction condition represents a scenario where the obstacle crosses a pedestrian crossing, and the second interaction condition represents a scenario where the obstacle turns toward the exit lane.
[0104] The motion trajectory determination module 520 is used to determine the motion trajectory of the target obstacle for a future target time period based on the obstacle status data of the target obstacle and the vehicle status data of the target vehicle.
[0105] For example, when the target interaction condition includes a first interaction condition, the perception data includes map perception data and obstacle perception data; the target obstacle determination module includes: a target pedestrian crossing determination submodule, used to determine, based on the map perception data, a target pedestrian crossing located in the driving direction of the target vehicle and satisfying a first distance threshold with respect to the current position of the target vehicle; a candidate obstacle determination submodule, used to determine, based on the obstacle perception data, obstacles that satisfy a first angle range with respect to the lane direction of the target vehicle and satisfy a second distance threshold with respect to the boundary along the lane direction as candidate obstacles; and a target obstacle determination submodule, used to determine the target obstacle based on the candidate obstacles and the intent masking condition; wherein, the first interaction condition represents the intention of the obstacle to cross the target pedestrian crossing, the first interaction condition is related to the first distance threshold, the second distance threshold, the first angle range, and the intent masking condition, and the intent masking condition represents the intention of the candidate obstacle to move away from the target pedestrian crossing.
[0106] For example, the trajectory determination apparatus according to the embodiments of the present disclosure further includes: a first update module, configured to update the target obstacle according to the historical traversal intention ratio, wherein the historical traversal intention ratio is M / N, N represents the number of historical video frames related to the target obstacle, and M represents the number of historical video frames corresponding to the target obstacle that satisfies the first interaction condition.
[0107] For example, the obstacle state data includes the obstacle position, obstacle velocity direction, and obstacle velocity value; the target vehicle's vehicle state data includes the vehicle velocity direction and vehicle velocity value; the motion trajectory determination module includes: a first constraint point determination submodule, used to determine a first constraint point based on the obstacle position and obstacle velocity direction; a second constraint point determination submodule, used to determine a second constraint point on the target pedestrian crossing that is collinear with the vehicle velocity direction; a third constraint point determination submodule, used to determine a third constraint point based on the boundary of the target pedestrian crossing; a crossing conflict result determination submodule, used to determine the crossing conflict result for the target pedestrian crossing in the future target time period based on the obstacle velocity value and vehicle velocity value at the current moment; and a motion trajectory determination submodule, used to determine the motion trajectory for the future target time period based on the first constraint point, the second constraint point, and the third constraint point when the crossing conflict result indicates that there is a crossing conflict between the target obstacle and the target vehicle for the target pedestrian crossing.
[0108] For example, the first motion trajectory determination submodule includes: a constraint point boundary determination unit, used to determine the constraint point boundary based on the first constraint point, the second constraint point, and the third constraint point; a constraint trajectory segmentation determination unit, used to divide the constraint trajectory range between the constraint point boundaries into multiple constraint trajectory segments through spline interpolation operations; and a first motion trajectory determination unit, used to determine the motion trajectory for the future target time period based on the spline interpolation equation solution of each constraint trajectory segment.
[0109] For example, when the target interaction condition includes a second interaction condition, the perception data includes map perception data and obstacle perception data; the target obstacle determination module includes: a first obstacle determination submodule, used to determine, based on the map perception data, obstacles whose distance from the target vehicle in the direction of travel of the target vehicle meets a third distance threshold and whose distance from the target vehicle in the lateral direction of the target vehicle meets a fourth distance threshold as first obstacles; and a target obstacle determination submodule, used to determine, based on the obstacle perception data, first obstacles whose lane direction relative to the lane where the target vehicle is located meets a second angle range as target obstacles; wherein, the second interaction condition characterizes the turning intention of the obstacle, and the second interaction condition is related to the third distance threshold, the fourth distance threshold, and the second angle range.
[0110] For example, the trajectory determination apparatus according to an embodiment of the present disclosure further includes: a second update module, configured to update the target obstacle according to a historical turning intention ratio, wherein the historical turning intention ratio is P / Q, Q represents the number of historical video frames related to the target obstacle, P represents the number of historical video frames corresponding to the target obstacle that satisfies the second interaction condition and the historical turning intention condition, and the historical turning intention condition represents at least one of the following: the target obstacle decelerates, the target obstacle issues a turning signal, and the target obstacle's speed direction moves toward the exit lane.
[0111] For example, the obstacle state data includes the obstacle position, obstacle velocity direction, and obstacle velocity value; the target vehicle's vehicle state data includes the vehicle velocity direction and vehicle velocity value; the motion trajectory determination module includes: a first constraint point second determination submodule, used to determine a first constraint point based on the obstacle position and obstacle velocity direction; a second constraint point second determination submodule, used to determine a second constraint point in the exit lane; a steering conflict result determination submodule, used to determine the steering conflict result for a future target time period based on the obstacle velocity value and vehicle velocity value at the current moment; and a motion trajectory second determination submodule, used to determine the motion trajectory for a future target time period based on the first constraint point and the second constraint point when the steering conflict result indicates a conflict between the target obstacle and the target vehicle over the exit lane.
[0112] For example, the second motion trajectory determination submodule includes: a constraint point second determination unit, used to determine the constraint point boundary based on the first constraint point and the second constraint point; a constraint trajectory segmentation second determination unit, used to divide the constraint trajectory range between the constraint point boundaries into multiple constraint trajectory segments through spline interpolation operation; and a motion trajectory third determination unit, used to determine the motion trajectory for the future target time period based on the spline interpolation equation solution of each constraint trajectory segment.
[0113] It should be understood that the embodiments of the apparatus portion of this disclosure correspond to the same or similar embodiments of the method portion of this disclosure, and the technical problems solved and the technical effects achieved are also the same or similar. This disclosure will not repeat them here.
[0114] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0115] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0116] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.
[0117] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0118] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the trajectory determination method. For example, in some embodiments, the trajectory determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the trajectory determination method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the trajectory determination method by any other suitable means (e.g., by means of firmware).
[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0120] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0121] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0124] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.
[0125] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A trajectory determination method, comprising: Based on the perception data of the target vehicle, target obstacles that meet the target interaction conditions with the target vehicle are identified. These target interaction conditions include at least one of a first interaction condition and a second interaction condition. The first interaction condition represents a scenario where the obstacle crosses a pedestrian crossing, and the second interaction condition represents a scenario where the obstacle turns towards an exit lane. Based on the obstacle status data of the target obstacle and the vehicle status data of the target vehicle, the movement trajectory of the target obstacle for a future target time period is determined; wherein, the obstacle status data includes the obstacle position, the obstacle velocity direction, and the obstacle velocity value; the vehicle status data of the target vehicle includes the vehicle velocity value; Wherein, when the target interaction condition includes the second interaction condition, determining the future target time period trajectory of the target obstacle based on the obstacle state data of the target obstacle and the vehicle state data of the target vehicle includes: The first constraint point is determined based on the obstacle's position and velocity direction. Determine a second constraint point in the exit lane; Based on the current obstacle speed value and the vehicle speed value, determine the steering conflict result for the future target time period; When the steering conflict result indicates that there is a conflict between the target obstacle and the target vehicle for the exit lane, the motion trajectory for the future target time period is determined based on the first constraint point and the second constraint point.
2. The method according to claim 1, wherein, When the target interaction condition includes the first interaction condition, the perception data includes map perception data and obstacle perception data. The step of determining the target obstacle that meets the target interaction conditions with the target vehicle based on the target vehicle's perception data includes: Based on the map perception data, a target pedestrian crossing is determined that is located in the driving direction of the target vehicle and meets a first distance threshold with respect to the current position of the target vehicle; Based on the obstacle perception data, obstacles that satisfy a first angle range with respect to the lane direction of the target vehicle and a second distance threshold with respect to the boundary along the lane direction are identified as candidate obstacles; and The target obstacle is determined based on the candidate obstacles and the intended shielding conditions; The first interaction condition represents the intention of the obstacle to cross the target pedestrian crossing. The first interaction condition is related to the first distance threshold, the second distance threshold, the first angle range, and the intention masking condition. The intention masking condition represents the intention of the candidate obstacle to move away from the target pedestrian crossing.
3. The method according to claim 2, further comprising: The target obstacle is updated based on the historical traversal intention ratio, wherein the historical traversal intention ratio is M / N, N represents the number of historical video frames related to the target obstacle, and M represents the number of historical video frames corresponding to the target obstacle that satisfies the first interaction condition.
4. The method according to any one of claims 1-3, wherein, The obstacle status data includes the obstacle position, obstacle velocity direction, and obstacle velocity value; the target vehicle's vehicle status data includes the vehicle velocity direction and vehicle velocity value. Determining the future target time period's trajectory of the target obstacle based on its obstacle state data and the target vehicle's vehicle state data includes: The first constraint point is determined based on the obstacle's position and velocity direction. A second constraint point is determined at the target pedestrian crossing that is collinear with the vehicle's velocity direction; Determine the third constraint point based on the boundary of the target pedestrian crossing; Based on the current obstacle speed value and the vehicle speed value, determine the crossing conflict result for the target pedestrian crossing in the future target time period; When the crossing conflict result indicates that there is a crossing conflict between the target obstacle and the target vehicle for the target pedestrian crossing, the movement trajectory for the future target time period is determined based on the first constraint point, the second constraint point, and the third constraint point.
5. The method according to claim 4, wherein, Determining the motion trajectory for the future target time period based on the first constraint point, the second constraint point, and the third constraint point includes: The constraint point boundaries are determined based on the first constraint point, the second constraint point, and the third constraint point; By using spline interpolation, the range of the constraint trajectory between the constraint point boundaries is divided into multiple constraint trajectory segments; and The motion trajectory for the future target time period is determined based on the spline interpolation equation solution for each constrained trajectory segment.
6. The method according to claim 1, wherein, When the target interaction condition includes the second interaction condition, the perception data includes map perception data and obstacle perception data. The step of determining the target obstacle that meets the target interaction conditions with the target vehicle based on the target vehicle's perception data includes: Based on the map perception data, obstacles whose distance from the target vehicle in the direction of travel meets a third distance threshold and whose distance from the target vehicle in the lateral direction meets a fourth distance threshold are identified as first obstacles; and Based on the obstacle perception data, the first obstacle that satisfies the second angle range with the lane direction of the lane where the target vehicle is located is identified as the target obstacle; The second interaction condition represents the turning intention of the obstacle, and the second interaction condition is related to the third distance threshold, the fourth distance threshold, and the second angle range.
7. The method according to claim 6, wherein, Also includes: The target obstacle is updated based on the historical turning intention ratio, wherein the historical turning intention ratio is P / Q, Q represents the number of historical video frames associated with the target obstacle, P represents the number of historical video frames corresponding to the target obstacle that satisfy the second interaction condition and the historical turning intention condition, and the historical turning intention condition represents at least one of the following: the target obstacle decelerates, the target obstacle issues a turning signal, and the target obstacle's speed direction moves toward the exit lane.
8. The method according to claim 7, wherein, The vehicle status data of the target vehicle also includes vehicle speed and direction.
9. The method according to claim 8, wherein, Determining the motion trajectory for the future target time period based on the first constraint point and the second constraint point includes: Determine the boundary of the constraint points based on the first constraint point and the second constraint point; By using spline interpolation, the range of the constraint trajectory between the constraint point boundaries is divided into multiple constraint trajectory segments; and The motion trajectory for the future target time period is determined based on the spline interpolation equation solution for each constrained trajectory segment.
10. A trajectory determining device, comprising: A target obstacle determination module is used to determine, based on perception data of a target vehicle, target obstacles that satisfy target interaction conditions with the target vehicle. These target interaction conditions include at least one of a first interaction condition and a second interaction condition. The first interaction condition characterizes a scenario where the obstacle crosses a pedestrian crossing, and the second interaction condition characterizes a scenario where the obstacle turns towards an exit lane. The motion trajectory determination module is used to determine the motion trajectory of the target obstacle for a future target time period based on the obstacle state data of the target obstacle and the vehicle state data of the target vehicle; wherein, the obstacle state data includes the obstacle position, the obstacle velocity direction, and the obstacle velocity value; the vehicle state data of the target vehicle includes the vehicle velocity value; Wherein, when the target interaction condition includes the second interaction condition, the motion trajectory determination module includes: The first constraint point second determination submodule is used to determine the first constraint point based on the obstacle position and the obstacle velocity direction; The second constraint point determination submodule is used to determine the second constraint point in the exit lane. The steering conflict result determination submodule is used to determine the steering conflict result for the future target time period based on the obstacle speed value and the vehicle speed value at the current moment. The second trajectory determination submodule is used to determine the trajectory of the future target time period based on the first constraint point and the second constraint point when the steering conflict result indicates that there is a conflict between the target obstacle and the target vehicle for the exit lane.
11. The apparatus according to claim 10, wherein, When the target interaction condition includes the first interaction condition, the perception data includes map perception data and obstacle perception data. The target obstacle determination module includes: The target pedestrian crossing determination submodule is used to determine, based on the map perception data, the target pedestrian crossing located in the direction of travel of the target vehicle and satisfying a first distance threshold with respect to the current position of the target vehicle; The candidate obstacle determination submodule is used to determine, based on the obstacle perception data, obstacles that satisfy a first angle range with respect to the lane direction of the target vehicle and a second distance threshold with respect to the boundary along the lane direction as candidate obstacles; and The target obstacle determination submodule is used to determine the target obstacle based on the candidate obstacles and the intended masking conditions; The first interaction condition represents the intention of the obstacle to cross the target pedestrian crossing. The first interaction condition is related to the first distance threshold, the second distance threshold, the first angle range, and the intention masking condition. The intention masking condition represents the intention of the candidate obstacle to move away from the target pedestrian crossing.
12. The apparatus of claim 11, further comprising: The first update module is used to update the target obstacle according to the historical traversal intention ratio, wherein the historical traversal intention ratio is M / N, N represents the number of historical video frames related to the target obstacle, and M represents the number of historical video frames corresponding to the target obstacle that satisfies the first interaction condition.
13. The apparatus according to any one of claims 10-12, wherein, The obstacle status data includes the obstacle position, obstacle velocity direction, and obstacle velocity value; The vehicle status data of the target vehicle includes the vehicle speed direction and the vehicle speed value; The motion trajectory determination module includes: The first constraint point determination submodule is used to determine the first constraint point based on the obstacle position and the obstacle velocity direction; The second constraint point first determination submodule is used to determine the second constraint point on the target pedestrian crossing that is collinear with the vehicle speed direction; The third constraint point determination submodule is used to determine the third constraint point based on the boundary of the target pedestrian crossing. The crossing conflict result determination submodule is used to determine the crossing conflict result for the target pedestrian crossing in the future target time period based on the obstacle speed value and the vehicle speed value at the current moment. The first motion trajectory determination submodule is used to determine the motion trajectory for the future target time period based on the first constraint point, the second constraint point, and the third constraint point when the crossing conflict result indicates that there is a crossing conflict between the target obstacle and the target vehicle for the target pedestrian crossing.
14. The apparatus according to claim 13, wherein, The first motion trajectory determination submodule includes: The constraint point boundary determination unit is used to determine the constraint point boundary based on the first constraint point, the second constraint point, and the third constraint point. The constraint trajectory segmentation unit is used to divide the range of the constraint trajectory between the constraint point boundaries into multiple constraint trajectory segments through spline interpolation; and The first motion trajectory determination unit is used to determine the motion trajectory of the future target time period based on the spline interpolation equation solution of each constrained trajectory segment.
15. The apparatus according to claim 10, wherein, When the target interaction condition includes the second interaction condition, the perception data includes map perception data and obstacle perception data. The target obstacle determination module includes: The first obstacle determination submodule is used to determine, based on the map perception data, obstacles whose distance from the target vehicle in the direction of travel of the target vehicle meets a third distance threshold and whose distance from the target vehicle in the lateral direction of the target vehicle meets a fourth distance threshold as first obstacles; and The target obstacle determination submodule is used to determine the first obstacle that satisfies the second angle range with respect to the lane direction of the lane where the target vehicle is located as the target obstacle based on the obstacle perception data. The second interaction condition represents the turning intention of the obstacle, and the second interaction condition is related to the third distance threshold, the fourth distance threshold, and the second angle range.
16. The apparatus according to claim 15, wherein, Also includes: The second update module is used to update the target obstacle according to the historical turning intention ratio, wherein the historical turning intention ratio is P / Q, Q represents the number of historical video frames related to the target obstacle, P represents the number of historical video frames corresponding to the target obstacle that satisfy the second interaction condition and the historical turning intention condition, and the historical turning intention condition represents at least one of the following: the target obstacle decelerates, the target obstacle issues a turning signal, and the target obstacle's speed direction moves towards the exit lane.
17. The apparatus according to claim 16, wherein, The vehicle status data of the target vehicle includes vehicle speed and direction.
18. The apparatus according to claim 17, wherein, The second motion trajectory determination submodule includes: The second constraint point determination unit is used to determine the constraint point boundary based on the first constraint point and the second constraint point; The second constraint trajectory segmentation determination unit is used to divide the constraint trajectory range between the constraint point boundaries into multiple constraint trajectory segments through spline interpolation; and The third motion trajectory determination unit is used to determine the motion trajectory of the future target time period based on the spline interpolation equation solution of each constrained trajectory segment.
19. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
20. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.
21. A computer program product comprising a computer program stored on at least one of a readable storage medium and an electronic device, the computer program implementing the method according to any one of claims 1-9 when executed by a processor.
22. An autonomous vehicle, including the electronic equipment as described in claim 19.