CN116097193A - Track data processing method, track data processing device, computer equipment and storage medium - Google Patents
Track data processing method, track data processing device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116097193A CN116097193A CN202080103187.1A CN202080103187A CN116097193A CN 116097193 A CN116097193 A CN 116097193A CN 202080103187 A CN202080103187 A CN 202080103187A CN 116097193 A CN116097193 A CN 116097193A
- Authority
- CN
- China
- Prior art keywords
- track
- data
- frame
- simulated
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 title claims description 12
- 238000004088 simulation Methods 0.000 claims abstract description 163
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims description 45
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 12
- 230000001133 acceleration Effects 0.000 description 7
- 230000036461 convulsion Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 239000000306 component Substances 0.000 description 3
- 238000013398 bayesian method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 239000008358 core component Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
A track data processing method, comprising: acquiring track data, road information, route data and road condition data of a target vehicle within a preset distance range from the target vehicle within a preset time period; inputting track data, road condition data, road information and route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of a target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameters; performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; and adjusting the current track planning parameter according to the cost value, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle according to the track data, the road condition data, the road information, the road data and the current track planning parameter until the preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
Description
The application relates to a track data processing method, a track data processing device, computer equipment and a storage medium.
The development of artificial intelligence technology has prompted the development of autopilot technology. In the course of autopilot, autopilot vehicles are exposed to increasingly open and complex traffic scenarios. While driving behavior of an autonomous vehicle in a traffic scene plays a decisive role in the safety of the autonomous vehicle, trajectory planning is a core component of the driving behavior, and in order to cope with a complex traffic scene, a large number of parameters are set in a trajectory planning algorithm adopted by a trajectory planner, and because the balance relationship between the parameters is very complex, adapting to a diversified traffic scene by adjusting the parameters becomes extremely difficult. In order to enable the track planning algorithm to adapt to diversified traffic scenes, the traditional method is to carry out parameter adjustment on the diversified traffic scenes by a method for learning track planning parameters in the track planning algorithm, such as an inverse reinforcement learning method, so that the track planning algorithm after parameter adjustment is adopted to carry out track planning in an automatic driving process.
However, the conventional method is only suitable for a specific track planning algorithm, and when the parameter adjustment is performed on the track planning algorithm outside the specific planning algorithm by using the conventional method, the parameter of the track planning algorithm is inaccurate.
Disclosure of Invention
According to various embodiments disclosed herein, a trajectory data processing method, apparatus, computer device, and storage medium are provided that are capable of improving the parameter accuracy of a trajectory planning algorithm.
A track data processing method, comprising:
acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;
inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;
performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; and
And adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
A trajectory data processing device, comprising:
the data acquisition module is used for acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;
the data simulation module is used for inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters; generating a simulated track of the target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameters by the data simulation unit;
the cost calculation module is used for calculating the cost of the simulated track to obtain a cost value corresponding to the simulated track; and
And the parameter adjusting module is used for adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulating unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the processor, cause the one or more processors to perform the steps of:
acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;
inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;
performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; and
And adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;
inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;
performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; and
And adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description and drawings, and from the claims.
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram of an application environment for a trajectory data processing method in one or more embodiments.
FIG. 2 is a flow diagram of a method of trace data processing in one or more embodiments.
FIG. 3 is a flow diagram of steps for adjusting current trajectory planning parameters in one or more embodiments.
FIG. 4 is a block diagram of a trace data processing apparatus in one or more embodiments.
FIG. 5 is a block diagram of a computer device in one or more embodiments.
In order to make the technical solution and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The track data processing method provided by the application can be applied to an application environment shown in fig. 1. The terminal 102 communicates with the server 104 via a network. When the track planning parameters need to be adjusted, the terminal 102 may send a parameter adjustment request to the server 104, and after the server 104 obtains the parameter adjustment request, the server analyzes the parameter adjustment request to obtain track data of the target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information of the target vehicle and route data of the target vehicle in the preset time period. The server 104 may issue a parameter adjustment instruction to the terminal 102, where the terminal 102 obtains track data of the target vehicle within a preset time period, road condition data of the target vehicle within a preset distance range, road information of the target vehicle, and route data of the target vehicle within the preset time period according to the parameter adjustment instruction, and sends the obtained data to the server 104. The server 104 inputs the track data, the road condition data, the road information and the route data into a data simulation unit, the data simulation unit comprises current track planning parameters, a simulation track of the target vehicle is generated through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters, so that the server 104 performs cost calculation on the simulation track to obtain a cost value corresponding to the simulation track, further adjusts the current track planning parameters according to the cost value to obtain adjusted track planning parameters, takes the adjusted track planning parameters as the current track planning parameters, and returns to the step of generating the simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters until preset conditions are met, and the adjustment of the parameters is stopped to obtain the target planning parameters. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, among others. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a track data processing method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
Autonomous vehicles face increasingly open, more complex traffic scenarios. While driving behavior of an autonomous vehicle in a traffic scenario plays a decisive role in the safety of the autonomous vehicle, trajectory planning is a core component of driving behavior, and in order to cope with complex traffic scenarios, a large number of parameters are set in a trajectory planning algorithm employed by a trajectory planner. In the track planning process, a driving route within a period of time can be planned through position information, surrounding environment information and the like, and specific actions are executed to change the driving state of the automatic driving vehicle, such as parking, straight running, lane changing, turning and the like. The track data processing method provided by the application can be suitable for any track planning algorithm to determine optimal track planning parameters of any complex and diversified traffic scene, for example, the track planning algorithm can comprise a rapid expansion random tree (RRT) method, a visual map (visibility map), a probability roadmap algorithm (probability roadmap method, PRM) and the like, and the traffic scene can comprise a lane changing scene, a turning scene, a lane keeping scene, a parking scene and the like.
The track data of the target vehicle in the preset time period refers to track data of the target vehicle in the actual running process, and the road condition data of the target vehicle in the preset distance range refers to track data of the environment vehicle in the actual running process. The track data and the road condition data are recorded historical data. The preset time period is a time period selected for adjusting the trajectory planning parameter. The target vehicle refers to any vehicle for automatic driving, and the track data of the target vehicle is used for adjusting track planning parameters. The road condition data within the preset distance range with the target vehicle refers to track data of environmental vehicles around the target vehicle. The route data refers to destination data that the target vehicle needs to reach.
In order to accurately track the autonomous vehicle in the traffic scene, parameters of a track planning algorithm employed in the traffic scene may be adjusted in advance. Specifically, the server may acquire a parameter adjustment request sent by the terminal, and analyze the parameter adjustment request to obtain track data of the target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information of the target vehicle, and route data of the target vehicle in the preset time period. The server can also issue parameter adjustment instructions to the terminal, the terminal obtains track data of the target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information of the target vehicle and route data of the target vehicle in the preset time period according to the parameter adjustment instructions, and the obtained data is sent to the server. The trajectory data of the target vehicle may include the position, speed, acceleration, jerk, etc. of the target vehicle at each moment. The road condition data of the target vehicle within the preset distance range comprises the position, the speed, the acceleration, the jerk and the like of the environment vehicle within the preset distance range with the target vehicle at each moment. The road information on which the target vehicle is located may include traffic lanes, road boundary points, lane line information, etc. on which the target vehicle is located, and the road information may be acquired from a high-precision map. The route data may include destination identification of the target vehicle, location of the destination, etc. For example, the preset time period may be 40s. The preset distance range may be a range with a distance radius of 10m centered on the position of the target vehicle.
The track data of the target vehicle within the preset time period, the road condition data of the target vehicle within the preset distance range, the road information of the target vehicle and the route data of the target vehicle within the preset time period can be extracted from the vehicle-mounted computer equipment by the terminal. The vehicle-mounted computer equipment is arranged in the automatic driving vehicle, and can store track data of the target vehicle, road condition data of the target vehicle within a damaged distance range, road information of the target vehicle and route data of the target vehicle within a preset time period.
Further, the server may further obtain a parameter adjustment request sent by the terminal, analyze the parameter adjustment request to obtain a request parameter, and extract track data of the target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information of the target vehicle and route data of the target vehicle in the preset time period from the vehicle-mounted computer device according to the request parameter.
The data simulation unit is used for planning the track and generating a simulation track according to the planned track. The simulated trajectory refers to a trajectory of the target vehicle running in the data simulation unit during the data simulation.
After the server acquires the track data, the road condition data, the road information and the route data, the data simulation unit is called, the track data, the road condition data, the road information and the route data are input into the data simulation unit, and the data simulation unit comprises current track planning parameters, so that the track of the target vehicle running in a preset time period can be simulated through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters.
Specifically, the server may perform frame processing on the track data, the road condition data, the road information and the route data through the data simulation unit, so as to obtain multi-frame data. Each frame of data comprises track data, road condition data, road information and route data corresponding to the frame. And generating a simulated track segment corresponding to each frame of data according to the current track planning parameters through the data simulation unit. The current trajectory planning parameters may be parameters that are pre-specified to be adjusted. The simulated track segment refers to a track for controlling the target vehicle to run in each frame in the data simulation process. Further, according to the time sequence between each frame of data, the data simulation unit sequentially generates a simulation track segment corresponding to each frame of data. And then generating a simulated track of the target vehicle according to the simulated track fragments corresponding to the multi-frame data through the data simulation unit. The simulated trajectory may include a position, a velocity, an acceleration, a jerk, etc. at each moment.
And 206, performing cost calculation on the simulated track to obtain the cost value corresponding to the simulated track.
In order to better adjust the track planning parameters, the server can perform cost calculation on the simulated track in various ways, the cost calculation can be performed by calculating the similarity between the simulated track and track data of the target vehicle, and the cost calculation can also be performed by comparing parameter values of all driving parameters in the environment vehicle within the range of the distance between the target vehicle and the environment vehicle in the track simulation process. The cost calculation mode is not limited, and a corresponding cost calculation mode can be adopted according to actual needs.
In one embodiment, performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track includes: calculating the similarity between the track data and the simulated track; and calculating according to the similarity to obtain the cost value corresponding to the simulation track.
When the server performs cost calculation by calculating the similarity between the simulated trajectory and the trajectory data of the target vehicle, the server may calculate the distance between the trajectory data and the simulated trajectory using a cost-mimicking method, taking the distance as the similarity. The smaller the distance, the more similar the trajectory data and the simulated trajectory. The server calculates the cost value corresponding to the simulated track according to the calculated similarity by adopting a simulated cost method, and the cost value corresponding to the simulated track can be a weighted sum of a plurality of cost values. Specifically, the server determines a plurality of cost values to be calculated according to the cost function in the cost simulation method, and further calculates the cost value corresponding to the simulation track according to the calculated similarity, the cost function and the cost weight corresponding to each cost value. Cost weights corresponding to the cost values in the cost function can be used as track planning parameters. For example, when the cost function is a weighted sum of efficiency cost, safety cost and comfort cost, if the weights corresponding to the three costs of efficiency cost, safety cost and comfort cost need to be automatically adjusted, the weights corresponding to the three costs can be used as the track planning parameters. In this embodiment, the cost calculation is performed by calculating the similarity between the track data simulation track and the track data of the target vehicle, so that a driving track more conforming to the driving habit of the human can be obtained in the subsequent automatic driving process, thereby improving the flexibility of track planning.
In one embodiment, performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track includes: determining driving track data corresponding to preset driving parameters in the simulation track; determining driving road condition data corresponding to preset driving parameters in the road condition data; and calculating the cost value corresponding to the simulated track according to the driving track data and the driving road condition data.
When the server performs cost calculation by comparing the parameter values of each running parameter in the environmental vehicle within the preset distance range with the target vehicle in the track simulation process, the running track data corresponding to the preset running parameter can be determined in the simulation track, and the running road condition data corresponding to the preset running parameter can be determined in the road condition data. The preset travel parameters may include distance, speed, acceleration, jerk, etc. The travel track data may include parameter values of respective travel parameters corresponding to the target vehicle at each time. The road condition data comprise track data of an environmental vehicle within a preset distance range with the target vehicle. The driving track data comprises parameter values of driving parameters corresponding to the environmental vehicle at each moment. The server calculates the cost value corresponding to the simulated track according to the parameter values of the running parameters of the target vehicle and the environment vehicle at each moment by adopting a self-supervision cost method. The cost value corresponding to the simulated trajectory may be a weighted sum of the cost values. Specifically, the server determines a plurality of cost values to be calculated according to a cost function in the self-supervision cost method, and further calculates the cost value corresponding to the simulation track according to the parameter values of each driving parameter of the target vehicle and the environment vehicle at each moment, the cost function and the cost weight corresponding to each cost value. Cost weights corresponding to the cost values in the cost function can be used as track planning parameters. For example, when the cost function is a weighted sum of the distance cost and the speed cost, if weights corresponding to the distance cost and the speed cost need to be automatically adjusted, the weights corresponding to the two costs can be used as the track planning parameters. In this embodiment, by comparing the parameter values of each running parameter in the target vehicle and the environmental vehicle within the preset distance range, the collision between the target vehicle and the environmental vehicle can be avoided, the phenomenon of co-speed surge is avoided, the accuracy of track planning in the subsequent automatic driving process can be improved, and the safety of automatic driving is ensured.
And step 208, adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating a simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until the preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
The data planning unit comprises a plurality of track planning parameters, the track planning parameters can be determined according to a track planning algorithm adopted by the data simulation unit, and cost calculation is needed to be carried out by using a cost function in the track planning algorithm, so that the track planning parameters can be determined according to the cost function. The trajectory planning parameters corresponding to the different cost functions may be different. The server may set the data planning unit according to the trajectory planning parameter in the cost function, so that the subsequent data planning unit performs trajectory planning according to the trajectory planning parameter.
Before performing the track parameter adjustment, the server may pre-specify the track planning parameter and pre-set a parameter adjustment range of the track planning parameter among a large number of track planning parameters of the data planning unit. And taking the pre-designated track planning parameter as the current track planning parameter. In the parameter adjustment process, after the cost value corresponding to the simulated track is obtained through calculation, the server can adjust the current track planning parameter in the data simulation unit according to the cost value and the track planning range, the adjusted track planning parameter is used as the current track planning parameter, the step of generating the simulated track of the target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameter through the data simulation unit is returned, and repeated parameter adjustment is carried out until the preset condition is met. The preset condition may be that the current trajectory planning parameter has reached an optimal value within the parameter adjustment range. The optimal values are pre-stored in the server for parameter adjustment by the server. The server may generate the adjusted trajectory planning parameter according to the cost value by using a bayesian method, so that the adjusted trajectory planning parameter is used as a current trajectory planning parameter and is input into the data simulation unit. And when the current track planning parameter meets the preset condition, the server stops parameter adjustment, and takes the track planning parameter at the moment as a target track planning parameter. For example, when the current trajectory planning parameter is the weight of the two costs, namely the efficiency cost and the safety cost, the server can iteratively adjust the weights of the two costs in the parameter adjustment range according to the cost value, and when the weight of the efficiency cost and the weight of the safety cost reach the optimal values, the parameter adjustment is stopped, and the weight of the efficiency cost and the weight of the safety cost at the moment are taken as the target trajectory planning parameters.
In one embodiment, the server may store the target trajectory planning parameters in a data simulation unit. In the automatic driving process, the data simulation unit can utilize the target track planning parameters to carry out track planning on the automatic driving vehicle, and the accuracy of track planning can be improved because the target track planning parameters are the pre-adjusted and accurate track planning parameters.
In this embodiment, the obtained track data of the target vehicle in the preset time period, road condition data corresponding to the target vehicle in the preset distance range, road information corresponding to the target vehicle in the preset time period and route data corresponding to the target vehicle in the preset time period are input into the data simulation unit, a simulated track of the target vehicle is generated by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters, so that cost calculation is performed on the simulated track, a cost value corresponding to the simulated track is obtained, the current track planning parameters are adjusted according to the cost value, the adjusted track planning parameters are used as current track planning parameters, and the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters is performed with repeated parameter adjustment until preset conditions are met, and the parameter adjustment is stopped, so that the target track planning parameters are obtained. In the adjustment process of the track planning parameters, the track planning mode of the track planner is not concerned, and the parameter adjustment can be carried out independently of the track planner, so that the method is applicable to any track planning method in various traffic scenes, and the parameter accuracy of a track planning algorithm is effectively improved. Meanwhile, the automatic adjustment of parameters can be realized only by setting the current track planning parameters and the preset conditions, and the adjustment efficiency of the track planning algorithm parameters is improved.
In one embodiment, the step of generating, by the data simulation unit, a simulated track of the target vehicle according to the track data, the road condition data, the road information, the road data, and the current track planning parameter includes: extracting track data of each frame from the track data, road condition data of each frame from the road condition data, road information of each frame from the road information and route data of each frame from the route data through the data simulation unit; generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; after the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
The trajectory data may include the position, speed, acceleration, jerk, etc. of the target vehicle at each moment. The road condition data includes the position, speed, acceleration, jerk, etc. of the environmental vehicle within a preset distance range from the target vehicle at each moment. The road information may include traffic lanes in which the target vehicle is located, road boundary points, lane line information, etc., and the road information may be acquired from a high-precision map. The route data may include destination identification of the target vehicle, location of the destination, etc. For example, the preset time period may be 40s. The preset distance range may be a range with a distance radius of 10m centered on the position of the target vehicle.
The track data, the road condition data, the road information and the route data which are sent to the data simulation unit by the server are all data in a preset time period, and the data simulation unit can perform frame division processing on the track data, the road condition data, the road information and the route data to obtain multi-frame data. Each frame of data comprises track data, road condition data, road information and route data corresponding to the frame. And the data simulation unit sequentially extracts the data of each frame according to the time sequence among the data of each frame, and performs track planning on the data of each frame according to the current track planning parameters to obtain a track planning result. And the data simulation unit controls the target vehicle to run for a period of time according to the track planning result until the time stamp corresponding to the next frame is reached, and a simulated track segment corresponding to the frame is obtained. The simulated track segment refers to a track for controlling the target vehicle to run in each frame in the data simulation process. After the data simulation unit generates the simulation track segment of the previous frame, the data of the next frame is obtained, the simulation track segment corresponding to the next frame is generated according to the data of the next frame until the simulation track segment of the last frame is obtained, and then the data simulation unit obtains the simulation track of the target vehicle according to the simulation track segments of the multiple frames. The data of the next frame includes track data of the next frame, road condition data of the next frame, road information of the next frame and route data of the next frame. The simulated trajectory may include a position, a velocity, an acceleration, a jerk, etc. at each moment.
In one embodiment, the number of simulation frames of the data simulation unit may be fixed for any one traffic scenario, and thus the number of cycles to generate the simulation segments is also fixed.
In this embodiment, a simulated track segment of each frame is generated according to track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and current track planning parameters, after a simulated track segment of a previous frame is obtained, a simulated track segment corresponding to a next frame is generated according to track data of a next frame, road condition data of a next frame, road information of a next frame, route data of a next frame and current track planning parameters until a simulated track segment of a last frame is obtained, and a simulated track of a target vehicle is obtained according to the simulated track segments of multiple frames. The method is beneficial to calculating the cost value according to the simulated track in the follow-up process so as to realize adjustment of the track planning parameters.
In one embodiment, the data simulation unit includes a simulator and a trajectory planner, and the method further includes: transmitting the track data and the road condition data to a simulator in the data simulation unit, and transmitting the road information and the route data to a track planner in the data simulation unit, wherein the track planner comprises current track planning parameters; extracting track data of each frame from the track data and road condition data of each frame from the road condition data through a simulator, and sending the extracted track data of each frame and the road condition data of each frame to a track planner; extracting road information of each frame from the road information and route data of each frame from the route data through a track planner, generating a track planning result corresponding to the corresponding frame according to the track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and current track planning parameters, and sending the track planning result corresponding to the corresponding frame to a simulator; and generating a simulated track segment of the corresponding frame according to the track planning result by a simulator.
The data simulation unit comprises a simulator and a track planner, wherein the simulator is used for generating a simulation track according to a track planning result sent by the track planner. The track planner is used for generating a track planning result corresponding to the corresponding frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters sent by the simulator.
Sequentially extracting the track data of each frame in the track data and the road condition data of each frame in the road condition data according to the time sequence by the simulator, and sending the extracted data to the track planner. The track planner extracts the road information of the corresponding frame in the road information and the route data of the corresponding frame in the route data according to the received data, and the extracted track data, road condition data, road information and route data of the same frame can be used as one frame of data. The track planner can generate track planning results corresponding to the corresponding frames according to the frame data and the current track planning parameters, and sends the track planning results corresponding to the corresponding frames to the simulator. The simulator controls the target vehicle to run according to the track planning result until the time stamp corresponding to the next frame is reached, extracts track data of the next frame from the track data and road condition data of each frame from the road condition data, and sends the extracted track data of the next frame and the road condition data of the next frame to the track planner. And the track planner generates a track planning result corresponding to the next frame according to the data of the next frame and the current track planning parameters, and sends the track planning result corresponding to the next frame to the simulator, so that the simulator controls the target vehicle to run according to the track planning result until the time stamp corresponding to the next frame is reached. The simulator and the track planner repeat the steps of generating the simulated track segments until the simulated track segments of the last frame are obtained. And the final simulator outputs the simulated track of the target vehicle according to the simulated track fragments of the multiple frames.
In this embodiment, through the circulation between the simulator and the track planner, a multi-frame simulated track segment is generated, and finally, a simulated track of the target vehicle is generated, and in the adjustment process of the current track planning parameter, the specific track planning mode of the track planner is not concerned, and only the track planning result output by the track planner is needed, so that the simulated track of the target vehicle can be generated. The parameter adjustment is realized independently of the track planner, the method is applicable to any track planning method in various traffic scenes, and the parameter accuracy of a track planning algorithm is effectively improved.
In one embodiment, as shown in fig. 3, the step of adjusting the current trajectory planning parameter includes:
And step 304, the data simulation unit is used for taking the adjusted track planning parameters as current track planning parameters, and the step of generating the simulated track of the target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameters by the data simulation unit is returned to until the preset conditions are met, and the parameter adjustment is stopped, so that the target track planning parameters are obtained.
The current track planning parameter may be a parameter preset by the server and to be adjusted. And the server acquires the current track planning parameters of the data simulation unit after calculating the cost value of the simulated track. The data simulation unit comprises a simulator and a track planner, and the current track planning parameters are parameters of the track planner. The server can call a non-gradient optimizer, input the current track planning parameters and cost values into the non-gradient optimizer, adjust the current track planning parameters within a parameter adjustment range by the non-gradient optimizer by adopting a Bayesian method to obtain adjusted track planning parameters, the non-gradient optimizer inputs the adjusted track planning parameters into a data simulation unit, the data simulation unit returns the adjusted track planning parameters as the current track planning parameters to the step of generating a simulated track of the target vehicle by the data simulation unit according to the track data, road condition data, road information, route data and the current track planning parameters, and repeat the step of parameter adjustment until preset conditions are met, and the parameter adjustment is stopped to obtain the target track planning parameters. The preset condition may be that the current trajectory planning parameter has reached an optimal value within the parameter adjustment range.
In this embodiment, the non-gradient optimizer adjusts the current track planning parameter within the parameter adjustment range, so that a new track planning parameter can be obtained by rapid calculation, a simulated track is generated again according to the new track planning parameter, cost calculation is performed on the simulated track, a cost value corresponding to the simulated track is obtained, the non-gradient optimizer adjusts the current track planning parameter within the parameter adjustment range, and the target track planning parameter is obtained by iterative loop.
In one embodiment, as shown in fig. 4, there is provided a trajectory data processing device including: a data acquisition module 402, a data simulation module 404, a cost calculation module 406, and a parameter adjustment module 408, wherein:
the data obtaining module 402 is configured to obtain track data of the target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period, and route data of the target vehicle in the preset time period.
The data simulation module 404 is configured to input the track data, the road condition data, the road information and the route data into the data simulation unit, where the data simulation unit includes current track planning parameters, and generate, by the data simulation unit, a simulated track of the target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameters.
And the cost calculation module 406 is configured to perform cost calculation on the simulated track, so as to obtain a cost value corresponding to the simulated track.
The parameter adjustment module 408 is configured to adjust the current track planning parameter according to the cost value, obtain an adjusted track planning parameter, and return the adjusted track planning parameter to a step of generating, by the data simulation unit, a simulated track of the target vehicle according to the track data, the road condition data, the road information, the route data and the current track planning parameter, until a preset condition is satisfied, and stop parameter adjustment, thereby obtaining the target track planning parameter.
In one embodiment, the data simulation module 404 is further configured to extract, by the data simulation unit, track data of each frame in the track data, road condition data of each frame in the road condition data, road information of each frame in the road information, and route data of each frame in the route data; generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; after the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
In one embodiment, the data simulation unit includes a simulator and a trajectory planner, and the data simulation module 404 is further configured to send the trajectory data and the road condition data to the simulator in the data simulation unit, and send the road information and the route data to the trajectory planner in the data simulation unit, where the trajectory planner includes current trajectory planning parameters; extracting track data of each frame from the track data and road condition data of each frame from the road condition data through a simulator, and sending the extracted track data of each frame and the road condition data of each frame to a track planner; extracting road information of each frame from the road information and route data of each frame from the route data through a track planner, generating a track planning result corresponding to the corresponding frame according to the track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and current track planning parameters, and sending the track planning result corresponding to the corresponding frame to a simulator; and generating a simulated track segment of the corresponding frame according to the track planning result by a simulator.
In one embodiment, the cost calculation module 406 is further configured to calculate a similarity between the trajectory data and the simulated trajectory; and calculating according to the similarity to obtain the cost value corresponding to the simulation track.
In one embodiment, the cost calculation module 406 is further configured to determine, in the simulated trajectory, driving trajectory data corresponding to the preset driving parameter; determining driving road condition data corresponding to preset driving parameters in the road condition data; and calculating the cost value corresponding to the simulated track according to the driving track data and the driving road condition data.
In one embodiment, the parameter adjustment module 408 is further configured to input the current trajectory planning parameter and the cost value into the non-gradient optimizer, adjust the current trajectory planning parameter within a parameter adjustment range according to the cost value by the non-gradient optimizer, obtain an adjusted trajectory planning parameter, and send the adjusted trajectory planning parameter to the data simulation unit; and returning the regulated track planning parameters serving as current track planning parameters through the data simulation unit to the step of generating a simulated track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters until the preset conditions are met, and stopping parameter regulation to obtain the target track planning parameters.
For specific limitations of the track data processing device, reference may be made to the above limitation of the track data processing method, and no further description is given here. The respective modules in the above-described trajectory data processing device may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer device is used for storing data of a track data processing method. The communication interface of the computer device is used for connecting and communicating with an external terminal. The computer readable instructions when executed by a processor implement a track data processing method.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
A computer device comprising a memory and one or more processors, the memory having stored thereon computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the steps of the various method embodiments described above.
One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps in the various method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the processes of the methods of the embodiments described above may be accomplished by instructing the associated hardware by computer readable instructions stored on a non-transitory computer readable storage medium, which when executed may comprise processes of embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be regarded as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (20)
- A track data processing method, comprising:acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;Performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; andAnd adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- The method of claim 1, wherein the generating, by the data modeling unit, a modeled trajectory of the target vehicle based on the trajectory data, the road condition data, the road information, the course data, and the current trajectory planning parameter comprises:extracting track data of each frame from the track data, road condition data of each frame from the road condition data, road information of each frame from the road information and route data of each frame from the route data through the data simulation unit;Generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; andAfter the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
- The method of claim 2, wherein the data simulation unit comprises a simulator and a trajectory planner, the method further comprising:transmitting the track data and the road condition data to a simulator in the data simulation unit, and transmitting the road information and the route data to a track planner in the data simulation unit, wherein the track planner comprises the current track planning parameters;extracting track data of each frame from the track data and road condition data of each frame from the road condition data through the simulator, and sending the extracted track data of each frame and the road condition data of each frame to the track planner;Extracting road information of each frame from the road information and route data of each frame from the route data through the track planner, generating a track planning result corresponding to the corresponding frame according to the track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and the current track planning parameter, and sending the track planning result corresponding to the corresponding frame to the simulator; andAnd generating a simulated track segment of the corresponding frame according to the track planning result by the simulator.
- The method of claim 1, wherein the calculating the cost for the simulated track to obtain the cost value corresponding to the simulated track comprises:calculating the similarity between the track data and the simulated track; andAnd calculating the cost value corresponding to the simulation track according to the similarity.
- The method of claim 1, wherein the calculating the cost for the simulated track to obtain the cost value corresponding to the simulated track comprises:determining driving track data corresponding to preset driving parameters in the simulation track;Determining driving road condition data corresponding to the preset driving parameters in the road condition data; andAnd calculating the cost value corresponding to the simulated track according to the driving track data and the driving road condition data.
- The method according to claim 1, wherein the step of adjusting the current trajectory planning parameter according to the cost value to obtain an adjusted trajectory planning parameter, and returning the adjusted trajectory planning parameter as the current trajectory planning parameter to the step of generating, by the data simulation unit, a simulated trajectory of the target vehicle according to the trajectory data, the road condition data, the road information, the route data, and the current trajectory planning parameter until a preset condition is satisfied, and stopping parameter adjustment, and obtaining a target trajectory planning parameter includes:inputting the current track planning parameters and the cost values into a non-gradient optimizer, adjusting the current track planning parameters in a parameter adjusting range by the non-gradient optimizer according to the cost values to obtain adjusted track planning parameters, and sending the adjusted track planning parameters to the data simulation unit; andAnd returning the regulated track planning parameters serving as the current track planning parameters through the data simulation unit to the step of generating the simulated track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters until the preset conditions are met, and stopping parameter regulation to obtain the target track planning parameters.
- A trajectory data processing device, comprising:the data acquisition module is used for acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;the data simulation module is used for inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and a simulation track of the target vehicle is generated through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;The cost calculation module is used for calculating the cost of the simulated track to obtain a cost value corresponding to the simulated track; andAnd the parameter adjusting module is used for adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulating unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- The apparatus of claim 7, wherein the data simulation module is further configured to extract track data of each frame from the track data, road condition data of each frame from the road condition data, road information of each frame from the road information, and route data of each frame from the route data by the data simulation unit; generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; and after the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
- The apparatus of claim 7, wherein the cost calculation module is further configured to calculate a similarity between the trajectory data and the simulated trajectory; and calculating the cost value corresponding to the simulation track according to the similarity.
- The apparatus of claim 7, wherein the parameter adjustment module is further configured to input the current trajectory planning parameter and the cost value into a non-gradient optimizer, adjust the current trajectory planning parameter within a parameter adjustment range according to the cost value by the non-gradient optimizer, obtain an adjusted trajectory planning parameter, and send the adjusted trajectory planning parameter to the data simulation unit; and returning the adjusted track planning parameter serving as the current track planning parameter through the data simulation unit to the step of generating a simulated track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the steps of:acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; andAnd adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- The computer device of claim 11, wherein the processor when executing the computer readable instructions further performs the steps of: extracting track data of each frame from the track data, road condition data of each frame from the road condition data, road information of each frame from the road information and route data of each frame from the route data through the data simulation unit; generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; and after the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
- The computer device of claim 12, wherein the data simulation unit comprises a simulator and a trajectory planner, the processor when executing the computer readable instructions further performing the steps of: transmitting the track data and the road condition data to a simulator in the data simulation unit, and transmitting the road information and the route data to a track planner in the data simulation unit, wherein the track planner comprises the current track planning parameters; extracting track data of each frame from the track data and road condition data of each frame from the road condition data through the simulator, and sending the extracted track data of each frame and the road condition data of each frame to the track planner; extracting road information of each frame from the road information and route data of each frame from the route data through the track planner, generating a track planning result corresponding to the corresponding frame according to the track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and the current track planning parameter, and sending the track planning result corresponding to the corresponding frame to the simulator; and generating a simulated track segment of the corresponding frame according to the track planning result by the simulator.
- The computer device of claim 11, wherein the processor when executing the computer readable instructions further performs the steps of: calculating the similarity between the track data and the simulated track; and calculating the cost value corresponding to the simulation track according to the similarity.
- The computer device of claim 11, wherein the processor when executing the computer readable instructions further performs the steps of: inputting the current track planning parameters and the cost values into a non-gradient optimizer, adjusting the current track planning parameters in a parameter adjusting range by the non-gradient optimizer according to the cost values to obtain adjusted track planning parameters, and sending the adjusted track planning parameters to the data simulation unit; and returning the adjusted track planning parameter serving as the current track planning parameter through the data simulation unit to the step of generating a simulated track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:acquiring track data of a target vehicle in a preset time period, road condition data of the target vehicle in a preset distance range, road information corresponding to the target vehicle in the preset time period and route data of the target vehicle in the preset time period;inputting the track data, the road condition data, the road information and the route data into a data simulation unit, wherein the data simulation unit comprises current track planning parameters, and generating a simulation track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameters;performing cost calculation on the simulated track to obtain a cost value corresponding to the simulated track; andAnd adjusting the current track planning parameter according to the cost value to obtain an adjusted track planning parameter, taking the adjusted track planning parameter as the current track planning parameter, and returning to the step of generating the simulated track of the target vehicle by the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
- The storage medium of claim 16, wherein the computer readable instructions, when executed by the processor, further perform the steps of: extracting track data of each frame from the track data, road condition data of each frame from the road condition data, road information of each frame from the road information and route data of each frame from the route data through the data simulation unit; generating a simulated track segment of each frame according to the track data of each frame, the road condition data of each frame, the road information of each frame, the route data of each frame and the current track planning parameters; and after the simulated track segment of the previous frame is obtained, generating a simulated track segment corresponding to the next frame according to the track data of the next frame, the road condition data of the next frame, the road information of the next frame, the road data of the next frame and the current track planning parameters until the simulated track segment of the last frame is obtained, and obtaining the simulated track of the target vehicle according to the simulated track segments of the multiple frames.
- The storage medium of claim 17, wherein the data modeling unit includes a simulator and a trajectory planner, the computer readable instructions when executed by the processor further performing the steps of: transmitting the track data and the road condition data to a simulator in the data simulation unit, and transmitting the road information and the route data to a track planner in the data simulation unit, wherein the track planner comprises the current track planning parameters; extracting track data of each frame from the track data and road condition data of each frame from the road condition data through the simulator, and sending the extracted track data of each frame and the road condition data of each frame to the track planner; extracting road information of each frame from the road information and route data of each frame from the route data through the track planner, generating a track planning result corresponding to the corresponding frame according to the track data of each frame, road condition data of each frame, road information of each frame, route data of each frame and the current track planning parameter, and sending the track planning result corresponding to the corresponding frame to the simulator; and generating a simulated track segment of the corresponding frame according to the track planning result by the simulator.
- The storage medium of claim 16, wherein the computer readable instructions, when executed by the processor, further perform the steps of: calculating the similarity between the track data and the simulated track; and calculating the cost value corresponding to the simulation track according to the similarity.
- The storage medium of claim 16, wherein the computer readable instructions, when executed by the processor, further perform the steps of: inputting the current track planning parameters and the cost values into a non-gradient optimizer, adjusting the current track planning parameters in a parameter adjusting range by the non-gradient optimizer according to the cost values to obtain adjusted track planning parameters, and sending the adjusted track planning parameters to the data simulation unit; and returning the adjusted track planning parameter serving as the current track planning parameter through the data simulation unit to the step of generating a simulated track of the target vehicle through the data simulation unit according to the track data, the road condition data, the road information, the route data and the current track planning parameter until a preset condition is met, and stopping parameter adjustment to obtain the target track planning parameter.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/138520 WO2022133775A1 (en) | 2020-12-23 | 2020-12-23 | Trajectory data processing method and apparatus, computer device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116097193A true CN116097193A (en) | 2023-05-09 |
Family
ID=82158542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080103187.1A Pending CN116097193A (en) | 2020-12-23 | 2020-12-23 | Track data processing method, track data processing device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116097193A (en) |
| WO (1) | WO2022133775A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116069041B (en) * | 2023-03-20 | 2023-06-23 | 北京集度科技有限公司 | Track planning method, device, vehicle and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106926844B (en) * | 2017-03-27 | 2018-10-19 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| US10599161B2 (en) * | 2017-08-08 | 2020-03-24 | Skydio, Inc. | Image space motion planning of an autonomous vehicle |
| CN109885891B (en) * | 2019-01-24 | 2022-09-30 | 中国科学院合肥物质科学研究院 | Intelligent vehicle GPU parallel acceleration trajectory planning method |
| CN112068586B (en) * | 2020-08-04 | 2021-08-13 | 西安交通大学 | Space-time joint optimization four-rotor unmanned aerial vehicle trajectory planning method |
-
2020
- 2020-12-23 WO PCT/CN2020/138520 patent/WO2022133775A1/en unknown
- 2020-12-23 CN CN202080103187.1A patent/CN116097193A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022133775A1 (en) | 2022-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921200B (en) | Method, apparatus, device and medium for classifying driving scene data | |
| CN110197027B (en) | Automatic driving test method and device, intelligent equipment and server | |
| US11226205B2 (en) | Method and device for reducing intermediate points in a polygon | |
| CN110688920B (en) | Unmanned control method and device and server | |
| CN113383283B (en) | Perceptual information processing method, apparatus, computer device, and storage medium | |
| CN111923919B (en) | Vehicle control method, vehicle control device, computer equipment and storage medium | |
| CN112406905B (en) | Data processing method and device based on vehicle, computer and storage medium | |
| CN112815948B (en) | Method, device, computer equipment and storage medium for identifying yaw mode | |
| CN112382165A (en) | Driving strategy generation method, device, medium, equipment and simulation system | |
| CN110297484B (en) | Unmanned control method, device, computer equipment and storage medium | |
| CN110751040A (en) | Three-dimensional object detection method and device, electronic equipment and storage medium | |
| CN115294539A (en) | Multitask detection method and device, storage medium and terminal | |
| JP2023038178A (en) | Method, apparatus and computer program for generating input feature map of artificial intelligence model to detect object based on lidar | |
| CN116097193A (en) | Track data processing method, track data processing device, computer equipment and storage medium | |
| CN109492835B (en) | Method for determining vehicle control information, method for training model and related device | |
| CN112671487A (en) | Vehicle testing method, server and testing vehicle | |
| CN110826695B (en) | Data processing method, device and computer readable storage medium | |
| CN116859931A (en) | Training method of track planning model, vehicle control mode and device | |
| US20230410338A1 (en) | Method for optimizing depth estimation model, computer device, and storage medium | |
| CN112507857B (en) | Lane line updating method, device, equipment and storage medium | |
| CN115782921A (en) | Environment sensing method and device for automatic driving and electronic equipment | |
| US20240202393A1 (en) | Motion planning | |
| CN113501007B (en) | Path trajectory planning method, device and terminal based on automatic driving | |
| CN113156961B (en) | Driving control model training method, driving control method and related device | |
| CN114104005A (en) | Decision-making method, device and equipment of automatic driving equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |