Grid map construction method, apparatus and device, and vehicle

Abstract

The invention relates to a grid map construction method and device, equipment and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: acquiring graphic information of a target object in a target area; and based on the graphic information of the target object in the target area and the type of the target object, projecting the target object to a plurality of layers of a grid map corresponding to the target area to obtain a layered grid map of the target area. Therefore, the accuracy of grid map construction can be improved, and the inaccuracy of subsequent decision making and path planning caused by the inaccuracy of the grid map is avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, in particular to the field of autonomous driving technology, and specifically to a grid map construction method, device, equipment and vehicle. Background Art

[0002] Among the core components of autonomous driving technology, grid map construction is the basis for vehicle environmental perception and path planning. Grid maps divide the vehicle's surroundings into a series of grids of equal size and mark the occupancy status of each grid (such as idle, occupied by obstacles, or unknown) based on sensor data, thereby providing the vehicle with an intuitive and easy-to-process environmental model.

[0003] However, in actual applications, vehicles only use the collected LiDAR point cloud data to generate a grid map and use it as a basis to plan a feasible driving path. The grid map generated in this way is less accurate, resulting in low applicability of the grid map in actual scenarios, reducing the reliability and safety of autonomous driving.

[0004] Therefore, how to improve the accuracy of raster maps has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a grid map construction method, device, equipment and vehicle to at least solve the technical problem of inaccurate grid maps in related technologies. The technical solution of the present application is as follows:

[0006] According to a first aspect of the present application, a grid map construction method is provided, the method comprising: obtaining graphic information of a target object in a target area; based on the graphic information of the target object in the target area and the type of the target object, projecting the target object into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area.

[0007] According to the above technical means, since different types of target objects may be detected by different sensors, and the detection accuracy of these sensors is different, the graphic information of the same type of target object under different sensors is different. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources, but also reduce the accuracy of the grid map. Therefore, a layered grid map of the target area is constructed by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0008] In a possible implementation, based on the graphic information of the target object in the target area and the type of the target object, the target object is projected into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area, including: based on the graphic information of the target object in the target area, and / or the type of the target object, determining the multiple layers of the grid map corresponding to the target area; based on the graphic information of the target object in the target area, projecting the target object into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area.

[0009] According to the above technical means, multiple layers of the grid map corresponding to the target area can be determined based on the graphic information of the target object in the target area, and / or the type of the target object, and then based on the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map corresponding to the target area to obtain a layered grid map of the target area. The present application constructs a layered grid map of the target area by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0010] In another possible implementation, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area, including: when the multiple layers include a layer corresponding to the graphic information of the target object in the target area, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map of the target area, and the type of the target object is marked in the grid cell corresponding to the target object to obtain a layered grid map of the target area.

[0011] According to the above technical means, each layer of the target object grid map can be connected with the graphic information of the target object in the target area, that is, based on the graphic information of the target object in the target area, it is determined that the multiple layers of the grid map corresponding to the target area include the layer corresponding to the graphic information of the target object in the target area. In this way, the information of each type of target object can be more independent and clear, and there will be no information crossing or overlapping, thereby providing more accurate data support for subsequent tasks such as path planning and decision making.

[0012] In another possible implementation, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area, including: when the multiple layers include a layer corresponding to the type of the target object, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map of the target area to obtain a layered grid map of the target area.

[0013] According to the above technical means, each layer of the target object grid map can be made to correspond to the type of the target object, that is, based on the graphic information of the target object in the target area, it is determined that the multiple layers of the grid map corresponding to the target area include the layer corresponding to the type of the target object. In this way, the information of each type of target object can be more independent and clear, and there will be no information crossing or overlapping, thereby providing more accurate data support for subsequent path planning, decision making and other tasks.

[0014] In another possible implementation, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map of the target area, including: based on the graphic information of the target object in the target area, determining the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object; based on the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object, projecting the target object into the multiple layers of the grid map of the target area.

[0015] According to the above technical means, when the target object is projected into multiple layers of the grid map of the target area, by calculating the probability of each grid cell being occupied by the target object, a more accurate spatial representation can be provided for the grid map. This method enables the layered grid map to accurately reflect the degree of occupancy of each grid cell, thereby improving the accuracy of the layered grid map construction.

[0016] In another possible implementation, the target object is projected into the multiple layers of the grid map of the target area based on the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object, including: for each grid cell in the multiple layers of the grid map of the target area, when the probability that the grid cell is occupied by the target object is greater than a preset probability, projecting the target object into the grid cell.

[0017] According to the above technical means, the sensor data may be affected by noise, so the probability value of the grid cell being occupied by the target object will not be an absolute 100% or 0%. By setting a probability threshold, the grid cell is considered to be occupied by the target object only when the probability of the grid cell being occupied by the target object is greater than the preset probability, and the target object is projected to the grid cell. This method can effectively filter out the information that the grid cell is mistakenly occupied by the target object due to noise or uncertainty, thereby reducing false alarms caused by environmental changes or sensor errors, and improving the accuracy of layered grid map construction.

[0018] In another possible implementation, the method further includes: the graphic information of the target object in the target area includes graphic information of the target object at multiple moments; based on the graphic information of the target object in the target area, determining the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object, including: based on the graphic information of the target object at multiple moments, determining the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object.

[0019] According to the above technical means, due to the movement of the vehicle or the movement of the target object itself, the target object may present different graphic information at different times, and the graphic information of the target object at a single moment may not reflect the true form of the object. Therefore, through the graphic information of the target object at multiple moments, the true form of the target object can be captured more comprehensively, so that the probability of each grid cell in the multiple layers of the grid map of the target area being occupied by the target object can be more accurately determined, thereby improving the accuracy of the layered grid map construction.

[0020] In another possible implementation, based on the graphic information of the target object at multiple moments, the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object is determined, including: based on the graphic information of the target object at each moment, adjusting the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object.

[0021] According to the above technical means, due to the movement of the vehicle or the movement of the target object itself, the target object may present different graphic information at different times. Therefore, based on the graphic information of the target object at each moment, the probability of each grid cell in the multiple layers of the grid map of the target area being occupied by the target object can be dynamically adjusted. In this way, the probability of the grid cells in each layer of the grid map being occupied by the target object will be continuously updated as the vehicle moves, thereby improving the accuracy of the layered grid map construction.

[0022] In another possible implementation, the method further includes: determining a target distance between each grid cell in multiple layers of a layered grid map of the target area and the nearest grid cell occupied by the target object; and performing collision detection on the target path in the layered grid map of the target area based on the target distance.

[0023] According to the above technical means, in the hierarchical grid map of the target area, the target path is collided with by detecting the target distance between each grid cell and the nearest grid cell occupied by the target object. This can more effectively plan and avoid obstacles in complex environments, thereby enhancing the obstacle avoidance capability of the target path.

[0024] In another possible implementation, based on the target distance, a collision detection is performed on the target path in a layered grid map of the target area, including: based on the graphic information of the target object required for the target path, selecting a corresponding layer from the layered grid map of the target area to construct a first grid map; based on the target distance and the first grid map, performing a collision detection on the target path.

[0025] According to the above technical means, since the graphic information of the target object can reflect the detection accuracy of the target object, based on the graphic information of the target object required based on the target path, a layer that matches the detection accuracy of the target object can be selected from the layered grid map of the target area. In this way, when collision detection is performed on the target path based on the target distance and the first grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection.

[0026] In another possible implementation, based on the target distance, a collision detection is performed on the target path in the layered grid map of the target area, including: based on the type of target object corresponding to the target path, selecting a corresponding layer from the layered grid map of the target area to construct a second grid map; based on the target distance and the second grid map, a collision detection is performed on the target path.

[0027] According to the above technical means, a suitable layer is selected according to the type of target object, and a layer matching the target object is selected from the layered grid map of the target area. In this way, when collision detection is performed on the target path based on the target distance and the second grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection.

[0028] According to the second aspect provided by the present application, a grid map construction device is provided, which includes an acquisition module for acquiring graphic information of a target object in a target area; and a construction module for projecting the target object into multiple layers of a grid map corresponding to the target area based on the graphic information of the target object in the target area and the type of the target object, so as to obtain a layered grid map of the target area.

[0029] According to the third aspect provided by the present application, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0030] According to a fourth aspect provided by the present application, a vehicle is provided, comprising: the grid map construction device of the second aspect above, or the electronic device of the third aspect above.

[0031] Therefore, the above technical features of the present application have the following beneficial effects:

[0032] (1) Since different types of target objects may be detected by different sensors, and the detection accuracy of these sensors is different, the same type of target object has different graphic information under different sensors. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources but also reduce the accuracy of the grid map. Therefore, a layered grid map of the target area is constructed by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also allows the information of different layers to be flexibly merged according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, greatly saving computing resources.

[0033] (2) Based on the graphic information of the target object in the target area and / or the type of the target object, multiple layers of the grid map corresponding to the target area can be determined, and then based on the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map corresponding to the target area to obtain a layered grid map of the target area. The present application constructs a layered grid map of the target area by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0034] (3) Each layer of the target object grid map can be connected with the graphic information of the target object in the target area. That is, based on the graphic information of the target object in the target area, it is determined that the multiple layers of the grid map corresponding to the target area include the layer corresponding to the graphic information of the target object in the target area. In this way, the information of each type of target object can be more independent and clear, and there will be no information crossing or overlapping, so as to provide more accurate data support for subsequent tasks such as path planning and decision making.

[0035] (4) Each layer of the target object grid map can be made to correspond to the type of the target object, that is, based on the graphic information of the target object in the target area, it is determined that the multiple layers of the grid map corresponding to the target area include the layer corresponding to the type of the target object. In this way, the information of each type of target object can be more independent and clear, and there will be no information crossing or overlapping, thereby providing more accurate data support for subsequent tasks such as path planning and decision making.

[0036] (5) When the target object is projected into multiple layers of the grid map of the target area, a more accurate spatial representation can be provided for the grid map by calculating the probability of each grid cell being occupied by the target object. This method enables the layered grid map to accurately reflect the degree of occupancy of each grid cell, thereby improving the accuracy of the layered grid map construction.

[0037] (6) Sensor data may be affected by noise, so the probability value of a grid cell being occupied by a target object will not be an absolute 100% or 0%. By setting a probability threshold, only when the probability of a grid cell being occupied by a target object is greater than the preset probability, the grid cell is considered to be occupied by the target object and the target object is projected onto the grid cell. This method can effectively filter out information about grid cells being mistakenly occupied by target objects due to noise or uncertainty, thereby reducing false alarms caused by environmental changes or sensor errors and improving the accuracy of layered grid map construction.

[0038] (7) Due to the movement of the vehicle or the movement of the target object itself, the target object may present different graphic information at different times, and the graphic information of the target object at a single time may not reflect the true form of the object. Therefore, through the graphic information of the target object at multiple times, the true form of the target object can be captured more comprehensively, so that the probability of each grid cell in the multiple layers of the grid map of the target area being occupied by the target object can be determined more accurately, thereby improving the accuracy of the layered grid map construction.

[0039] (8) Due to the movement of the vehicle or the movement of the target object itself, the target object may present different graphic information at different times. Therefore, the probability of each grid cell in the multiple layers of the grid map of the target area being occupied by the target object can be dynamically adjusted based on the graphic information of the target object at each moment. In this way, the probability of the grid cells in each layer of the grid map being occupied by the target object will be continuously updated as the vehicle moves, thereby improving the accuracy of the layered grid map construction.

[0040] (9) In the hierarchical grid map of the target area, collision detection of the target path is performed by calculating the target distance between each grid cell and the nearest grid cell occupied by the target object. This can more effectively plan and avoid obstacles in complex environments, thereby enhancing the obstacle avoidance capability of the target path.

[0041] (10) Since the graphic information of the target object can reflect the detection accuracy of the target object, a layer that matches the detection accuracy of the target object can be selected from the layered grid map of the target area according to the graphic information of the target object required based on the target path. In this way, when the target path is subjected to collision detection based on the target distance and the first grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection.

[0042] (11) Selecting a suitable layer according to the type of the target object, and selecting a layer that matches the target object from the layered grid map of the target area, so that when performing collision detection on the target path based on the target distance and the second grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection.

[0043] It should be noted that the technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0044] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0046] Figure 1 is a structural schematic diagram of a grid map construction system according to an exemplary embodiment;

[0047] Figure 2 is a flowchart of a grid map construction method according to an exemplary embodiment;

[0048] Figure 3 is a schematic diagram of a layered grid map according to an exemplary embodiment;

[0049] Figure 4 is a flowchart of another grid map construction method according to an exemplary embodiment;

[0050] Figure 5is a flowchart of another grid map construction method according to an exemplary embodiment;

[0051] Figure 6 is a block diagram of a grid map construction device according to an exemplary embodiment;

[0052] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0053] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0055] In order to realize the vehicle's autonomous driving function, the vehicle is usually equipped with a variety of sensors, including but not limited to radar sensors, ultrasonic radars, and visual sensors. These sensors have their own advantages and can perceive the surrounding environment from different angles and levels, providing diverse data inputs, which helps the vehicle accurately judge surrounding obstacles, such as speed bumps, walls, vehicles, pedestrians, bicycles, and static obstacles (such as trees, buildings, etc.).

[0056] In practical applications, especially during automatic parking, the vehicle needs to use a collision detector to determine the distance between the obstacle detected by each sensor and the vehicle for collision detection to determine whether the vehicle is at risk of collision. The current collision detection system usually adopts a "one-to-one" approach, that is, a different collision detector is called for collision detection for each obstacle detected by each sensor. Although this method can improve the accuracy of detection to a certain extent, it also brings significant computing resource consumption and energy waste. Especially when multiple sensors detect the same target at the same time, repeatedly calling different collision detectors is not only inefficient, but may also lead to system conflicts and the risk of false alarms.

[0057] In response to the above problems, the present application proposes a method for constructing a grid map. Since different types of target objects may be detected by different sensors, and the detection accuracy of these sensors is different, the graphic information of the same type of target object under different sensors is different. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources, but also reduce the accuracy of the grid map. Therefore, a layered grid map of the target area is constructed by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0058] For ease of understanding, the grid map construction method provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0059] Figure 1 FIG. 1 is a schematic diagram showing the composition of a grid map construction system according to an exemplary embodiment. Figure 1 As shown, the system includes a perception information module 101, a grid map module 102, a path planning module 103 and a collision detection module 104. The perception information module 101 is connected to the grid map module 102, the grid map module 102 is connected to the path planning module 103 and the collision detection module 104 respectively, and the path planning module 103 is connected to the collision detection module 104.

[0060] In some embodiments, the perception information module 101 is used to detect multiple types of obstacles and generate target data in multiple representations (such as points, line segments, and polygons), wherein the target data is the target data of the obstacle generated by processing and analyzing the raw data of the obstacle detected by the vehicle's sensor. Since the vehicle is equipped with multiple sensors, and the detection accuracy of each sensor is different, the target data corresponding to different sensors present different representations. For example, after the perception information module 101 performs semantic segmentation processing on the raw data detected by the visual sensor, the target data presents the representation of the envelope point sequence of the drivable area (freespace). For another example, after the perception information module clusters the raw data detected by the ultrasonic radar sensor, the target data presents the representation of the line segment (cluster). For another example, after the perception information module processes the raw data detected by the ultrasonic radar sensor, the target data presents the representation of the bounding box (bb). Therefore, the perception information module 101 can store target data in multiple representations. Among them, the envelope point sequence can also be referred to as a point, and the envelope box can also be referred to as a polygon.

[0061] In some embodiments, the grid map module 102 is used to determine the occupancy information and distance information of each grid cell in the layered grid map according to the target data in multiple representations in the perception module 101, so as to construct a layered grid map. The occupancy information is used to represent the information that each grid cell is occupied by an obstacle, and the distance information is used to represent the distance between each grid cell and the nearest grid cell occupied by the target object.

[0062] In some embodiments, the path planning module 103 is used to generate an optimal path from the starting point to the end point based on the layered grid map constructed by the grid map module 102 and the detection result output by the collision detection module 104. The detection result can indicate whether each grid unit in the layered grid map has a risk of collision with the vehicle, and the optimal path can avoid obstacles.

[0063] In some embodiments, the collision detection module 104 is used to detect in real time whether there is a risk of collision between the vehicle and each grid cell in the layered grid map based on the layered grid map constructed by the grid map module 102, so as to ensure that no accidental collision occurs when the path planning module 103 plans the optimal path for the vehicle, thereby avoiding potential safety risks.

[0064] It should be noted that the system architecture and application scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0065] Figure 2 is a flowchart of a grid map construction method according to an exemplary embodiment. Figure 2 As shown, the grid map construction method includes the following steps:

[0066] S201: Obtain graphic information of a target object in a target area.

[0067] The target area is the spatial range where the vehicle can detect and identify obstacles. The target object is an obstacle in the target area, such as a speed bump, a wall, a vehicle, a curb, etc. The graphic information is the representation of the target data generated after the target object is recognized by the perception information module in the preset area. For example, the representation of the target data generated after the target object is recognized by the perception information module can be a point, a line segment, a polygon, that is, the graphic information of the target object can be a point, a line segment, a polygon, etc.

[0068] As a possible implementation method, the graphic information of the target object in the target area can be obtained through the perception information module.

[0069] It should be noted that the target object includes one or more obstacles. In the case where the target object includes multiple obstacles, no matter the target object is detected by one sensor or multiple sensors, the target object has multiple graphic information. In the case where the target object includes one obstacle, the target object may be detected by multiple sensors to obtain multiple graphic information of the target object, or the target object may be detected by one sensor to obtain one graphic information of the target object. Since the possibility of the target object being detected by one sensor is small, the following takes the case where the target object includes one obstacle and is detected by multiple sensors as an example to illustrate the grid map construction method.

[0070] S202 : Based on the graphic information of the target object in the target area and the type of the target object, the target object is projected into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area.

[0071] It is understandable that different types of target objects may be detected by different sensors, and the detection accuracy of these sensors varies, resulting in different graphic information of the same type of target object under different sensors. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources but also reduce the accuracy of the grid map. Therefore, the present application constructs a layered grid map of the target area by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0072] As a possible implementation method, multiple layers of the grid map corresponding to the target area can be determined based on the graphic information of the target object in the target area and / or the type of the target object. Then, based on the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map corresponding to the target area to obtain a layered grid map of the target area.

[0073] In one example, there is a corresponding relationship between the graphic information of the target object in the target area and the layers of the grid map, so the multiple layers of the grid map corresponding to the target area can be determined according to the graphic information of the target object in the target area. Furthermore, when the multiple layers include the layer corresponding to the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map of the target area based on the graphic information of the target object in the target area, and the type of the target object is marked in the grid cell corresponding to the target object, so as to obtain a layered grid map of the target area.

[0074] For example, Figure 3 As shown, the layered grid map includes a first layer, a second layer, and a third layer from top to bottom. When the graphic information of the target object in the target area is a line segment, the target object can be projected into the first layer. When the graphic information of the target object in the target area is a polygon, the target object can be projected into the second layer. When the graphic information of the target object in the target area is a line segment, the target object can be projected into the third layer.

[0075] In another example, there is a corresponding relationship between the type of the target object and the layer of the grid map, so the multiple layers of the grid map corresponding to the target area can be determined according to the type of the target object. Furthermore, when the multiple layers include a layer corresponding to the type of the target object, based on the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map of the target area to obtain a layered grid map of the target area.

[0076] In another example, there is a correspondence between the graphic information of the target object in the target area and the type of the target object and the layers of the grid map, so the multiple layers of the grid map corresponding to the target area can be determined according to the graphic information of the target object in the target area and the type of the target object. Furthermore, when the multiple layers include the graphic information of the target object in the target area and the layers corresponding to the type of the target object, based on the graphic information of the target object in the target area, the target object is projected into the multiple layers of the grid map of the target area to obtain a layered grid map of the target area.

[0077] In some embodiments, when projecting the target object into the multiple layers, the grid cells occupied by the target object in each layer and their corresponding indexes can be determined, and then the target object can be projected into the corresponding layer according to the indexes of these grid cells.

[0078] Exemplarily, for a target object whose graphic information is a point, the index of the grid cell occupied by the point can be found according to the coordinates of the point. For a target object whose graphic information is a line segment, the line segment can be discretized into a series of points, and then the index of the grid cell occupied by the point can be found according to the coordinates of the discretized point. For example, the line segment can be discretized into a series of points based on Bresenham's line algorithm (Bresenham). For a target object whose graphic information is a polygon, first determine the outer boundary of the polygon (i.e., the outer contour of the polygon), the outer boundary is composed of multiple line segments, then identify the internal area of ​​the polygon by discretizing these line segments, and then determine the index of the grid cell occupied by the internal area of ​​the polygon through a filling algorithm (such as a flood-fill algorithm).

[0079] Based on the above S201-S202, the present application proposes a method for constructing a grid map. Since different types of target objects may be detected by different sensors, and the detection accuracy of these sensors is different, the graphic information of the same type of target object under different sensors is different. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources, but also reduce the accuracy of the grid map. Therefore, a layered grid map of the target area is constructed by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0080] It should be noted that when merging information of different layers, if a grid cell of any layer is occupied, the grid cell in the merged layer will also be occupied.

[0081] In some embodiments, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map corresponding to the target area to obtain a layered grid map of the target area, which can be specifically implemented as follows:

[0082] S301 : Based on the graphic information of the target object in the target area, determine the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object.

[0083] As a possible implementation manner, the probability that each grid cell in multiple layers of the grid map of the target area is occupied by the target object can be determined by using a Bayesian formula.

[0084] In some embodiments, based on the graphic information of the target object at each moment, the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object is adjusted.

[0085] It is understandable that due to the movement of the vehicle or the movement of the target object itself, the target object may present different graphic information at different times, and the graphic information of the target object at a single moment may not reflect the true form of the object. Therefore, through the graphic information of the target object at multiple moments, the true form of the target object can be captured more comprehensively, so that the probability of each grid unit in the multiple layers of the grid map of the target area being occupied by the target object can be determined more accurately, thereby improving the accuracy of the layered grid map construction.

[0086] As a possible implementation, for each grid cell in the multiple layers of the grid map of the target area, it is possible to determine whether the grid cell is occupied based on the graphic information of the target object at the current moment, and if the grid cell is occupied, the probability that the grid cell was occupied by the target object at the previous moment is increased by a probability increment until the probability determination end condition is reached. If the grid cell is not occupied, the probability that the grid cell was occupied by the target object at the previous moment is reduced by a probability increment until the probability determination end condition is reached.

[0087] It should be noted that the probability increment corresponding to each grid cell in each layer of the grid map of the target area can be determined according to actual needs, that is, the probability increment corresponding to each grid cell in each layer of the grid map of the target area can be different.

[0088] As another possible implementation method, for each grid cell in multiple layers of the grid map of the target area, the probability of the grid cell being occupied by the target object at the current moment can be determined based on the graphic information of the target object at the current moment, and the probability of the grid cell being occupied by the target object at the previous moment can be replaced by the probability of the grid cell being occupied by the target object at the current moment.

[0089] S302 : Projecting the target object into the multiple layers of the grid map of the target area based on the probability that each grid unit in the multiple layers of the grid map of the target area is occupied by the target object.

[0090] In some embodiments, for each grid cell in multiple layers of the grid map of the target area, when the probability that the grid cell is occupied by the target object is greater than a preset probability, it indicates that the grid cell is occupied by the target object, and thus the target object can be projected to the grid cell.

[0091] When the probability that the grid cell is occupied by the target object is less than or equal to the preset probability, it indicates that the grid cell is not occupied by the target object, and therefore there is no need to project the target object to the grid cell.

[0092] In some embodiments, if a grid cell is neither measured as being occupied by a target object nor measured as being unoccupied by a target object, the probability that the grid cell is occupied by a target object remains unchanged.

[0093] In some embodiments, when the graphic information of the target object is points, the inner area surrounded by these points is the drivable area, and the grid cells in the inner area can be measured as grid cells not occupied by the target object.

[0094] Based on the above S301-S302, the present application proposes a grid map construction method. The sensor data may be affected by noise, so the probability value of the grid cell being occupied by the target object will not be an absolute 100% or 0%. By setting a probability threshold, only when the probability of the grid cell being occupied by the target object is greater than the preset probability, the grid cell is considered to be occupied by the target object and the target object is projected to the grid cell. This method can effectively filter out information about the grid cell being mistakenly occupied by the target object due to noise or uncertainty, thereby reducing false alarms caused by environmental changes or sensor errors, and improving the accuracy of layered grid map construction.

[0095] The following is an exemplary introduction to the complete process of building a raster map.

[0096] like Figure 4 As shown, the process starts.

[0097] Step a1: Initialize the grid map corresponding to the target area.

[0098] As a possible implementation manner, each grid unit of the grid map corresponding to the target area may be constructed according to a preset resolution and a preset size.

[0099] Step a2: traverse the target object.

[0100] Traverse different types of target objects obtained from the perception information module.

[0101] Step a3: determine the index of the grid cell occupied by the target object in the grid map corresponding to the target area.

[0102] Step a4: Determine multiple layers of the grid map corresponding to the target area according to the type of the target object and / or the graphic information of the target object in the target area.

[0103] Step a5: project the target object into multiple layers of the grid map corresponding to the target area according to the index of the grid unit occupied by the target object in the grid map corresponding to the target area.

[0104] Step a6: Determine whether the traversal of the target object is complete.

[0105] If yes, execute the following step a7.

[0106] If not, continue to execute the above step a2.

[0107] Step a7: determining a target distance between each grid cell in a plurality of layers of the layered grid map of the target area and the nearest grid cell occupied by the target object.

[0108] In some embodiments, after the hierarchical grid unit of the target area is constructed, collision detection can be performed based on the hierarchical grid unit to determine whether there is a risk of collision in the vehicle's driving path. Therefore, the grid map construction method provided in the embodiment of the present application also includes the following steps:

[0109] S401: Determine a target distance between each grid cell in multiple layers of a layered grid map of a target area and the nearest grid cell occupied by a target object.

[0110] As a possible implementation, a target distance between each grid cell in multiple layers of a layered grid map of a target area and the nearest grid cell occupied by a target object may be determined according to a distance transform algorithm.

[0111] S402: Based on the target distance, collision detection is performed on the target path in the layered grid map of the target area.

[0112] As a possible implementation method, based on the graphic information of the target object required for the target path, the corresponding layer can be selected from the layered grid map of the target area to construct a first grid map, and then the target path can be collided with based on the target distance and the first grid map.

[0113] The target object graphic information required for the target path can be determined according to actual needs. For example, if the target path needs to be collided with a line segment, the corresponding layer can be selected from the layered grid map of the target area according to the target object graphic information required for the target path to construct the first grid map.

[0114] Exemplarily, the grid cells occupied by each layer of the first grid map when the vehicle travels along the target path can be determined. For each grid cell occupied by each layer of the first grid map when the vehicle travels along the target path, it can be determined whether the grid cell is occupied by the target object based on the size relationship between the distance between the grid cell and each grid cell occupied by the target object and a preset threshold value, so as to achieve collision detection on the target path.

[0115] It should be noted that the preset threshold corresponding to each layer of the first grid map is different and can be set according to actual needs, and this application does not impose specific restrictions on this. For example, the preset threshold corresponding to the layer whose target object type is grass is lower than the preset threshold corresponding to the layer whose target object type is other vehicles.

[0116] As another possible implementation, based on the type of the target object corresponding to the target path, a corresponding layer can be selected from the layered grid map of the target area to construct a second grid map, and then collision detection can be performed on the target path based on the target distance and the second grid map.

[0117] Similarly, the type of the target object corresponding to the target path can be determined according to actual needs. For example, if the target path needs to be collided with a wall of a road type, a corresponding layer can be selected from the layered grid map of the target area according to the wall of the road to construct a second grid map.

[0118] In addition, regarding the specific process of performing collision detection on the target path based on the target distance and the second grid map, reference can be made to the description of performing collision detection on the target path based on the target distance and the first grid map, and this application will not elaborate on it here.

[0119] In some embodiments, when the collision detection result of the target path is that there is no collision risk for the target path, the cost function of the target path can be determined based on the distance between the grid cells occupied by each layer of the first grid map and the grid cells occupied by the target object in each layer of the first grid map when the vehicle travels along the target path.

[0120] Based on the above S401-S402, the present application, on the one hand, since the graphic information of the target object can reflect the detection accuracy of the target object, based on the graphic information of the target object required based on the target path, a layer that matches the detection accuracy of the target object can be selected from the layered grid map of the target area, so that when the target path is subjected to collision detection based on the target distance and the first grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection. On the other hand, a suitable layer is selected according to the type of the target object, and a layer that matches the target object is selected from the layered grid map of the target area, so that when the target path is subjected to collision detection based on the target distance and the second grid map, the detection accuracy of the target object can be better adapted, thereby improving the accuracy of collision detection.

[0121] The following is an exemplary introduction to the complete process of collision detection based on a grid map.

[0122] like Figure 5 As shown, the process starts.

[0123] Step b1: Determine the grid cells occupied by each layer in the first grid map when the vehicle travels along the target path.

[0124] Step b2: traverse each grid cell.

[0125] Determine whether the grid cell is occupied by the target object.

[0126] If yes, execute the following step b4.

[0127] If not, execute the following step b3.

[0128] Step b3: determine whether the traversal of the grid cells is complete.

[0129] If yes, execute the following step b5.

[0130] If not, continue to execute the above step b2.

[0131] Step b4: Determine whether there is a collision risk on the target path.

[0132] Step b5: Determine that there is no collision risk on the target path.

[0133] It should be noted that the grid map construction method provided in the present application according to the exemplary embodiment can be executed by a grid map construction system, an electronic device, or a vehicle. The present application does not specifically limit the execution subject of the grid map construction method.

[0134] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the grid map construction device, electronic device or vehicle includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0135] The embodiments of the present application can exemplarily divide the functional modules of the grid map construction device, electronic device or vehicle according to the above method. For example, the grid map construction device, electronic device or vehicle can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0136] Figure 6 is a block diagram of a grid map construction device according to an exemplary embodiment. Figure 6 The grid map construction device 600 includes: an acquisition module 601 and a construction module 602.

[0137] In some embodiments, the acquisition module 601 is used to acquire graphic information of the target object in the target area; the construction module 602 is used to project the target object into multiple layers of the grid map corresponding to the target area based on the graphic information of the target object in the target area and the type of the target object, so as to obtain a layered grid map of the target area.

[0138] According to the above-mentioned technical means, the present application provides a grid map construction device. Since different types of target objects may be detected by different sensors, and the detection accuracy of these sensors is different, the graphic information of the same type of target object under different sensors is different. If a grid map is constructed separately for the graphic information of each type of target object under each sensor, it will not only waste resources, but also reduce the accuracy of the grid map. Therefore, the present application constructs a layered grid map of the target area by projecting the graphic information of different types of target objects under each sensor into different layers. This method not only improves the construction accuracy of the layered grid map, but also can flexibly merge the information of different layers according to needs in subsequent decision-making and path planning, so that only one layered grid map is needed to support subsequent operations, which greatly saves computing resources.

[0139] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0140] Figure 7 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 includes but is not limited to: a processor 701 and a memory 702 .

[0141] The memory 702 is used to store executable instructions of the processor 701. It can be understood that the processor 701 is configured to execute instructions to implement the grid map construction method in the above embodiment.

[0142] It should be noted that those skilled in the art can understand that Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0143] The processor 701 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 702, and calling data stored in the memory 702, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0144] The memory 702 may be used to store software programs and various data. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0145] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions. The above instructions can be executed by a processor 701 of an electronic device 700 to implement the grid map construction method in the above embodiment.

[0146] In actual implementation, Figure 6 The functions of the acquisition module 601 and the construction module 602 in Figure 7 The processor 701 in the embodiment calls the computer program stored in the memory 702. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0147] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0148] In an exemplary embodiment, the present application also provides a vehicle, the vehicle comprising Figure 6 The grid map construction device shown, or, Figure 7 Electronic equipment shown.

[0149] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by the processor 701 of the vehicle to complete the grid map construction method in the above embodiment.

[0150] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the vehicle's processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0151] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0152] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0154] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0156] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A grid map construction method, characterized in that: The method comprises: Obtaining graphic information of the target object in the target area; Based on the graphic information of the target object in the target area and the type of the target object, the target object is projected onto a plurality of layers of a grid map corresponding to the target area to obtain a layered grid map of the target area.

2. The method according to claim 1, characterized in that The step of projecting the target object onto a plurality of layers of a grid map corresponding to the target area based on the graphic information of the target object in the target area and the type of the target object to obtain a layered grid map of the target area includes: Determine a plurality of layers of a grid map corresponding to the target area based on the graphic information of the target object in the target area and / or the type of the target object; Based on the graphic information of the target object in the target area, the target object is projected into a plurality of layers of a grid map corresponding to the target area to obtain a layered grid map of the target area.

3. The method according to claim 2, characterized in that The step of projecting the target object onto a plurality of layers of a grid map corresponding to the target area based on the graphic information of the target object in the target area to obtain a layered grid map of the target area includes: In a case where the multiple layers include a layer corresponding to graphic information of the target object in the target area, the target object is projected into multiple layers of a grid map of the target area based on the graphic information of the target object in the target area, and the type of the target object is marked in the grid cell corresponding to the target object to obtain a layered grid map of the target area.

4. The method according to claim 2, characterized in that: The step of projecting the target object onto a plurality of layers of a grid map corresponding to the target area based on the graphic information of the target object in the target area to obtain a layered grid map of the target area includes: In the case where the multiple layers include a layer corresponding to the type of the target object, based on the graphic information of the target object in the target area, the target object is projected into multiple layers of the grid map of the target area to obtain a layered grid map of the target area.

5. The method according to claim 3 or 4, characterized in that: The step of projecting the target object onto a plurality of layers of a grid map of the target area based on the graphic information of the target object in the target area comprises: Based on the graphic information of the target object in the target area, determining the probability that each grid cell in a plurality of layers of a grid map of the target area is occupied by the target object; The target object is projected into the multiple layers of the grid map of the target area based on the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object.

6. The method according to claim 5, characterized in that The projecting the target object onto the multiple layers of the grid map of the target area based on the probability that each grid unit in the multiple layers of the grid map of the target area is occupied by the target object comprises: For each grid cell in a plurality of layers of the grid map of the target area, when the probability that the grid cell is occupied by the target object is greater than a preset probability, the target object is projected onto the grid cell.

7. The method according to claim 5, characterized in that The graphic information of the target object in the target area includes graphic information of the target object at multiple moments; determining the probability that each grid unit in multiple layers of the grid map of the target area is occupied by the target object based on the graphic information of the target object in the target area includes: Based on the graphic information of the target object at the multiple moments, the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object is determined.

8. The method according to claim 7, characterized in that The determining, based on the graphic information of the target object at the multiple moments, the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object comprises: Based on the graphic information of the target object at each moment, the probability that each grid cell in the multiple layers of the grid map of the target area is occupied by the target object is adjusted.

9. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Determining a target distance between each grid cell in a plurality of layers of a layered grid map of the target area and the nearest grid cell occupied by the target object; Based on the target distance, collision detection is performed on the target path in the layered grid map of the target area.

10. The method according to claim 9, characterized in that The step of performing collision detection on the target path in the layered grid map of the target area based on the target distance includes: Based on the graphic information of the target object required by the target path, a corresponding layer is selected from the layered grid map of the target area to construct a first grid map; Based on the target distance and the first grid map, collision detection is performed on the target path.

11. The method according to claim 9, characterized in that The step of performing collision detection on the target path in the layered grid map of the target area based on the target distance includes: Based on the type of the target object corresponding to the target path, a corresponding layer is selected from the layered grid map of the target area to construct a second grid map; Based on the target distance and the second grid map, collision detection is performed on the target path.

12. A grid map construction device, characterized in that: The device comprises: an acquisition module and a construction module; The acquisition module is used to acquire graphic information of the target object in the target area; The construction module is used to project the target object into multiple layers of the grid map corresponding to the target area based on the graphic information of the target object in the target area and the type of the target object, so as to obtain a layered grid map of the target area.

13. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 11.

14. A vehicle, characterized in that: include: The grid map constructing device as claimed in claim 12, or the electronic device as claimed in claim 13.

Images