A sensor processing method, apparatus, device, and storage medium

Abstract

This invention discloses a sensor processing method, apparatus, device, and storage medium, comprising: constructing a driving scenario for a local vehicle based on road condition information of the local vehicle's driving road; planning candidate position information for sensors on the local vehicle based on the vehicle's state information and driving scenario; obtaining sensor data of candidate obstacles by simulating detection of the candidate obstacles using the sensors based on the sensors' position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution; constructing a top view of the sensor's simulated sensing area based on the sensing data; obtaining the sensor's detection results and detection priority for the target obstacle based on the target obstacle's position information, size information, and driving scenario; and selecting target position information from the sensor's candidate position information based on the target obstacle's detection results and detection priority, for placing the sensor at the target position. This improves the sensor's detection efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the field of computers, and more particularly to a sensor processing method, apparatus, device, and storage medium. Background Technology

[0002] With the continuous development of intelligent driving technology, more and more vehicles are equipped with sensors such as image acquisition devices, positioning devices, inertial navigation sensors, millimeter-wave radar, lidar, and ultrasonic radar. These sensors enhance the vehicle's perception of its surroundings and provide the driver with more sensor detection information. Traditional vehicle sensor deployment often employs centralized or distributed methods. Existing sensor deployment methods are prone to mutual interference during detection, or the sensor placement is constrained by the vehicle's shape. Furthermore, the specific driving scenarios are not considered during sensor deployment, affecting the sensor's detection efficiency and accuracy in assessing the vehicle's surroundings. Therefore, improving vehicle sensor deployment schemes to enhance sensor detection efficiency and accuracy is a problem that needs to be addressed. Summary of the Invention

[0003] This invention provides a sensor processing method, apparatus, device, and storage medium, which can improve the sensor's detection efficiency and accuracy of the local vehicle's surrounding environment.

[0004] According to one aspect of the present invention, a sensor processing method is provided, comprising:

[0005] Based on the road condition information of the local roads where vehicles travel, construct the driving scenario of local vehicles;

[0006] Based on the local vehicle's status information and the driving scenario, plan the candidate location information of the sensors on the local vehicle;

[0007] Based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution, the sensor performs simulated detection of candidate obstacles to obtain sensing data of the candidate obstacles;

[0008] Based on the sensing data, a top view is constructed for the simulated sensing area of ​​the sensor; wherein, the top view includes the position and size information of the target obstacle in the simulated sensing area;

[0009] Based on the location and size information of the target obstacle and the driving scenario, the detection results and detection priority of the sensor on the target obstacle are obtained;

[0010] Based on the detection results and detection priority of the target obstacle, target location information is selected from the candidate location information of the sensor, and the sensor is placed at the target location.

[0011] According to another aspect of the present invention, a sensor processing apparatus is provided, the apparatus comprising:

[0012] The driving scenario construction module is used to construct the driving scenario of the local vehicle based on the road condition information of the local vehicle's driving road.

[0013] The candidate location information planning module is used to plan candidate location information of sensors on the local vehicle based on the status information of the local vehicle and the driving scenario.

[0014] The sensor data acquisition module is used to obtain the sensor data of the candidate obstacle by simulating the detection of the candidate obstacle through the sensor based on the position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy and resolution of the sensor.

[0015] A top-view construction module is used to construct a top-view for the simulated sensing area of ​​the sensor based on the sensing data; wherein, the top-view includes the position and size information of the target obstacle in the simulated sensing area;

[0016] The detection result acquisition module is used to acquire the detection results and detection priority of the sensor on the target obstacle based on the location information, size information of the target obstacle and the driving scenario;

[0017] The target location information selection module is used to select target location information from the candidate location information of the sensor based on the detection results and detection priority of the target obstacle, and to place the sensor at the target location.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] At least one processor; and

[0020] A memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the sensor processing method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the sensor processing method according to any embodiment of the present invention.

[0023] The technical solution of this invention involves: constructing a driving scenario for the local vehicle based on road condition information of the local road; planning candidate positions for sensors on the local vehicle based on the vehicle's status information and driving scenario; obtaining sensor data of candidate obstacles through simulated detection using sensors based on sensor position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution; constructing a top-down view of the sensor's simulated sensing area based on the sensor data; obtaining the sensor's detection results and detection priority for the target obstacle based on the target obstacle's position information, size information, and driving scenario; and selecting target position information from the candidate sensor position information based on the target obstacle's detection results and detection priority, for placing the sensor at the target position. This solution provides a technical approach that, based on vehicle status information, driving scenario, and various sensor functional parameters, uses computer simulation to determine the sensor's detection results under different placement methods for the driving scenario, and then determines the optimal sensor placement method based on the detection results. This achieves the technical effect of flexibly deploying local vehicle sensors based on the vehicle's driving scenario, thereby improving the sensor's detection efficiency and accuracy in detecting the surrounding environment of the local vehicle. Meanwhile, since different sensors have their own advantages and limitations in terms of sensing range and detection capability, sensor information fusion technology can be used to rationally arrange the sensors on the vehicle so that each sensor can give full play to its own advantages, thereby improving the safety and reliability of the entire intelligent driving system.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart of a sensor processing method provided in Embodiment 1 of the present invention;

[0027] Figure 2This is a flowchart of a sensor processing method provided in Embodiment 2 of the present invention;

[0028] Figure 3 A flowchart illustrating a sensor processing method provided in Embodiment 3 of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of a sensor processing device provided in Embodiment 4 of the present invention;

[0030] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "optional," "candidate," and "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "etc.", and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1This is a flowchart illustrating a sensor processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where vehicle sensors are processed using simulation software to arrange the sensors. This method can be executed by a sensor processing device, which can be implemented in hardware and / or software and can be configured in an electronic device. In this embodiment, the sensor arrangement and sensor detection process can be simulated using the AutoDrivingDesigner toolbox in MATLAB. The AutoDrivingDesigner toolbox includes sensor models; by calling the sensor models in the AutoDrivingDesigner toolbox, the sensor arrangement can be simulated. Figure 1 As shown, the method includes:

[0035] S101. Construct a driving scenario for local vehicles based on the road condition information of the roads on which local vehicles travel.

[0036] In this context, "local vehicle" refers to the vehicle whose sensors need to be deployed. "Road condition information" refers to the road condition information that a local vehicle might encounter while traveling, determined based on actual needs. For example, road condition information may include at least one of the following: lane markings, traffic lights, obstacles, and road congestion index. "Local vehicle driving scenario" refers to a virtual driving scenario constructed by the user based on the road condition information of the local vehicle's travel route, according to actual needs. Lane markings are lane markings that guide direction; lane markings include the position and color of the lane markings. Traffic light information includes the position and color of the traffic lights. Obstacles include both moving and stationary obstacles on the local vehicle's travel route. Moving obstacles include pedestrians and other vehicles on the local vehicle's travel route. Obstacle information includes the size and location information of the obstacles.

[0037] Specifically, based on actual needs, the road condition information of the local vehicle's driving route is determined, and this road condition information is input into the scenario building software to construct the local vehicle's driving scenario.

[0038] For example, based on actual needs, determine the lane markings, traffic lights, obstacles, and road congestion index of the local roads where vehicles travel. Input this determined road condition information into Matlab software so that Matlab can construct a local vehicle driving scenario based on the input road condition information.

[0039] S102. Based on the local vehicle's status information and driving scenario, plan the candidate location information of the sensors on the local vehicle.

[0040] The local vehicle status information includes the vehicle's driving status and model. Environmental perception sensors for intelligent driving vehicles mainly include ultrasonic radar, millimeter-wave radar, lidar, image acquisition equipment, and night vision equipment. Candidate location information refers to the locations on the vehicle where sensors can be deployed, meeting the requirements of the driving scenario and the vehicle's status information.

[0041] Image acquisition devices, such as cameras, are primarily used in medium- to long-range scenarios to identify clear lane line information, traffic light information, and obstacle information. Ultrasonic radar is mainly used in short-range scenarios to identify obstacle information. Millimeter-wave radar includes 24GHz radar for short- to medium-range measurement and 77GHz radar for long-range measurement. Millimeter-wave radar can effectively extract depth and velocity information, identify obstacles, and has some ability to penetrate fog, smoke, and dust. However, in complex environments with obstacles, because millimeter-wave radar relies on sound waves for positioning, diffuse reflection of sound waves can cause identification errors. LiDAR has extremely high speed, range, and angular resolution and strong anti-interference capabilities, but it is expensive and easily affected by adverse weather and smoky environments.

[0042] Specifically, based on the local vehicle's driving scenario, the sensors that need to be deployed on the local vehicle are determined. Based on the local vehicle's status information, the vehicle model is determined, and based on the vehicle model, candidate locations on the local vehicle that can be used to deploy sensors are determined.

[0043] For example, planning candidate location information for sensors on a local vehicle can be achieved through the following sub-steps:

[0044] S1021. Based on the local vehicle's status information, determine the local vehicle's speed and the available locations where sensors can be deployed on the local vehicle.

[0045] The optional location information refers to the locations on the vehicle that can be used to deploy sensors. It is understandable that different vehicle models may have different locations available for sensor deployment.

[0046] Specifically, based on the local vehicle status information, the driving status and vehicle model of the local vehicles are determined. Based on the driving status, the speed of the local vehicles is determined; based on the vehicle model, the available sensor placement locations on the local vehicles that meet the requirements are determined. The sensor placement requirements include both spatial and lighting requirements for sensor placement.

[0047] S1022. Based on vehicle speed, driving scenario and sensor detection function, determine candidate location information of sensors on the local vehicle from the available location information.

[0048] The sensor's detection function refers to its ability to detect and identify driving scenarios.

[0049] It's important to note that the information a sensor can detect in a driving environment varies depending on its height. A sensor mounted on the roof can detect obstacles farther away earlier, but with lower accuracy. A lower placement improves detection accuracy, but only detects obstacles closer to the vehicle. At high speeds, a low sensor placement and shorter detection range could lead to rear-end collisions due to delayed data transmission. Therefore, at high speeds, detection range takes precedence over accuracy; at lower speeds, accuracy takes precedence over range.

[0050] Specifically, based on the driving scenario and the sensor's detection capabilities, the sensors required for that scenario are determined. A speed threshold is determined based on the actual situation. If the vehicle speed exceeds the threshold, the highest available location information is selected as the candidate location information for the sensors on the local vehicle. If the vehicle speed is less than or equal to the speed threshold, a pre-defined correspondence between vehicle speed and other available location information (excluding the highest location information) is established. Based on this correspondence, candidate location information for the sensors on the local vehicle is determined from the available location information.

[0051] Understandably, when determining the candidate location information of sensors on a local vehicle, fully considering the impact of vehicle speed on sensor detection results can ensure that the placement of vehicle sensors meets the needs of vehicle driving scenarios and driving conditions, thereby improving vehicle safety during driving.

[0052] S103. Based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution, the sensor performs simulated detection of the candidate obstacle to obtain the sensing data of the candidate obstacle.

[0053] The sensor's detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution can be determined based on the sensor model, and can be obtained from the AutoDrivingDesigner toolbox in MATLAB. Candidate obstacles refer to obstacles in the driving scene. The sensing data of candidate obstacles refers to the obstacle information detected by the sensor, including the obstacle's position, speed, and size. Resolution refers to the sensor's sensitivity, i.e., the minimum input that causes a change in the sensor's output. Sensing accuracy refers to the degree of closeness between the actual digital output and the theoretically expected digital output for a given analog input.

[0054] Specifically, after determining the candidate location information of the sensors on the local vehicle, the area in the driving scene that the sensors can detect can be determined based on the sensor's location information, detection distance, horizontal viewing angle, and vertical viewing angle. Based on the sensing accuracy and resolution, the sensor data of candidate obstacles that can be accurately detected by the sensors within the detectable driving scene area are then determined.

[0055] S104. Based on the sensing data, construct a top view for the simulated sensing area of ​​the sensor;

[0056] The top-down view includes the location and size information of target obstacles within the simulated perception area. The simulated perception area refers to the region in the driving scenario that the sensor can detect. Target obstacles refer to the sensor data of candidate obstacles within the simulated perception area that can be accurately detected by the sensor.

[0057] Specifically, the simulated perception area of ​​the sensor is determined based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle. Mapping the sensor data onto this simulated perception area allows the creation of a top-down view containing the position and size information of the target obstacle. For example, the size information of the target obstacle can be displayed in the top-down view using a preset graphic at a set scale. The preset graphic can be circular or square; there are no restrictions here.

[0058] S105. Based on the location information, size information, and driving scenario of the target obstacle, obtain the sensor's detection results and detection priority for the target obstacle.

[0059] It's important to note that placing sensors on the roof increases the blind spot in the driving area, making it difficult for them to detect smaller obstacles. For example, when using radar, a high sensor placement increases the blind spot, preventing the vehicle from detecting lower obstacles within the simulated perception area. For instance, a radar device positioned 0.35m above the ground can detect all obstacles within the simulated perception area, but the area is relatively small. At 1.45m, the minimum height of obstacles detectable by the radar increases as the distance between the vehicle and the obstacle decreases; within 4m of the obstacle, the minimum detectable height is 0.1m. Therefore, the sensor's detection priority must be determined based on the vehicle's driving scenario.

[0060] Specifically, based on the location and size information of the target obstacle, the actual information of the target obstacle detected by the sensor at the candidate location corresponding to the candidate location information is obtained. For example, the location and size information of the target obstacle can be used to determine whether it is a pedestrian, vehicle, or other obstacle. The driving scenario and detection results can be used as priority judgment indicators, and the correspondence between the priority judgment indicators and the detection priority can be pre-set. Based on the local vehicle's driving scenario and detection results, the local vehicle's priority judgment indicators are determined, and then the sensor's detection priority for the target obstacle is determined according to the correspondence between the priority judgment indicators and the detection priority.

[0061] S106. Based on the detection results and detection priority of the target obstacle, select the target location information from the candidate location information of the sensor, and use it to place the sensor at the target location.

[0062] Specifically, based on the detection results of the target obstacles, detection results containing a large number of target obstacles are identified as candidate results. For example, based on the number of target obstacles detected, the three detection results containing the most target obstacles can be selected as candidate results, and the corresponding candidate position information is selected from the candidate position information of the sensors. Then, based on the detection priority, the desired height for deploying the sensors is determined. The candidate position information corresponding to the candidate results that meet the desired height is determined as the target position information, which is used to deploy the sensors at the target location.

[0063] For example, the correspondence between priority judgment indicators and detection priorities can be as follows: If the local vehicle's driving scenario is a highway scenario, then the sensor's detection priority for target obstacles can be: vehicle detection priority is higher than pedestrian detection priority, pedestrian detection priority is higher than other obstacle detection priority. In this case, the target position is 1.45m above the ground, and the sensor can be placed at a height of 1.45m above the ground. If the local vehicle's driving scenario is a street scenario, and it is determined that there are pedestrians in the driving scenario based on the detection results of target obstacles, then the sensor's detection priority for target obstacles can be: pedestrian detection priority is higher than vehicle detection priority, vehicle detection priority is higher than other obstacle detection priority. In this case, the target position is 0.35m above the ground, and the sensor can be placed at a height of 0.35m above the ground. If the local vehicle's driving scenario is a street scenario, and it is determined from the detection results of the target obstacle that there are no pedestrians in the driving scenario, then the sensor's detection priority for the target obstacle can be that the detection priority of the vehicle is higher than the detection priority of the pedestrian, and the detection priority of the pedestrian is higher than the detection priority of other obstacles. At this time, the target position is 1.45m above the ground, and the sensor can be placed at a position 1.45m above the ground.

[0064] Optionally, the local vehicle status information, driving scenario, target location information, and sensor identification information can be output to Simulink as a sensor layout scheme for vehicles that meet the aforementioned status information under the driving scenario, allowing users to call upon this sensor layout scheme according to actual needs. Sensor identification information refers to information that can characterize the name and function of the sensor.

[0065] The technical solution provided in this embodiment constructs a driving scenario for the local vehicle based on road condition information of the local road. Based on the vehicle's state information and the driving scenario, candidate positions for sensors on the vehicle are planned. Based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution, sensor data of candidate obstacles is obtained through simulated detection. A top-down view is constructed for the sensor's simulated sensing area based on the sensing data. The detection results and priority of the target obstacle are obtained based on its position and size information and the driving scenario. Based on the detection results and priority, target position information is selected from the candidate sensor positions for placing the sensor at the target location. This solution provides a technical approach that, based on the vehicle's state information, driving scenario, and various sensor functional parameters, uses computer simulation to determine the sensor's detection results under different placement methods, and then determines the optimal sensor placement method based on the detection results. This achieves the technical effect of flexibly deploying local vehicle sensors based on the vehicle's driving scenario, thereby improving the sensor's detection efficiency and accuracy in detecting the surrounding environment of the local vehicle. Meanwhile, since different sensors have their own advantages and limitations in terms of sensing range and detection capability, sensor information fusion technology can be used to rationally arrange the sensors on the vehicle so that each sensor can give full play to its own advantages, thereby improving the safety and reliability of the entire intelligent driving system.

[0066] Example 2

[0067] Figure 2 This is a flowchart of a sensor processing method provided in Embodiment 2 of the present invention. This embodiment optimizes the above embodiment and provides a preferred implementation scheme for obtaining sensor data of candidate obstacles by simulating detection of candidate obstacles using the sensor based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution. Specifically, as shown... Figure 2 As shown, the method includes:

[0068] S201. Construct a driving scenario for local vehicles based on the road condition information of the roads on which local vehicles travel.

[0069] S202. Based on the local vehicle's status information and driving scenario, plan the candidate location information of the sensors on the local vehicle.

[0070] S203. Determine the simulated sensing area of ​​the sensor based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle.

[0071] Specifically, based on the sensor's location information and detection distance, a circle is drawn with the sensor's location as the center and the sensor's detection distance as the radius to obtain the maximum detection area that the sensor can theoretically detect. Then, based on the sensor's horizontal and vertical viewing angles, the blind zone area of ​​the sensor within the maximum detection area is determined. The blind zone area is then removed from the maximum detection area, and the maximum detection area after removing the blind zone area is used as the sensor's simulated sensing area.

[0072] S204. Obtain the regional scene within the simulated perception area from the driving scene;

[0073] The regional scene includes at least one candidate obstacle.

[0074] Specifically, based on the sensor's location information and the sensor's simulated perception area, the overlapping area in the driving scenario that coincides with the simulated perception area is determined, and the overlapping area is taken as the regional scene within the simulated perception area.

[0075] S205. Based on the sensor's position information and sensing accuracy, candidate obstacles within the sensor's detection range in the area scene are selected as target obstacles.

[0076] The sensor detection range refers to the maximum range of obstacles of a certain size that the sensor can detect.

[0077] Specifically, based on the sensor's position information and sensing accuracy, the sensor's detection range for candidate obstacles of different sizes is determined. The size and position information of candidate obstacles in the area scene are determined. Based on the sensor's sensing accuracy and the size and position information of the candidate obstacles in the area scene, it is determined whether the candidate obstacles in the area scene are within the sensor's detection range. Candidate obstacles in the area scene that are within the sensor's detection range are designated as target obstacles.

[0078] For example, based on the sensor's location information and sensing accuracy, a threshold for the size of an obstacle that the sensor can detect at the location of a candidate obstacle can be determined. Then, based on the obstacle's size and the threshold, the target obstacle can be identified from the candidate obstacles. Specifically, this can be achieved through the following sub-steps:

[0079] S2051. Extract the location information and size of candidate obstacles from the regional scene.

[0080] Specifically, after obtaining the regional scene within the simulated perception area from the driving scenario, candidate obstacles within the regional scene are identified, and the location information and size of the candidate obstacles within the regional scene are obtained.

[0081] S2052. Based on the sensor's position information and sensing accuracy, determine the threshold size of the obstacle that the sensor can detect at the candidate obstacle location.

[0082] The obstacle size threshold refers to the minimum size of an obstacle that the sensor can detect at the location of a candidate obstacle.

[0083] Specifically, based on the sensor's sensing accuracy, the distance information between the sensor and obstacles, as well as the correspondence between the obstacle size thresholds that the sensor can detect at different distances, can be pre-set. Based on the sensor's position information and the position information of candidate obstacles within the scene, the distance information between the sensor and the candidate obstacles in the scene is determined. Based on the aforementioned correspondence and distance information, the obstacle size threshold that the sensor can detect at the candidate obstacle's location is determined.

[0084] S2053. If the size of a candidate obstacle is greater than the obstacle size threshold, then the candidate obstacle is determined to be within the sensor detection range, and the candidate obstacle within the sensor detection range is taken as the target obstacle.

[0085] Specifically, if the size of a candidate obstacle in the area scene is greater than the obstacle size threshold, then the candidate obstacle in the area scene is determined to be within the sensor detection range, and the candidate obstacle within the sensor detection range is taken as the target obstacle.

[0086] It is understandable that if the size of a candidate obstacle in the scene is less than or equal to the obstacle size threshold, then the candidate obstacle in the scene is determined to be outside the sensor's detection range.

[0087] S206. Based on the sensor's resolution, adjust the clarity of the target obstacle to enable the sensor to successfully detect the target obstacle.

[0088] Specifically, the resolution of the target obstacle is adjusted. This involves determining the image of the target obstacle based on the sensor's detection results and adjusting the image resolution of the target obstacle to match the sensor's resolution, so that the sensor can successfully detect the target obstacle and thus successfully simulate and acquire the image of the target obstacle.

[0089] The output image of the target obstacle can be a preset graphic, and the size of the preset graphic can be determined according to the size information of the target obstacle and the set size ratio.

[0090] S207. Collect sensor data of the target obstacle through sensor simulation.

[0091] Specifically, by calling the sensor model in the AutoDrivingDesigner toolbox, sensor data of the target obstacle can be collected through sensor simulation.

[0092] S208. Based on the sensing data, construct a top view for the simulated sensing area of ​​the sensor.

[0093] The top view includes the location and size information of the target obstacle in the simulated perception area.

[0094] S209. Based on the location information, size information, and driving scenario of the target obstacle, obtain the sensor's detection results and detection priority for the target obstacle.

[0095] S210. Based on the detection results and detection priority of the target obstacle, select the target location information from the candidate location information of the sensor, and use it to place the sensor at the target location.

[0096] The technical solution of this embodiment constructs a driving scenario for the local vehicle based on road condition information of the local vehicle's driving road; plans candidate position information for sensors on the local vehicle based on the vehicle's state information and driving scenario; determines the simulated perception area of ​​the sensor based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle; obtains the regional scene within the simulated perception area from the driving scenario; selects candidate obstacles within the sensor's detection range in the regional scene as target obstacles based on the sensor's position information and sensing accuracy; adjusts the clarity of the target obstacles based on the sensor's resolution to enable the sensor to successfully detect the target obstacles; collects sensing data of the target obstacles through sensor simulation; constructs a top view for the simulated perception area of ​​the sensor based on the sensing data; obtains the sensor's detection results and detection priority for the target obstacles based on the target obstacle's position information, size information, and driving scenario; and selects target position information from the candidate position information of the sensor based on the target obstacle's detection results and detection priority, for placing the sensor at the target position. The above scheme can determine the detectable area of ​​a driving scenario based on the sensor's detection capabilities. Then, based on the sensor's location information, sensing accuracy, and resolution, it identifies target obstacles within that area that can be successfully detected. Finally, based on the sensing data of these target obstacles, it determines the sensor's detection results, thereby establishing the target location information for sensor deployment. This approach, which determines sensor data based on their detection capabilities and performance, results in more accurate sensing data and improves the reliability of the acquired target location information for sensor deployment.

[0097] Example 3

[0098] Figure 3This is a flowchart of a sensor processing method provided in Embodiment 3 of the present invention. This embodiment optimizes the above embodiments and provides a preferred implementation method for obtaining sensor data of candidate obstacles by simulating detection of candidate obstacles using the sensor based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution. Specifically, as shown... Figure 3 As shown, the method includes:

[0099] S301. Construct a driving scenario for local vehicles based on the road condition information of the roads on which local vehicles travel.

[0100] S302. Based on the local vehicle's status information and driving scenario, plan the candidate location information of the sensors on the local vehicle.

[0101] S303. Based on the sensor's position information, sensing accuracy, and resolution, determine the obstacle distance threshold at which candidate obstacles in the driving scenario can be detected.

[0102] Specifically, the size information of candidate obstacles in the driving scene is determined. Based on the sensor's position information, sensing accuracy, and resolution, the area of ​​the driving scene that can be detected by the sensor is determined. Candidate obstacles in the area are those that may be detected by the sensor. Then, based on the sensor's sensing accuracy and resolution, the obstacle distance threshold for the candidate obstacles in the area to be detected is determined.

[0103] S304. Determine the sensor's blind zone index based on the obstacle distance threshold and the sensor's detection distance.

[0104] Among them, the sensor blind zone index refers to an index that can be used to measure the size of the detection blind zone area of ​​a sensor.

[0105] Specifically, the sensor blind zone index is determined based on the ratio between the obstacle distance threshold and the sensor's detection distance. The calculation formula for the sensor blind zone index is shown in formula (1):

[0106]

[0107] Where Q is the sensor blind zone index, and F i is the obstacle distance threshold, S is the sensor detection distance, and n is the number of candidate obstacles.

[0108] The sensor blind zone index can also be used to evaluate the effectiveness of sensor placement. The lower the sensor blind zone index, the greater the driving scenarios that the sensor placement scheme corresponding to the sensor blind zone index can detect.

[0109] S305. Based on the sensor blind zone index, the sensor's horizontal and vertical viewing angles, candidate obstacles located outside the sensor's blind zone are designated as target obstacles.

[0110] The blind zone of a sensor refers to the area that the sensor cannot detect.

[0111] Specifically, the area of ​​the sensor's detection blind zone is determined based on the blind zone index, and the location information of the sensor's detection blind zone is determined based on the sensor's horizontal and vertical viewing angles. The range of the sensor's detection blind zone is then determined based on the blind zone area and location information. Candidate obstacles located outside the sensor's detection blind zone range are designated as target obstacles.

[0112] S306. Sensor data of the target obstacle is collected through sensor simulation.

[0113] S307. Based on the sensing data, construct a top view for the simulated sensing area of ​​the sensor.

[0114] The top view includes the location and size information of the target obstacle in the simulated perception area.

[0115] S308. Based on the location information, size information, and driving scenario of the target obstacle, obtain the sensor's detection results and detection priority for the target obstacle.

[0116] S309. Based on the detection results and detection priority of the target obstacle, select the target location information from the candidate location information of the sensor, and use it to place the sensor at the target location.

[0117] The technical solution of this embodiment constructs a driving scenario for the local vehicle based on road condition information of the local vehicle's driving road; plans candidate position information for sensors on the local vehicle based on the vehicle's state information and driving scenario; determines the obstacle distance threshold that can be detected by candidate obstacles in the driving scenario based on the sensor's position information, sensing accuracy, and resolution; determines the sensor's blind zone index based on the obstacle distance threshold and the sensor's detection distance; identifies candidate obstacles located outside the sensor's blind zone as target obstacles based on the blind zone index, the sensor's horizontal and vertical viewing angles; collects sensing data of the target obstacles through sensor simulation; constructs a top view of the sensor's simulated sensing area based on the sensing data; obtains the sensor's detection results and detection priority for the target obstacles based on the target obstacle's position information, size information, and driving scenario; and selects target position information from the sensor's candidate position information based on the target obstacle's detection results and detection priority, for placing the sensor at the target position. The above scheme determines the sensor blind zone index based on the obstacle distance threshold that the candidate obstacle can be detected and the sensor's detection distance. Then, based on the blind zone index and the sensor's viewing angle, it determines the sensing data. This provides a preferred implementation method for quantifying the detection effect corresponding to different sensor placement schemes. This makes the detection effects of different sensor placement schemes more intuitive, improves the efficiency of acquiring target location information, thereby improving sensor placement efficiency while ensuring sensor detection accuracy.

[0118] Example 4

[0119] Figure 4 This is a schematic diagram of a sensor processing device provided in Embodiment 4 of the present invention. This embodiment is applicable to situations where vehicle sensors are processed using simulation software to arrange the sensors. Figure 4 As shown, the processing device of the sensor includes: a driving scene construction module 410, a candidate position information planning module 420, a sensor data acquisition module 430, a top view construction module 440, a detection result acquisition module 450, and a target position information selection module 460.

[0120] Among them, the driving scenario construction module 410 is used to construct the driving scenario of the local vehicle based on the road condition information of the local vehicle driving road.

[0121] The candidate location information planning module 420 is used to plan the candidate location information of sensors on the local vehicle based on the local vehicle's status information and driving scenario.

[0122] The sensor data acquisition module 430 is used to obtain the sensor data of the candidate obstacle by simulating the detection of the candidate obstacle through the sensor based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy and resolution.

[0123] The top view construction module 440 is used to construct a top view for the simulated sensing area of ​​the sensor based on the sensing data; wherein, the top view includes the position and size information of the target obstacle in the simulated sensing area;

[0124] The detection result acquisition module 450 is used to acquire the sensor's detection results and detection priority of the target obstacle based on the target obstacle's location information, size information, and driving scenario;

[0125] The target location information selection module 460 is used to select target location information from the candidate location information of the sensor based on the detection results and detection priority of the target obstacle, so as to place the sensor at the target location.

[0126] The technical solution provided in this embodiment constructs a driving scenario for the local vehicle based on road condition information of the local road. Based on the vehicle's state information and the driving scenario, candidate positions for sensors on the vehicle are planned. Based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution, sensor data of candidate obstacles is obtained through simulated detection. A top-down view is constructed for the sensor's simulated sensing area based on the sensing data. The detection results and priority of the target obstacle are obtained based on its position and size information and the driving scenario. Based on the detection results and priority, target position information is selected from the candidate sensor positions for placing the sensor at the target location. This solution provides a technical approach that, based on the vehicle's state information, driving scenario, and various sensor functional parameters, uses computer simulation to determine the sensor's detection results under different placement methods, and then determines the optimal sensor placement method based on the detection results. This achieves the technical effect of flexibly deploying local vehicle sensors based on the vehicle's driving scenario, thereby improving the sensor's detection efficiency and accuracy in detecting the surrounding environment of the local vehicle. Meanwhile, since different sensors have their own advantages and limitations in terms of sensing range and detection capability, sensor information fusion technology can be used to rationally arrange the sensors on the vehicle so that each sensor can give full play to its own advantages, thereby improving the safety and reliability of the entire intelligent driving system.

[0127] For example, the candidate location information planning module 420 includes:

[0128] An optional location information determination unit is used to determine the speed of the local vehicle and the optional location information where the local vehicle can deploy sensors based on the status information of the local vehicle.

[0129] The candidate location information determination unit is used to determine the candidate location information of the sensors on the local vehicle from the available location information based on vehicle speed, driving scenario and sensor detection function.

[0130] For example, the sensor data acquisition module 430 includes:

[0131] The simulated sensing area determination unit is used to determine the simulated sensing area of ​​the sensor based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle.

[0132] The regional scene acquisition unit is used to acquire the regional scene within the simulated perception area from the driving scene; wherein the regional scene includes at least one candidate obstacle;

[0133] The target obstacle determination unit is used to identify candidate obstacles within the sensor's detection range in the area scene as target obstacles based on the sensor's position information and sensing accuracy.

[0134] A sharpness adjustment unit is used to adjust the sharpness of target obstacles based on the sensor's resolution, enabling the sensor to successfully detect target obstacles.

[0135] The sensor data acquisition unit is used to acquire sensor data of the target obstacle through sensor simulation.

[0136] Furthermore, the target obstacle determination unit is specifically used for:

[0137] Extract the location information and size of candidate obstacles from the local scene;

[0138] Based on the sensor's location information and sensing accuracy, determine the threshold size of the obstacle that the sensor can detect at the candidate obstacle location;

[0139] If the size of a candidate obstacle is larger than the obstacle size threshold, the candidate obstacle is determined to be within the sensor's detection range, and the candidate obstacle within the sensor's detection range is taken as the target obstacle.

[0140] For example, the sensor data acquisition module 430 is specifically used for:

[0141] Based on the sensor's location information, sensing accuracy, and resolution, determine the obstacle distance threshold that can be detected for candidate obstacles in the driving scenario;

[0142] Based on the obstacle distance threshold and the sensor's detection range, determine the sensor's blind zone index;

[0143] Based on the sensor blind zone index, the sensor's horizontal and vertical viewing angles, candidate obstacles located outside the sensor's blind zone are identified as target obstacles.

[0144] Sensor data of the target obstacle is collected through sensor simulation.

[0145] The aforementioned road condition information for local vehicles includes at least one of the following: lane markings, traffic lights, obstacles, and road congestion index.

[0146] The sensor processing device provided in this embodiment can be applied to the sensor processing method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0147] Example 5

[0148] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0149] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0150] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as sensor processing methods.

[0152] In some embodiments, the sensor processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the sensor processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the sensor processing method by any other suitable means (e.g., by means of firmware).

[0153] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable sensor processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0155] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0157] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0158] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0159] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0160] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A processing method of a sensor, characterized by, include: Based on the road condition information of the local roads where vehicles travel, construct the driving scenario of local vehicles; Based on the local vehicle's status information and the driving scenario, plan the candidate location information of the sensors on the local vehicle; Based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution, the sensor performs simulated detection of candidate obstacles to obtain sensing data of the candidate obstacles; Based on the sensing data, a top view is constructed for the simulated sensing area of ​​the sensor; wherein, the top view includes the position and size information of the target obstacle in the simulated sensing area; Based on the location and size information of the target obstacle and the driving scenario, the detection results and detection priority of the sensor on the target obstacle are obtained; Based on the detection results and detection priority of the target obstacle, target location information is selected from the candidate location information of the sensor, and the sensor is placed at the target location. The step of obtaining sensor data of candidate obstacles by simulating detection of candidate obstacles using the sensor based on the sensor's position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy, and resolution includes: Based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle, the simulated sensing area of ​​the sensor is determined; The region scene within the simulated perception area is obtained from the driving scenario; wherein the region scene includes at least one candidate obstacle; Based on the position information and sensing accuracy of the sensor, candidate obstacles within the sensor's detection range in the area scene are selected as target obstacles. Based on the resolution of the sensor, the sharpness of the target obstacle is adjusted so that the sensor can successfully detect the target obstacle; The sensor data of the target obstacle is collected through simulation using the aforementioned sensor. The step of planning candidate location information for sensors on the local vehicle based on the local vehicle's state information and the driving scenario includes: Based on the local vehicle status information, determine the local vehicle's driving status and vehicle model; Based on the driving conditions of the local vehicles, determine the speed of the local vehicles. Based on the vehicle model of the local vehicle, determine the optional location information on the local vehicle that meets the sensor placement conditions; Based on the vehicle speed, the driving scenario, and the detection function of the sensors, candidate location information of the sensors on the local vehicle is determined from the selectable location information; The sensor arrangement conditions include meeting the space and lighting requirements for sensor arrangement.

2. The method of claim 1, wherein, The step of identifying candidate obstacles within the sensor's detection range in the area scene as target obstacles based on the sensor's position information and sensing accuracy includes: Extract the location information and size of candidate obstacles from the local scene; Based on the sensor's location information and sensing accuracy, determine the threshold size of the obstacle that the sensor can detect at the candidate obstacle location; If the size of a candidate obstacle is larger than the obstacle size threshold, then the candidate obstacle is determined to be within the sensor detection range, and the candidate obstacle within the sensor detection range is taken as the target obstacle.

3. The method according to any one of claims 1-2, characterized in that, The road condition information of the local vehicle travel route includes at least one of the following: lane line information, traffic light information, obstacle information, and road congestion index.

4. A sensor processing device, characterized in that, include: The driving scenario construction module is used to construct the driving scenario of the local vehicle based on the road condition information of the local vehicle's driving road. The candidate location information planning module is used to plan candidate location information of sensors on the local vehicle based on the status information of the local vehicle and the driving scenario. The sensor data acquisition module is used to obtain the sensor data of the candidate obstacle by simulating the detection of the candidate obstacle through the sensor based on the position information, detection distance, horizontal viewing angle, vertical viewing angle, sensing accuracy and resolution of the sensor. A top-view construction module is used to construct a top-view for the simulated sensing area of ​​the sensor based on the sensing data; wherein, the top-view includes the position and size information of the target obstacle in the simulated sensing area; The detection result acquisition module is used to acquire the detection results and detection priority of the sensor on the target obstacle based on the location information, size information of the target obstacle and the driving scenario; The target location information selection module is used to select target location information from the candidate location information of the sensor based on the detection results and detection priority of the target obstacle, and to place the sensor at the target location; The sensor data acquisition module includes: The simulated sensing area determination unit is used to determine the simulated sensing area of ​​the sensor based on the sensor's position information, detection distance, horizontal viewing angle, and vertical viewing angle. The regional scene acquisition unit is used to acquire the regional scene within the simulated perception area from the driving scene; wherein the regional scene includes at least one candidate obstacle; The target obstacle determination unit is used to identify candidate obstacles within the sensor's detection range in the area scene as target obstacles based on the sensor's position information and sensing accuracy. A sharpness adjustment unit is used to adjust the sharpness of target obstacles based on the sensor's resolution, enabling the sensor to successfully detect target obstacles. The sensor data acquisition unit is used to acquire sensor data of the target obstacle through sensor simulation. The candidate location information planning module includes: An optional location information determination unit is used to determine the driving status and vehicle model of a local vehicle based on the local vehicle's status information; and to determine the speed of a local vehicle based on the local vehicle's driving status. Based on the vehicle model of the local vehicle, determine the optional location information on the local vehicle that meets the sensor placement conditions; A candidate location information determination unit is used to determine candidate location information of the sensors on the local vehicle from the selectable location information based on the vehicle speed, the driving scenario, and the detection function of the sensors. The sensor arrangement conditions include meeting the space and lighting requirements for sensor arrangement.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the sensor processing method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the sensor processing method according to any one of claims 1-3.

Images