Running track optimization method and device, electronic equipment and readable storage medium

Abstract

The invention provides a driving track optimization method and device, electronic equipment and a readable storage medium. According to one example of the disclosure, the method is applied to a target vehicle; the method comprises the following steps: acquiring at least two driving tracks predicted based on driving intentions of surrounding vehicles; according to the trajectory parameters of the at least two driving trajectories, calculating driving costs corresponding to the at least two driving trajectories, and determining a target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost generated when the vehicle runs according to the driving track; and optimizing the track parameters of the target driving track. According to the method and the device, the driving track with relatively high driving cost can be accurately optimized, so that the driving efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device and readable storage medium for optimizing a driving trajectory. Background Art

[0002] An autonomous vehicle is a vehicle that can complete driving tasks autonomously without human intervention. In actual applications, autonomous vehicles usually travel on the same road as non-autonomous vehicles. For autonomous vehicles, the driving intentions of non-autonomous vehicles are unclear.

[0003] For example, autonomous driving vehicle A can drive on the left side of the road, and non-autonomous driving vehicle B can drive on the right side of the road. When autonomous driving vehicle A detects that non-autonomous driving vehicle B has turned on the left turn signal, but has not turned after one minute, the driving intention of non-autonomous driving vehicle B is unclear to autonomous driving vehicle A. Based on this, the autonomous driving vehicle can predict the driving trajectory according to the driving intention of the non-autonomous driving vehicle, and obtain at least two driving trajectories that are consistent with the driving intention of the non-autonomous driving vehicle.

[0004] In the above scenario, the at least two driving trajectories can be optimized to reduce the driving cost of the autonomous driving vehicle.

[0005] In current technology, since the probabilities corresponding to different driving intentions of non-autonomous driving vehicles are different, at least two driving trajectories corresponding to the driving intentions are usually comprehensively optimized according to the probability values ​​corresponding to the different driving intentions.

[0006] Among them, the at least two driving trajectories include a driving trajectory with a lower probability value but a higher driving cost. Since the probability value is calculated based on all driving data, it is not accurate to apply it directly to the current scenario; and the optimization process is to comprehensively optimize all driving trajectories. Therefore, when the driving intention of the non-autonomous driving vehicle is a driving intention with a lower probability value, and the autonomous driving vehicle drives according to the driving trajectory corresponding to the driving intention, a larger driving cost will be generated, thereby affecting the driving efficiency. Summary of the invention

[0007] The present disclosure provides a method for optimizing a driving trajectory, which is applied to a target vehicle; the method comprises:

[0008] Obtain at least two driving trajectories predicted based on the driving intentions of surrounding vehicles;

[0009] Calculate driving costs corresponding to the at least two driving trajectories respectively according to the trajectory parameters of the at least two driving trajectories, and determine a target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory;

[0010] The trajectory parameters of the target driving trajectory are optimized.

[0011] Optionally, the method further includes:

[0012] The at least two driving trajectories are iteratively optimized according to the following method until an iteration stop condition is met:

[0013] recalculating the driving costs respectively corresponding to the at least two driving trajectories according to the optimized trajectory parameters of the target driving trajectory and the trajectory parameters of other driving trajectories in the at least two driving trajectories, and re-determining the target driving trajectory with the maximum driving cost from the at least two driving trajectories;

[0014] The trajectory parameters of the target driving trajectory are optimized.

[0015] Optionally, the trajectory parameters include a plurality of driving trajectory points;

[0016] Optimizing the trajectory parameters of the target driving trajectory includes:

[0017] Based on the optimization algorithm, the optimal variable value of the objective function is calculated; wherein the objective function is used to characterize the driving cost; the optimal variable value is the parameter value corresponding to the multiple driving trajectory points respectively that satisfies the minimum driving cost.

[0018] Optionally, before obtaining at least two driving trajectories predicted based on the driving intentions of surrounding vehicles, the method further includes:

[0019] In response to detecting that the driving intention of the surrounding vehicles is ambiguous, determining at least two driving intentions of the surrounding vehicles;

[0020] Based on the at least two driving intentions, a driving trajectory of the target vehicle is predicted and calculated to obtain at least two driving trajectories corresponding to the at least two driving intentions.

[0021] Optionally, the driving trajectory includes a common driving trajectory traveled before the intention of the surrounding vehicles is clear, and an independent driving trajectory traveled after the intention of the surrounding vehicles is clear.

[0022] Optionally, in response to detecting that the driving intention of the surrounding vehicles is unclear, before determining at least two driving intentions of the surrounding vehicles, the method further includes:

[0023] Monitor the driving status of surrounding vehicles and obtain monitoring data;

[0024] Determining, based on the monitoring data, whether the surrounding vehicles meet a condition of unclear driving intention;

[0025] If the surrounding vehicles satisfy the condition that the driving intention is unclear, it is determined that the driving intention of the surrounding vehicles is unclear.

[0026] Optionally, the monitoring data includes image data and / or laser radar data;

[0027] Determining whether the surrounding vehicles meet the condition of unclear driving intention according to the monitoring data includes:

[0028] The image data and / or laser radar data are used as input parameters and input into a trajectory prediction model for prediction calculation to obtain a future driving trajectory corresponding to the surrounding vehicles; wherein the trajectory prediction model is a neural network model obtained by supervised learning training based on historical image data and / or laser radar data and historical driving trajectories;

[0029] Determine whether the number of future driving trajectories is greater than 1;

[0030] If the surrounding vehicles satisfy the condition that the driving intention is unclear, determining that the driving intention of the surrounding vehicles is unclear includes:

[0031] If the number of the future driving trajectories is greater than 1, it is determined that the driving intention of the surrounding vehicles is unclear.

[0032] Optionally, before calculating the driving costs respectively corresponding to the at least two driving trajectories according to the trajectory parameters of the at least two driving trajectories, the method further includes:

[0033] Generating coarse paths corresponding to the at least two driving trajectories respectively according to trajectory parameters of the at least two driving trajectories, and performing cost pre-evaluation on the coarse paths to obtain pre-evaluated costs corresponding to the at least two driving trajectories respectively;

[0034] Determining, from the at least two driving trajectories, at least a portion of the driving trajectories whose pre-evaluation costs satisfy a preset evaluation condition;

[0035] Calculating driving costs corresponding to the at least two driving trajectories respectively according to the trajectory parameters of the at least two driving trajectories includes:

[0036] Driving costs corresponding to at least part of the driving trajectories are calculated according to the trajectory parameters of the at least two driving trajectories.

[0037] Optionally, the parameter value includes at least one parameter value shown below:

[0038] Position value; speed value; acceleration value; driving direction value.

[0039] The present disclosure also provides a driving trajectory optimization device, which is applied to a target vehicle; the device comprises:

[0040] An acquisition unit, used to acquire at least two driving trajectories predicted based on the driving intentions of surrounding vehicles;

[0041] A calculation unit, configured to calculate driving costs corresponding to the at least two driving trajectories respectively according to trajectory parameters of the at least two driving trajectories, and determine a target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory;

[0042] The optimization unit is used to optimize the trajectory parameters of the target driving trajectory.

[0043] The present disclosure also provides an electronic device, comprising a communication interface, a processor, a memory and a bus, wherein the communication interface, the processor and the memory are interconnected via the bus;

[0044] The memory stores machine-readable instructions, and the processor executes the driving trajectory optimization method by calling the machine-readable instructions.

[0045] The present disclosure also provides a machine-readable storage medium, wherein the machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by a processor, the driving trajectory optimization method is implemented.

[0046] The technical solution provided by the present disclosure may at least include the following beneficial effects:

[0047] Through the above embodiments, at least two driving trajectories predicted based on the driving intentions of surrounding vehicles can be obtained; according to the trajectory parameters of the at least two driving trajectories, the driving costs corresponding to the at least two driving trajectories can be calculated, and the target driving trajectory with the largest driving cost can be determined from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory; the trajectory parameters of the target driving trajectory can be optimized. First, this method is not based on probability values ​​for calculation, thus avoiding inaccurate calculation results caused by inaccurate probability values; second, since the autonomous driving vehicle optimizes the trajectory parameters of the driving trajectory with the largest driving cost, when the autonomous driving vehicle travels along the driving trajectory, a relatively small driving cost will be generated, thereby improving driving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 This is an application scenario diagram of a driving trajectory optimization method according to an exemplary embodiment.

[0050] Figure 2 It is a flow chart of a method for optimizing a driving trajectory according to an exemplary embodiment.

[0051] Figure 3 The diagram is a scene diagram of a driving trajectory according to an exemplary embodiment.

[0052] Figure 4 It is a block diagram of a driving trajectory optimization device according to an exemplary embodiment.

[0053] Figure 5 It is a hardware structure diagram of an electronic device in which a driving trajectory optimization device is located according to an exemplary embodiment. DETAILED DESCRIPTION

[0054] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure.

[0055] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in the present disclosure. In some other embodiments, the steps included in the method may be more or less than those described in the present disclosure.

[0056] The following is an introduction to the driving trajectory optimization method provided by the present disclosure through specific embodiments and in combination with specific application scenarios. The method optimizes the trajectory parameters of the driving trajectory with the maximum driving cost, so that when the autonomous driving vehicle drives along the driving trajectory, a relatively small driving cost is generated, which can improve driving efficiency.

[0057] During implementation, at least two driving trajectories predicted based on the driving intentions of surrounding vehicles may be obtained;

[0058] According to the trajectory parameters of the at least two driving trajectories, the driving costs corresponding to the at least two driving trajectories can be calculated, and a target driving trajectory with the maximum driving cost can be determined from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory;

[0059] The trajectory parameters of the target driving trajectory may be optimized.

[0060] Through the above embodiments, at least two driving trajectories predicted based on the driving intentions of surrounding vehicles can be obtained; according to the trajectory parameters of the at least two driving trajectories, the driving costs corresponding to the at least two driving trajectories can be calculated, and the target driving trajectory with the largest driving cost can be determined from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory; the trajectory parameters of the target driving trajectory can be optimized. First, this method is not based on probability values ​​for calculation, thus avoiding inaccurate calculation results caused by inaccurate probability values; second, since the autonomous driving vehicle optimizes the trajectory parameters of the driving trajectory with the largest driving cost, when the autonomous driving vehicle travels along the driving trajectory, a relatively small driving cost will be generated, thereby improving driving efficiency.

[0061] The present disclosure is described below through specific embodiments and in combination with specific application scenarios.

[0062] See also Figure 1 , Figure 1 FIG. 1 is an application scenario diagram of a method for optimizing a driving trajectory according to an exemplary embodiment. Figure 1 As shown, the target vehicle may be an autonomous driving vehicle A, and the surrounding vehicles may be non-autonomous driving vehicles B. The autonomous driving vehicle A may be driven in the right lane of the road, and the non-autonomous driving vehicle B may be driven in the left lane of the road.

[0063] The autonomous driving vehicle A can monitor the driving status of the non-autonomous driving vehicle B and obtain monitoring data. For example, it can be monitored that the non-autonomous driving vehicle B is on the lane dividing line between the left lane and the right lane. Based on this, the autonomous driving vehicle A can determine that the non-autonomous driving vehicle B meets the condition of unclear driving intention and further determine that the driving intention of the non-autonomous driving vehicle B is unclear.

[0064] In this case, the autonomous driving vehicle A determines at least two driving intentions of the non-autonomous driving vehicle B in response to the unclear driving intention of the non-autonomous driving vehicle B, and can predict and calculate the driving trajectory of the target vehicle based on the at least two driving intentions to obtain at least two driving trajectories corresponding to the at least two driving intentions.

[0065] The autonomous driving vehicle A can obtain the at least two driving trajectories, and can calculate the driving costs corresponding to the at least two driving trajectories respectively according to the trajectory parameters of the at least two driving trajectories, and determine the target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost can represent the cost incurred by the vehicle traveling along the driving trajectory; the autonomous driving vehicle A can optimize the trajectory parameters of the target driving trajectory.

[0066] The autonomous driving vehicle A may also iteratively optimize at least two driving trajectories according to the following method until an iteration stop condition is met:

[0067] According to the optimized trajectory parameters of the target driving trajectory and the trajectory parameters of other driving trajectories in the at least two driving trajectories, the driving costs corresponding to the at least two driving trajectories are recalculated, and the target driving trajectory with the maximum driving cost is re-determined from the at least two driving trajectories; and the trajectory parameters of the target driving trajectory are optimized.

[0068] Wherein, the trajectory parameters include multiple driving trajectory points; the autonomous driving vehicle A can calculate the optimal variable value of the objective function based on the optimization algorithm; wherein, the objective function can be used to characterize the driving cost; the optimal variable value can be the parameter value corresponding to the multiple driving trajectory points that satisfies the minimum driving cost.

[0069] The driving trajectory may include a common driving trajectory traveled before the intention of the surrounding vehicles is clear, and an independent driving trajectory traveled after the intention of the surrounding vehicles is clear.

[0070] Wherein, the monitoring data may include image data and / or lidar data; the autonomous driving vehicle A may use the image data and / or lidar data as input parameters and input them into a trajectory prediction model for prediction calculation to obtain a future driving trajectory corresponding to the surrounding vehicles; wherein the trajectory prediction model may be a neural network model obtained through supervised learning training based on historical image data and / or lidar data and historical driving trajectories; the autonomous driving vehicle A may determine whether the number of future driving trajectories is greater than 1; if the number of future driving trajectories is greater than 1, it may be determined that the driving intention of the surrounding vehicles is unclear.

[0071] Among them, the autonomous driving vehicle A can also generate coarse paths corresponding to at least two driving trajectories according to the trajectory parameters of at least two driving trajectories, and pre-evaluate the cost of the coarse paths to obtain pre-evaluated costs corresponding to at least two driving trajectories, before calculating the driving costs corresponding to at least two driving trajectories according to the trajectory parameters of at least two driving trajectories; determine at least part of the driving trajectories whose pre-evaluated costs meet the preset evaluation conditions from the at least two driving trajectories; and calculate the driving costs corresponding to at least part of the driving trajectories according to the trajectory parameters of at least two driving trajectories.

[0072] The parameter value includes at least one of the following parameter values: position value; speed value; acceleration value; driving direction value.

[0073] See also Figure 2 , Figure 2 It is a flow chart of a method for optimizing a driving trajectory according to an exemplary embodiment.

[0074] The above-mentioned target vehicle may refer to an autonomous driving vehicle or a vehicle with an autonomous driving function, and the present disclosure does not limit this.

[0075] like Figure 2 As shown, the target vehicle can perform the following steps:

[0076] Step 202: Obtain at least two driving trajectories predicted based on the driving intentions of surrounding vehicles.

[0077] Among them, the surrounding vehicles may refer to one vehicle or multiple vehicles. When the surrounding vehicles refer to one vehicle, the driving intention may refer to the driving intention of the vehicle. When the surrounding vehicles refer to multiple vehicles, the driving intention may refer to a combination of the driving intentions of the multiple vehicles.

[0078] For example, the surrounding vehicles may include multiple vehicles, and the multiple vehicles may include vehicle_1 and vehicle_2. The driving intention of vehicle_1 may include driving intention_11 and driving intention_12, and the driving intention of vehicle_2 may include driving intention_21 and driving intention_22. The driving intentions of the surrounding vehicles may include driving intention combination_1, driving intention combination_2, driving intention combination_3 and driving intention combination_4. The driving intention combination_1 may include driving intention_11 and driving intention_21; the driving intention combination_2 may include driving intention_11 and driving intention_22; the driving intention combination_3 may include driving intention_12 and driving intention_21; and the driving intention combination_4 may include driving intention_12 and driving intention_22.

[0079] The driving intention may refer to the future driving trajectory of the surrounding vehicles. For example, when the surrounding vehicles are on the lane dividing line between the left lane and the right lane, the future driving trajectory of the surrounding vehicles may be to turn left or to go straight.

[0080] The specific content of the trajectory parameter can be set according to actual needs, and the present disclosure does not limit this. For example, the trajectory parameter can include multiple driving trajectory points, and the driving trajectory point can refer to the driving coordinate point of the target vehicle on the road.

[0081] The triggering conditions for obtaining the driving trajectory can be set according to actual needs, and this disclosure does not limit this.

[0082] In one embodiment shown, before obtaining at least two driving trajectories predicted based on the driving intentions of surrounding vehicles, the target vehicle can determine at least two driving intentions of the surrounding vehicles in response to detecting that the driving intentions of the surrounding vehicles are unclear, and can predict and calculate the driving trajectory of the target vehicle based on the at least two driving intentions to obtain at least two driving trajectories corresponding to the at least two driving intentions.

[0083] The specific method of the prediction calculation can be set according to actual needs, and the present disclosure does not limit this. For example, the prediction calculation can be performed based on the driving intention through the prediction model carried by the target vehicle.

[0084] It should be noted that, for each of the at least two driving intentions, a corresponding driving trajectory can be predicted and calculated to cope with changes in driving states of surrounding vehicles.

[0085] For example, the at least two driving intentions may include driving intention_1 and driving intention_2, and the at least two driving trajectories predicted and calculated based on the at least two driving intentions may include driving trajectory_1 corresponding to driving intention_1 and driving trajectory_2 corresponding to driving intention_2.

[0086] In this way, the corresponding driving trajectory can be predicted and calculated for each driving intention, so as to cope with the changes in the driving status of surrounding vehicles and improve the driving safety of the target vehicle.

[0087] The specific monitoring method for the unclear driving intention can be set according to actual needs, and the present disclosure does not limit this.

[0088] In one embodiment shown, the target vehicle can monitor the driving status of surrounding vehicles to obtain monitoring data; based on the monitoring data, determine whether the surrounding vehicles meet the condition of unclear driving intention; if the surrounding vehicles meet the condition of unclear driving intention, determine that the driving intention of the surrounding vehicles is unclear.

[0089] Among them, the specific content of the driving status can be set according to actual needs, and the present disclosure does not limit this.

[0090] For example, the driving status may include the driving speed, direction, light switch status, whether the vehicle crosses the line, etc. of the surrounding vehicles.

[0091] Among them, the condition of unclear driving intention can be set according to actual needs, and the present disclosure does not limit this.

[0092] For example, the conditions for unclear driving intention may include surrounding vehicles crossing the line for a preset time, surrounding vehicles turning on turn signals but not turning within a preset time, surrounding vehicles decelerating abnormally, etc.

[0093] The specific method for determining whether the surrounding vehicles meet the condition of unclear driving intention can be set according to actual needs, and the present disclosure does not limit this.

[0094] For example, the monitoring data can be input into a trajectory prediction model, and the trajectory prediction model makes a judgment based on the monitoring data; a list of driving data with unclear driving intentions can also be pre-stored, and the driving data in the list can be matched with the above-mentioned monitoring data. If the match is successful, it can be indicated that the driving intention is unclear.

[0095] In one embodiment shown, the monitoring data may include image data and / or lidar data; the target vehicle may use the image data and / or lidar data as input parameters and input them into a trajectory prediction model for prediction calculation to obtain a future driving trajectory corresponding to the surrounding vehicles; wherein the trajectory prediction model is a neural network model obtained by supervised learning training based on historical image data and / or lidar data and historical driving trajectories; determining whether the number of future driving trajectories is greater than 1; if the number of future driving trajectories is greater than 1, it can be determined that the driving intentions of the surrounding vehicles are unclear.

[0096] The image data may refer to the collected two-dimensional data including the driving status of the surrounding vehicles, and the laser radar data may refer to the scanned three-dimensional data including the driving status of the surrounding vehicles. In the present disclosure, the driving trajectory of the surrounding vehicles may be predicted and calculated in combination with the image data and the laser radar data, thereby improving the accuracy of the prediction.

[0097] The image data collection method can be set according to actual needs, and the present disclosure does not limit this. For example, the image data can be collected by an onboard image collection device.

[0098] The laser radar data collection method can be set according to actual needs, and the present disclosure does not limit this. For example, the image data can be collected by the laser radar collection device on board.

[0099] Among them, the trajectory prediction model can be a neural network model obtained by supervised learning training using historical image data and / or lidar data as input parameters and historical driving trajectories as labels.

[0100] Regarding the specific type of the trajectory prediction model, it can be any model that can be trained as described above and can be used to predict future driving trajectories, and the present disclosure does not limit this.

[0101] The target vehicle can predict and calculate the future driving trajectories corresponding to the surrounding vehicles based on the trajectory prediction model, and when it is determined that the number of the future driving trajectories is greater than 1, it can be determined that the driving intention of the surrounding vehicles is unclear.

[0102] For example, the target vehicle can predict and calculate the future driving trajectories corresponding to the surrounding vehicles based on the trajectory prediction model. When the number of the future driving trajectories is 2, it can be determined that the driving intention of the surrounding vehicles is unclear.

[0103] In this way, the model is used to determine the future driving trajectory of surrounding vehicles, which can improve the accuracy of the prediction and the efficiency of the prediction.

[0104] Step 204, based on the trajectory parameters of the at least two driving trajectories, calculate the driving costs corresponding to the at least two driving trajectories respectively, and determine the target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory.

[0105] The trajectory parameters may refer to initial trajectory parameters of the at least two driving trajectories. The target vehicle may calculate the driving costs corresponding to the at least two driving trajectories respectively according to the initial trajectory parameters, and may determine the target driving trajectory with the maximum driving cost.

[0106] For example, the at least two driving trajectories may include driving trajectory_1 and driving trajectory_2. The initial trajectory parameter corresponding to the driving trajectory_1 may be trajectory parameter_1, and the initial trajectory parameter corresponding to the driving trajectory_2 may be trajectory parameter_2. The target vehicle may calculate the driving cost_1 corresponding to the driving trajectory_1 and the driving cost_2 corresponding to the driving trajectory_2 based on the trajectory parameter_1 and the trajectory parameter_2. The target vehicle may determine that the target driving trajectory with the largest driving cost from the two driving trajectories is driving trajectory_1.

[0107] The specific indicators of the driving cost can be set according to actual needs, and this disclosure does not limit this.

[0108] For example, the driving cost may include time cost and / or space cost. Specifically, the time cost may include the driving time of the target vehicle to the same destination. The space cost may include the sum of the minimum distances between the target vehicle and the surrounding vehicles, the driving distance of the target vehicle to the same destination, the smoothness of the driving trajectory, etc.

[0109] In one embodiment shown, before calculating the driving costs corresponding to at least two driving trajectories respectively according to the trajectory parameters of at least two driving trajectories, the target vehicle can also generate coarse paths corresponding to at least two driving trajectories respectively according to the trajectory parameters of at least two driving trajectories, and pre-evaluate the cost of the coarse paths to obtain pre-evaluated costs corresponding to at least two driving trajectories respectively; from at least two driving trajectories, determine at least part of the driving trajectories whose pre-evaluated costs meet preset evaluation conditions; the target vehicle can calculate the driving costs corresponding to at least part of the driving trajectories respectively according to the trajectory parameters of at least two driving trajectories.

[0110] The at least two driving trajectories may include a driving trajectory with a lower driving cost, and at least part of the driving trajectory may not be optimized, thereby improving calculation efficiency.

[0111] Specifically, before calculating the driving costs respectively corresponding to at least two driving trajectories based on the trajectory parameters of the at least two driving trajectories, rough paths respectively corresponding to the at least two driving trajectories can be generated based on the trajectory parameters of the at least two driving trajectories, and the rough paths can be pre-evaluated. Based on the pre-evaluated driving costs, at least part of the driving trajectories that require subsequent cost optimization calculation can be determined from the at least two driving trajectories.

[0112] For example, the at least two driving trajectories may include driving trajectory_1, driving trajectory_2 and driving trajectory_3, the initial trajectory parameter corresponding to the driving trajectory_1 may be trajectory parameter_1, the initial trajectory parameter corresponding to the driving trajectory_2 may be trajectory parameter_2, and the initial trajectory parameter corresponding to the driving trajectory_3 may be trajectory parameter_3; the target vehicle may generate a coarse path_1 corresponding to the driving trajectory_1, a coarse path_2 corresponding to the driving trajectory_2, and a coarse path_3 corresponding to the driving trajectory_3 according to the trajectory parameter_1, trajectory parameter_2 and trajectory parameter_3, the target vehicle may perform a cost pre-evaluation on the three coarse paths to obtain pre-evaluation costs corresponding to the three driving trajectories respectively; the target vehicle may determine, based on the pre-evaluation costs, at least some driving trajectories (exemplarily, driving trajectory_1 and driving trajectory_2) from the three driving trajectories whose pre-evaluation costs meet the preset evaluation conditions.

[0113] The specific content of the preset evaluation condition can be set according to actual needs, and this disclosure does not limit this.

[0114] For example, the driving cost of the coarse path can be expressed as:

[0115] L=L steer -L obstacle +L len

[0116] Among them, L steer It can represent the total curvature of the driving track and can be used to measure the curvature of the driving track; L obstacle It can represent the sum of the minimum distances between the target vehicle and surrounding vehicles; L len It can represent the length of the driving trajectory of the target vehicle to reach the destination. The target vehicle can pre-evaluate the driving cost of the coarse path based on the above three pre-evaluation conditions.

[0117] In this way, the driving trajectories that need to be optimized can be pre-screened, thereby improving the calculation efficiency.

[0118] It should be noted that before optimizing the trajectory parameters of at least part of the driving trajectory, the rough path corresponding to at least part of the driving trajectory may be smoothed. The specific method of the smoothing may be set according to actual needs, and the present disclosure does not limit this.

[0119] Step 206: Optimize the trajectory parameters of the target driving trajectory.

[0120] In one embodiment shown, the driving trajectory may include a common driving trajectory that is driven before the intention of the surrounding vehicles is clear, and an independent driving trajectory that is driven after the intention of the surrounding vehicles is clear.

[0121] For example, see Figure 3 , Figure 3 FIG. 1 is a scene diagram of a driving trajectory according to an exemplary embodiment. Figure 3 As shown, the target vehicle may be an autonomous driving vehicle A, and the surrounding vehicles may be non-autonomous driving vehicles B. The autonomous driving vehicle A may be driven in the right lane of the road, and the non-autonomous driving vehicle B may be driven in the left lane of the road.

[0122] When the autonomous driving vehicle A determines that the driving intention of the non-autonomous driving vehicle B is unclear, it can obtain the driving trajectory_1 corresponding to the driving intention_1 and the driving trajectory_2 corresponding to the driving intention_2, wherein the driving trajectory_1 can include a public driving trajectory and an independent driving trajectory_1, and the driving trajectory_2 can include a public driving trajectory and an independent driving trajectory_2.

[0123] When the non-autonomous driving vehicle B is still in a driving state with unclear driving intention, the autonomous driving vehicle A can drive according to the public driving trajectory. When the driving intention of the non-autonomous driving vehicle B is clear, for example, the driving intention of the non-autonomous driving vehicle B is driving intention_1, then the autonomous driving vehicle A can drive according to the independent driving trajectory_1 corresponding to the driving intention_1.

[0124] In this way, it is possible to flexibly respond to changes in the driving status of surrounding vehicles and improve the driving flexibility of the target vehicle.

[0125] In one embodiment shown, the target vehicle may iteratively optimize at least two driving trajectories according to the following method until an iteration stop condition is met:

[0126] According to the optimized trajectory parameters of the target driving trajectory and the trajectory parameters of other driving trajectories in the at least two driving trajectories, the driving costs corresponding to the at least two driving trajectories are recalculated, and the target driving trajectory with the maximum driving cost is re-determined from the at least two driving trajectories; and the trajectory parameters of the target driving trajectory are optimized.

[0127] Among them, the specific method of the optimization can be set according to actual needs, and this disclosure does not limit this.

[0128] In one embodiment shown, the trajectory parameters may include multiple driving trajectory points; the target vehicle may calculate the optimal variable value of the objective function based on the optimization algorithm; wherein the objective function is used to characterize the driving cost; the optimal variable value is the parameter value corresponding to the multiple driving trajectory points respectively that satisfies the minimum driving cost.

[0129] The trajectory parameters of the target driving trajectory may include multiple driving trajectory points, and optimizing the trajectory parameters may refer to optimizing and adjusting parameter values ​​corresponding to the multiple driving trajectory points.

[0130] Among them, the optimization algorithm can be set according to actual needs, and the present disclosure does not limit this. For example, the optimization algorithm may refer to the IPOPT (Interior Point Optimizer) algorithm, which is an optimization algorithm for solving nonlinear programming problems. It is based on the interior point method and is suitable for large-scale optimization problems. It gradually approaches the optimal solution through an iterative process, which is used to process constraints and optimize the objective function. In the present disclosure, the IPOPT algorithm is used to calculate the optimal variable value of the objective function.

[0131] The specific form of the objective function can be set according to actual needs, and the present disclosure does not limit this.

[0132] For example, the objective function can be expressed as:

[0133]

[0134] Among them, the objective function can represent the minimum driving cost corresponding to the target driving trajectory of the target vehicle from time 0 to time T; before time t, the intentions of the surrounding vehicles are clear and unclear, and after time t, the intentions of the surrounding vehicles are clear, J(τ 0:t ) can represent the driving cost corresponding to the common driving trajectory before the intention of the surrounding vehicles is clear, J(τ t:T |λ) can represent the driving cost corresponding to the independent driving trajectory of the surrounding vehicles with driving intention λ, max λ J(τ t:T |λ) can represent the driving cost corresponding to the driving trajectory with the maximum driving cost determined from all driving trajectories corresponding to the driving intention.

[0135] In this way, the driving trajectories with higher costs can be reduced in a targeted manner, thereby improving driving efficiency.

[0136] The specific content of the parameter value can be set according to actual needs, and this disclosure does not limit this.

[0137] In one embodiment shown, the parameter value may include at least one of the following parameter values: a position value; a speed value; an acceleration value; and a driving direction value.

[0138] Among them, the position value can be the coordinate value of the trajectory point in the geodetic coordinate system, the speed value can be the speed value of the target vehicle at the trajectory point, the acceleration value can be the acceleration value of the target vehicle at the trajectory point, and the driving direction value can be the direction value of the target vehicle at the trajectory point.

[0139] By optimizing the parameter values ​​of the trajectory points, the driving cost of the target vehicle on the driving trajectory can be reduced, thereby improving the driving efficiency of the target vehicle.

[0140] At the same time, corresponding to the above-mentioned embodiment of the method for optimizing the driving trajectory, the present disclosure also provides an embodiment of the device for optimizing the driving trajectory. Figure 4 , the device comprises:

[0141] An acquisition unit 402 is used to acquire at least two driving trajectories predicted based on the driving intentions of surrounding vehicles;

[0142] The calculation unit 404 is used to calculate the driving costs corresponding to the at least two driving trajectories according to the trajectory parameters of the at least two driving trajectories, and determine the target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling according to the driving trajectory;

[0143] The optimization unit 406 is used to optimize the trajectory parameters of the target driving trajectory.

[0144] In this embodiment, the above device may further include an iteration unit, configured to:

[0145] The at least two driving trajectories are iteratively optimized according to the following method until an iteration stop condition is met:

[0146] recalculating the driving costs respectively corresponding to the at least two driving trajectories according to the optimized trajectory parameters of the target driving trajectory and the trajectory parameters of other driving trajectories in the at least two driving trajectories, and re-determining the target driving trajectory with the maximum driving cost from the at least two driving trajectories;

[0147] The trajectory parameters of the target driving trajectory are optimized.

[0148] In this embodiment, the trajectory parameters may include a plurality of driving trajectory points;

[0149] The above optimization unit 406 may be specifically used for:

[0150] Based on the optimization algorithm, the optimal variable value of the objective function is calculated; wherein the objective function is used to characterize the driving cost; the optimal variable value is the parameter value corresponding to the multiple driving trajectory points respectively that satisfies the minimum driving cost.

[0151] In this embodiment, the above device may further include a response unit, which is used to:

[0152] Before acquiring at least two driving trajectories predicted based on the driving intentions of the surrounding vehicles, in response to detecting that the driving intentions of the surrounding vehicles are unclear, determining at least two driving intentions of the surrounding vehicles;

[0153] Based on the at least two driving intentions, a driving trajectory of the target vehicle is predicted and calculated to obtain at least two driving trajectories corresponding to the at least two driving intentions.

[0154] In this embodiment, the driving trajectory may include a common driving trajectory traveled before the intention of the surrounding vehicles is clear, and an independent driving trajectory traveled after the intention of the surrounding vehicles is clear.

[0155] In this embodiment, the above device may further include a monitoring unit, which is used to:

[0156] In response to detecting that the driving intention of the surrounding vehicles is unclear, before determining at least two driving intentions of the surrounding vehicles, monitoring the driving status of the surrounding vehicles to obtain monitoring data;

[0157] Determining, based on the monitoring data, whether the surrounding vehicles meet a condition of unclear driving intention;

[0158] If the surrounding vehicles satisfy the condition that the driving intention is unclear, it is determined that the driving intention of the surrounding vehicles is unclear.

[0159] In this embodiment, the monitoring data includes image data and / or lidar data;

[0160] The above monitoring unit can be specifically used for:

[0161] The image data and / or laser radar data are used as input parameters and input into a trajectory prediction model for prediction calculation to obtain a future driving trajectory corresponding to the surrounding vehicles; wherein the trajectory prediction model is a neural network model obtained by supervised learning training based on historical image data and / or laser radar data and historical driving trajectories;

[0162] Determine whether the number of future driving trajectories is greater than 1;

[0163] If the number of the future driving trajectories is greater than 1, it is determined that the driving intention of the surrounding vehicles is unclear.

[0164] In this embodiment, the above device may further include a determining unit, configured to:

[0165] Before calculating the driving costs respectively corresponding to the at least two driving trajectories according to the trajectory parameters of the at least two driving trajectories, coarse paths respectively corresponding to the at least two driving trajectories are generated according to the trajectory parameters of the at least two driving trajectories, and the cost of the coarse paths is pre-evaluated to obtain pre-evaluated costs respectively corresponding to the at least two driving trajectories;

[0166] Determining, from the at least two driving trajectories, at least a portion of the driving trajectories whose pre-evaluation costs satisfy a preset evaluation condition;

[0167] The above-mentioned calculation unit 404 can be specifically used for:

[0168] Driving costs corresponding to at least part of the driving trajectories are calculated according to the trajectory parameters of the at least two driving trajectories.

[0169] In this embodiment, the parameter value may include at least one parameter value shown below:

[0170] Position value; speed value; acceleration value; driving direction value.

[0171] The implementation process of the functions and effects of each module in the device is specifically described in the implementation process of the corresponding steps in the method, which will not be repeated here.

[0172] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art may understand and implement it without creative work.

[0173] The system, device or module described in the embodiments may be implemented by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0174] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the method described in any of the above embodiments.

[0175] Figure 5 5 is a block diagram of an electronic device according to an exemplary embodiment. For example, the electronic device 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0176] Reference Figure 5 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0177] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0178] The memory 504 is configured to store various types of data to support operations on the electronic device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0179] The power supply component 506 provides power to the various components of the electronic device 500. The power supply component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0180] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0181] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0182] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0183] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the electronic device 500, the relative positioning of components, such as the display and keypad of the electronic device 500, and the sensor assembly 514 can also detect the position change of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0184] The communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0185] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the method described in any of the above embodiments.

[0186] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by a processor 520 of an electronic device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0187] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in any of the above embodiments when the program is executed by a processor.

[0188] An embodiment of the present disclosure further provides a computer program product, which is configured to execute the wireless charging foreign object detection method described in any of the above embodiments.

[0189] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0190] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0191] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

Claims

1. A method for optimizing driving trajectories, It is characterized in that Applied to a target vehicle; the method comprises: Obtain at least two driving trajectories predicted based on the driving intentions of surrounding vehicles; Calculate driving costs corresponding to the at least two driving trajectories respectively according to the trajectory parameters of the at least two driving trajectories, and determine a target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory; The trajectory parameters of the target driving trajectory are optimized.

2. The method according to claim 1, It is characterized in that The method further comprises: The at least two driving trajectories are iteratively optimized according to the following method until an iteration stop condition is met: recalculating the driving costs respectively corresponding to the at least two driving trajectories according to the optimized trajectory parameters of the target driving trajectory and the trajectory parameters of other driving trajectories in the at least two driving trajectories, and re-determining the target driving trajectory with the maximum driving cost from the at least two driving trajectories; The trajectory parameters of the target driving trajectory are optimized.

3. The method according to any one of claims 1 or 2, It is characterized in that The trajectory parameters include a plurality of driving trajectory points; Optimizing the trajectory parameters of the target driving trajectory includes: Based on the optimization algorithm, the optimal variable value of the objective function is calculated; wherein the objective function is used to characterize the driving cost; the optimal variable value is the parameter value corresponding to the multiple driving trajectory points respectively that satisfies the minimum driving cost.

4. The method according to claim 1, It is characterized in that Before obtaining at least two driving trajectories predicted based on the driving intentions of surrounding vehicles, the method further includes: In response to detecting that the driving intention of the surrounding vehicles is ambiguous, determining at least two driving intentions of the surrounding vehicles; Based on the at least two driving intentions, a driving trajectory of the target vehicle is predicted and calculated to obtain at least two driving trajectories corresponding to the at least two driving intentions.

5. The method according to claim 4, It is characterized in that The driving trajectory includes a common driving trajectory traveled before the intention of the surrounding vehicles is clear, and an independent driving trajectory traveled after the intention of the surrounding vehicles is clear.

6. The method according to claim 4, It is characterized in that In response to detecting that the driving intention of the surrounding vehicles is ambiguous, before determining at least two driving intentions of the surrounding vehicles, the method further includes: Monitor the driving status of surrounding vehicles and obtain monitoring data; Determining, based on the monitoring data, whether the surrounding vehicles meet a condition of unclear driving intention; If the surrounding vehicles satisfy the condition that the driving intention is unclear, it is determined that the driving intention of the surrounding vehicles is unclear.

7. The method according to claim 6, It is characterized in that The monitoring data includes image data and / or lidar data; Determining whether the surrounding vehicles meet the condition of unclear driving intention according to the monitoring data includes: The image data and / or laser radar data are used as input parameters and input into a trajectory prediction model for prediction calculation to obtain a future driving trajectory corresponding to the surrounding vehicles; wherein the trajectory prediction model is a neural network model obtained by supervised learning training based on historical image data and / or laser radar data and historical driving trajectories; Determine whether the number of future driving trajectories is greater than 1; If the surrounding vehicles satisfy the condition that the driving intention is unclear, determining that the driving intention of the surrounding vehicles is unclear includes: If the number of the future driving trajectories is greater than 1, it is determined that the driving intention of the surrounding vehicles is unclear.

8. The method according to claim 1, It is characterized in that Before calculating the driving costs respectively corresponding to the at least two driving trajectories according to the trajectory parameters of the at least two driving trajectories, the method further includes: Generating coarse paths corresponding to the at least two driving trajectories respectively according to trajectory parameters of the at least two driving trajectories, and performing cost pre-evaluation on the coarse paths to obtain pre-evaluated costs corresponding to the at least two driving trajectories respectively; Determining, from the at least two driving trajectories, at least a portion of the driving trajectories whose pre-evaluation costs satisfy a preset evaluation condition; Calculating driving costs corresponding to the at least two driving trajectories respectively according to the trajectory parameters of the at least two driving trajectories includes: Driving costs corresponding to at least part of the driving trajectories are calculated according to the trajectory parameters of the at least two driving trajectories.

9. The method according to claim 3, It is characterized in that The parameter value includes at least one parameter value shown below: Position value; speed value; acceleration value; driving direction value.

10. A driving trajectory optimization device, It is characterized in that Applied to a target vehicle; the device comprises: An acquisition unit, used to acquire at least two driving trajectories predicted based on the driving intentions of surrounding vehicles; A calculation unit, configured to calculate driving costs corresponding to the at least two driving trajectories respectively according to trajectory parameters of the at least two driving trajectories, and determine a target driving trajectory with the maximum driving cost from the at least two driving trajectories; wherein the driving cost represents the cost incurred by the vehicle traveling along the driving trajectory; The optimization unit is used to optimize the trajectory parameters of the target driving trajectory.

11. A user device, It is characterized in that include: processor; a memory for storing processor-executable instructions; The processor is used to implement the method according to any one of claims 1 to 9.

12. A machine-readable storage medium, It is characterized in that The machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images