Collision detection method, electronic device, and mobile device

Abstract

The application discloses a collision detection method, comprising: generating a first distance transform map according to map information within a preset range around a mobile device; generating a second distance transform map according to real-time information around the mobile device detected by a sensor of the mobile device; determining whether a to-be-detected point is passable according to the first distance transform map, obtaining a first collision detection result; determining whether the to-be-detected point is passable according to the second distance transform map, obtaining a second collision detection result; and determining that the to-be-detected point is a collision point when the first collision detection result and / or the second collision detection result indicates that the to-be-detected point is impassable. The first distance transform map and the second distance transform map are generated according to map information and real-time information respectively, and whether the mobile device will collide at the detection point is determined by comprehensively considering the two transform maps. The problem of false detection of a collision point caused by errors in superimposed information obtained by directly superimposing prior map information and perceived real-time information is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a collision detection method, an electronic device, a mobile device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] In recent years, with the rapid development of automatic driving technology, more and more unmanned vehicles have entered the field of vision of people. At the same time, the safety problems involved are also paid more and more attention by people. Among them, how to scientifically detect the collision of the vehicle path is particularly important.

[0003] In the automatic driving system, the prior map information and the real-time perception information (perceived real-time obstacle information) are generally superimposed as a new data source to check the collision of the path, so as to judge the validity of the path. How to make good use of map information and perception information is very helpful for subsequent path processing.

[0004] At present, in the automatic driving system, the map information is generally designed in advance, and the passable area and the impassable area are established. Then the real-time obstacle information obtained by perception is superimposed on the map in the form of grid points. If the original passable area is covered by an obstacle point, the corresponding area becomes an impassable area, thereby forming new area information, and collision detection is performed based on the new area information, but there is often no detection problem. SUMMARY

[0005] The embodiments of the present application aim to at least solve one of the above technical problems.

[0006] In a first aspect, the embodiments of the present application provide a collision detection method, comprising:

[0007] generating a first distance transform map according to the map information within a preset range around the mobile device;

[0008] generating a second distance transform map according to the real-time information around the mobile device detected by the sensor of the mobile device;

[0009] determining whether a to-be-detected point is passable according to the first distance transform map, to obtain a first collision detection result;

[0010] determining whether the to-be-detected point is passable according to the second distance transform map, to obtain a second collision detection result;

[0011] When the first collision detection result and / or the second collision detection result indicates that the to-be-detected point is impassable, determining that the to-be-detected point is a collision point.

[0012] In a second aspect, an embodiment of the present application provides an electronic device, comprising at least one processor, and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any of the collision detection methods described above.

[0013] In a third aspect, an embodiment of the present application provides a mobile device, comprising a body and the electronic device described in any of the embodiments of the present application installed on the body.

[0014] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, comprising a program or instructions, when the program or instructions are run on a computer, realizing the collision detection method described in any of the embodiments of the present application.

[0015] In a fifth aspect, an embodiment of the present application further provides a computer program product, when the computer program product is run on a computer, enabling the computer to perform the collision detection method described in any of the embodiments of the present application.

[0016] The embodiments of the present application respectively generate a first distance transform map and a second distance transform map according to prior map information and real-time information obtained by sensors, and perform collision detection on a to-be-detected point based on the first distance transform map and the second distance transform map respectively to obtain two collision detection results, and only when both the collision detection results indicate that the to-be-detected point is a passable point, it is determined that the mobile device is passable at the detection point. The problem of false detection of collision points caused by errors in superimposed information obtained by directly superimposing prior map information and perceived real-time information is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0018] Figure 1a A schematic diagram of obstacle distribution determined according to prior map;

[0019] Figure 1b A schematic diagram of obstacle distribution determined according to real-time information perceived by sensors;

[0020] Figure 1c A schematic diagram of obstacle distribution obtained by merging the two schematic diagrams of obstacle distribution; Figure 1a and Figure 1b A schematic diagram of obstacle distribution obtained by merging the two schematic diagrams of obstacle distribution;

[0021] Figure 2 Flow chart of an embodiment of the collision detection method of the present application;

[0022] Figure 3 Flow chart of another embodiment of the collision detection method of the present application;

[0023] Figure 4 Flow chart of another embodiment of the collision detection method of the present application;

[0024] Figure 5 Flow chart of another embodiment of the collision detection method of the present application;

[0025] Figure 6 Schematic diagram of a grid map under the map information in the present application;

[0026] Figure 7 Schematic diagram of converting a binary image into a first distance transform map using an eight-neighborhood update method in the present application;

[0027] Figure 8 Schematic diagram of the first distance transform map generated using an eight-neighborhood update method in the present application;

[0028] Figure 9 Schematic diagram of an embodiment of the electronic device of the present application. DETAILED DESCRIPTION

[0029] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0030] It should also be noted that, in this document, the terms “comprising” and “including” not only include those elements, but also include other elements not explicitly listed, or further include elements inherent in the process, method, article or device. Without more limitations, the elements defined by the statement “comprising” do not exclude the presence of other identical elements in the process, method, article or device comprising the elements.

[0031] As Figures 1a-1c Schematic diagram of collision point detection in the prior art. Figure 1a Schematic diagram of obstacle distribution determined according to a prior map, in which the distance between two obstacles is K1. Figure 1bA distribution sketch of obstacles determined according to real-time information sensed by a sensor, wherein the distance between two obstacles is K2. Figure 1c A distribution sketch of obstacles determined according to real-time information sensed by a sensor, wherein the distance between two obstacles is K2. Figure 1a A distribution sketch of obstacles determined according to real-time information sensed by a sensor, wherein the distance between two obstacles is K2. Figure 1b A distribution sketch of obstacles determined according to real-time information sensed by a sensor, wherein the distance between two obstacles is K2.

[0032] However, the inventors found that in the actual process of automatic driving, due to the existence of positioning errors and the like, the edge of the perceived obstacle may not coincide with the corresponding edge on the map (as shown in Figure 1c In some narrow lane scenarios, simple superposition of the two obstacle regions may cause the vehicle to be unable to effectively pass through the narrow lane (the actual vehicle can pass through).

[0033] To overcome the technical problems found, the inventors propose a collision detection method, which can be applied to an electronic device. The electronic device can be a car machine system or a control unit of an aircraft or an underwater robot, etc., and the present application does not limit this. The electronic device can be applied to a mobile device, which can be an unmanned vehicle, such as an unmanned cleaning vehicle, an unmanned sweeper, an unmanned logistics vehicle, an unmanned taxi, and a robot, etc., and the present application does not limit this. The following embodiments are described taking a vehicle as an example.

[0034] As shown in Figure 2 The embodiment of the present application provides a collision detection method, which comprises:

[0035] S10, generating a first distance transform map according to map information within a preset range around a mobile device.

[0036] Exemplarily, the mobile device can be a vehicle. The preset range around the vehicle can be a rectangular area with a certain length and width centered on the vehicle, or can be a circular area with a preset length as the radius centered on the vehicle. The present application does not limit this. The map information can be pre-determined historical map information, which is a kind of prior information. The historical map information includes but is not limited to road boundary information, obstacle boundary information, passable area information and impassable area information, etc.

[0037] S20, generating a second distance transform map according to real-time information around the mobile device detected by a sensor of the mobile device.

[0038] Exemplarily, the mobile device can be a vehicle. The sensors of the vehicle include, but are not limited to, one or more of the following: millimeter wave radar, laser radar, camera, infrared sensor, etc. Real-time information of the surrounding environment of the vehicle is detected in real time by the sensors during driving of the vehicle, and the real-time information can include, but is not limited to, obstacle information, road sign information, lane line information, etc.

[0039] S30, determining whether the to-be-detected point is passable according to the first distance transform map, to obtain a first collision detection result.

[0040] Exemplarily, the first distance transform map includes a plurality of to-be-detected points, and each to-be-detected point is configured with a distance to the nearest obstacle (i.e., a map distance change value). For a to-be-detected point located above an obstacle, the corresponding map distance change value is 0.

[0041] When it is determined that the to-be-detected point is passable, the obtained first collision detection result is that the current to-be-detected point is a non-collision point; when it is determined that the to-be-detected point is not passable, the obtained first collision detection result is that the current to-be-detected point is a collision point.

[0042] Exemplarily, determining whether the to-be-detected point is passable according to the first distance transform map to obtain a first collision detection result includes: determining a map distance change value of the to-be-detected point according to the first distance transform map, the map distance change value being a distance from the to-be-detected point to the nearest obstacle; and judging whether the map distance change value is greater than a minimum safety distance to obtain the first collision detection result.

[0043] The minimum safety distance is determined according to the width of the vehicle. Exemplarily, the minimum safety distance is half the width of the vehicle. The vehicle is a left-right symmetrical object, and when the vehicle drives to the to-be-detected point, the center point of the vehicle ideally corresponds to the to-be-detected point. At this time, as long as there is no obstacle within the range of half the width of the vehicle from the to-be-detected point, the vehicle is theoretically safe to pass, so the minimum safety distance can be set to half the width of the vehicle.

[0044] Exemplarily, the minimum safety distance can also be set to be greater than half the width of the vehicle. Because the center of the vehicle may not coincide with the to-be-detected point during actual driving due to factors such as positioning accuracy or road complexity, it is necessary to configure a certain amount of redundancy for the safety distance to more reliably ensure that the vehicle can pass smoothly.

[0045] S40, determining whether the to-be-detected point is passable according to the second distance transform map, to obtain a second collision detection result.

[0046] For example, the second distance transformation map includes multiple points to be detected, each of which is configured with the distance (i.e., map distance change value) to its nearest obstacle. For a point to be detected located on an obstacle, its corresponding map distance change value is 0.

[0047] When it is determined that the point to be detected is passable, the second collision detection result is: the current point to be detected is a non-collision point; when it is determined that the point to be detected is not passable, the second collision detection result is: the current point to be detected is a collision point.

[0048] S50. When the first collision detection result and / or the second collision detection result indicate that the point to be detected is impassable, the point to be detected is determined to be a collision point.

[0049] In this embodiment, a first distance transformation map and a second distance transformation map are generated based on prior map information and real-time information obtained from sensors, respectively. Collision detection is then performed on the point to be detected based on the first and second distance transformation maps to obtain two collision detection results. The mobile device is considered to be passable at the detection point only when both collision detection results indicate that the point to be detected is passable. This avoids the problem of false collision detection caused by errors in the superimposed information obtained by directly superimposing prior map information and perceived real-time information.

[0050] like Figure 3 The diagram shown is a flowchart illustrating another embodiment of the collision detection method of the present invention. In this embodiment, determining whether the point to be detected is passable based on the first distance transformation map to obtain a first collision detection result includes:

[0051] S31. Determine the map distance change value of the point to be detected based on the first distance transformation map. The map distance change value is the distance between the point to be detected and the nearest obstacle.

[0052] For example, a point to be detected is selected from a first distance transformation map, and the map distance change value corresponding to the point to be detected is obtained from the first distance transformation map.

[0053] The methods for selecting the points to be detected from the first distance transformation map include, but are not limited to, the following:

[0054] Points to be detected are selected one by one from the first distance transformation map, either by row or by column, for collision detection.

[0055] S32. The map distance change value is corrected using the positioning correction value to obtain the corrected map distance change value.

[0056] Exemplarily, due to the existence of positioning errors in the actual automatic driving process, the point actually traveled to by the vehicle can deviate from the corresponding to-be-detected point. Therefore, in order to avoid the deviation from causing subsequent collision false detection, the map distance change value of the to-be-detected point is corrected by using the positioning correction value, for subsequent collision point detection.

[0057] S33, judging whether the corrected map distance change value is greater than the minimum safety distance, to obtain a first collision detection result.

[0058] The collision detection method of the embodiment corrects the map distance change value of the to-be-detected point in the first distance change graph determined based on the prior map information, thereby avoiding collision false detection caused by positioning deviation in the actual automatic driving process.

[0059] As Figure 4 shown, a flowchart of another embodiment of the collision detection method of the application is shown. In this embodiment, it further includes: comparing whether the distance between the mobile device and the to-be-detected point is less than a preset distance threshold.

[0060] Exemplarily, the preset distance threshold is determined according to the effective detection distance of the sensor. The effective detection distance refers to the distance that can be accurately detected by the sensor, and there will be a certain error in the detection of environmental information beyond this distance. Exemplarily, the preset distance threshold can be 3m. It should be noted that the above is only an example. The preset distance threshold is different with sensors having different effective detection distances.

[0061] If the distance between the mobile device and the to-be-detected point is less than the preset distance threshold, the to-be-detected point is determined to be passable according to the second distance change graph, to obtain a second collision detection result, including:

[0062] S41, determining a perception distance change value of the to-be-detected point according to the second distance change graph, the perception distance change value being the distance between the to-be-detected point and the nearest obstacle.

[0063] Exemplarily, the to-be-detected point is selected from the second distance change graph, and the perception distance change value corresponding to the to-be-detected point is obtained from the second distance change graph.

[0064] The way of selecting the to-be-detected point from the second distance change graph includes but is not limited to the following ways: selecting the to-be-detected point from the second distance change graph row by row or column by column for collision detection.

[0065] S42, judging whether the perception distance change value is greater than the minimum safety distance, to obtain a second collision detection result.

[0066] In this embodiment, the perceived distance transformation value of the detection point is determined by using a second distance transformation map, and then compared with the minimum safe distance to obtain a second collision detection result. The second distance transformation map is determined based on real-time information detected by the vehicle's sensors. Since the effective detection range of the sensors is limited, this embodiment is only executed when the distance between the moving device and the detection point is less than a preset distance threshold. This ensures the accuracy of the second distance transformation map generated based on real-time information detected within the effective detection range, thereby improving the reliability of collision detection.

[0067] like Figure 5 The diagram shown is a flowchart of another embodiment of the collision detection method of the present invention. In this embodiment, the method further includes: comparing whether the distance between the mobile device and the point to be detected is less than a preset distance threshold;

[0068] - If the distance between the mobile device and the point to be detected is not less than a preset distance threshold, then determining whether the point to be detected is passable based on the second distance transformation map to obtain a second collision detection result includes:

[0069] S41' Determine the change value of the perceived distance of the point to be detected based on the second distance transformation diagram. The change value of the perceived distance is the distance between the point to be detected and the nearest obstacle.

[0070] For example, a point to be detected is selected from the second distance transformation map, and the perceived distance change value corresponding to the point to be detected is obtained from the second distance transformation map.

[0071] The methods for selecting points to be detected from the second distance transformation map include, but are not limited to, the following: selecting points to be detected one by one from the second distance transformation map by row or column for collision detection.

[0072] S42'. The perception distance change value is corrected using the perception correction value to obtain the corrected perception distance change value;

[0073] S43' Determine whether the corrected sensing distance change value is greater than the minimum safe distance to obtain the second collision detection result.

[0074] In this embodiment, the perception distance transform value of the to-be-detected point is determined by the second distance transform graph, and compared with the minimum safety distance to obtain a second collision detection result. The second distance transform graph is determined based on the real-time information detected by the sensor of the vehicle, and since the effective detection distance of the sensor is limited, when the to-be-detected point exceeds the effective detection distance of the sensor, the real-time information detected by the sensor will have errors, and thus the second distance transform graph obtained based on this will also be less reliable, which will eventually lead to a false judgment when collision detection is performed based on the unreliable second distance transform graph. To solve the above problem, in this embodiment, a perception correction value is used to correct the perception distance transform value of the to-be-detected point, so as to compare it with the minimum safety distance to complete collision detection and improve the reliability of collision detection.

[0075] In some embodiments, the collision detection method proposed in the present application is implemented based on distance transform. The specific implementation steps are as follows:

[0076] 1. Establishing a first distance transform graph

[0077] Exemplarily, the first distance transform graph is generated according to the map information within a preset range around the mobile device, including: generating a first grid map according to the map information within a preset range around the mobile device, the first grid map containing marked passable areas and impassable areas; and converting the first grid map into a first distance transform graph by using a preset algorithm, the first distance transform graph including distance values of each to-be-detected point from the nearest obstacle.

[0078] Exemplarily, the preset algorithm can use a mask method or a brushfire algorithm, or other algorithms, which are not limited in the present application.

[0079] Exemplarily, the map information within a certain area around the current vehicle is cropped as the first input source. The map information is saved in the form of a grid map. As shown in Figure 6 The grid map under the map information in the present application is shown in the figure, which is also called a binary image. Among them, the obstacle area (impassable area) is set to 0, and the area without obstacles (passable area) is set to 255.

[0080] Next, the binary image is processed by distance transform to convert it into a first distance transform graph. Among them, the value of the grid point (corresponding to the to-be-detected point) in the obstacle area is 0, and the value of the grid point in the area without obstacles is the distance value of the grid point from the nearest obstacle point. Since there are many algorithms for generating a first distance transform graph (for example, mask method and brushfire algorithm), here we use a relatively simple brushfire algorithm to illustrate the generation.

[0081] AsFigure 7 Fig. 2 shows the schematic diagram of converting the binary image into the first distance transform map by using the eight-neighborhood update method in the present application. Figure 8 Fig. 3 shows the schematic diagram of the first distance transform map generated by using the eight-neighborhood update method in the present application. Exemplarily, starting from the obstacle point, the distance transform value of the obstacle point is set to 0, and the grid points in its 8-neighborhood are traversed, and the distance transform values (the distance from the point to the obstacle) of the grid points in the 8-neighborhood are calculated. Next, in a similar way, the process is pushed out layer by layer, and the distance transform values of the corresponding points are updated. When it is found that different obstacle points have reached the same grid point, the further pushing of the grid point can be stopped. Thus, when the grid points of the entire map are traversed, the distance transform values of the grid points of the entire map are obtained, i.e., the entire distance transform map is obtained.

[0082] 2. Establishing the second distance transform map

[0083] Exemplarily, the second distance transform map generated according to the real-time information around the mobile device detected by the sensors of the mobile device comprises:

[0084] The second grid map comprises the marked passable region and the marked impassable region. The second distance transform map is generated by using a preset algorithm to transform the second grid map, and the second distance transform map comprises the distance value of each to-be-detected point to the nearest obstacle.

[0085] Exemplarily, the preset algorithm can use the mask method or the brushfire algorithm, or other algorithms, and the present application is not limited thereto.

[0086] Exemplarily, the method for establishing the distance transform map under real-time perception is as follows:

[0087] The vehicle is taken as the center, and a certain range around the vehicle is taken as the to-be-observed region. The obstacle points in the perception output are projected into the to-be-observed region. The region containing the obstacle points is set to 0, and the region not containing the obstacle points is set to 255. Thus, the binary grid point map under real-time perception (corresponding to the second grid map) is obtained. Then, the corresponding distance transform map is generated based on the binary grid point map, and the process is the same as the generation process in the first step, which is not described herein again.

[0088] 3. Path collision detection design based on the distance transform

[0089] After the two distance transform maps are generated, the path collision detection design can be performed.

[0090] Under the historical map, the map distance change value at any point (x, y) is recorded as D_MAP x,y ; any point (x, y) corresponds to the point to be detected.

[0091] Under the real-time perception map, the perception distance change value at any point (x, y) is recorded as D_OBS x,y .

[0092] At any point (x, y), the minimum passing distance of the vehicle at the point is recorded as D_FREE x,y . As long as there is no obstacle within the distance range of D_FREE x,y , it is considered that the vehicle can pass at the point, recorded as FLAG = 1; otherwise, recorded as FLAG = 0. How to obtain the FLAG value at a certain point (x, y) is described below.

[0093] In actual operation, the vehicle has a certain positioning deviation, so although there is information input of the priori map, it is still necessary to maintain a certain fault tolerance for the priori map. For the perception map, based on the characteristics of the laser radar, camera and other sensors on the vehicle, the closer the obstacle to the vehicle, the higher the detection accuracy; the farther the obstacle to the vehicle, the lower the detection accuracy. Therefore, we divide the calculation of FLAG into two cases for consideration:

[0094] When the distance between the point (x, y) and the vehicle is less than a certain distance value d, at this time we can consider that the accuracy of perception is relatively reliable, and based on the perception map alone, if D_FREE x,y ﹤D_OBS x,y , it is considered that the vehicle can pass under the perception map; and the historical map is affected by the positioning deviation, and the accuracy influence of the historical map is set to σ, so it is considered that if D_FREE x,y -σ﹤D_MAP x,y , the vehicle can pass under the historical map. In summary, we obtain the following conclusions:

[0095]

[0096] When the distance between the point (x, y) and the vehicle is greater than or equal to the distance value d, at this time the accuracy of perception will decrease, and the accuracy influence of the perception map at this time is set to γ, so it is considered that if D_FREE x,y -γ<D_OBS x,y , the vehicle can pass under the perception map; and for the historical map, the positioning deviation influence still exists, so it is considered that if D_FREE x,y -σ<D_MAP x,y , the vehicle can pass in the historical map. The conclusions are as follows:

[0097]

[0098] The collision detection mechanism obtained from the above formula is the final detection result.

[0099] The embodiment of the present application considers the influence of perception and map deviation, establishes a fault-tolerant mechanism for perception and prior map, ensures the stability of the vehicle in collision detection, and avoids the situation that the vehicle is stuck in a narrow lane or other special scenes.

[0100] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of actions, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application. In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0101] In some embodiments, the embodiment of the present application also provides an electronic device, comprising at least one processor, and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the collision detection method.

[0102] In some embodiments, the embodiment of the present application also provides a mobile device comprising a body and an electronic device according to any of the foregoing embodiments mounted on the body. Wherein the mobile device can be an unmanned vehicle, such as an unmanned cleaning vehicle, an unmanned scrubbing vehicle, an unmanned logistics vehicle, an unmanned passenger vehicle, an unmanned sanitation vehicle, an unmanned minibus / bus, a truck, a mine car, etc., and can also be a robot, etc.

[0103] In some embodiments, the embodiment of the present application provides a computer readable storage medium comprising a program or instructions, which, when executed on a computer, implement the collision detection method of any one of the embodiments of the present application.

[0104] In some embodiments, the embodiment of the present application also provides a computer program product, which, when executed on a computer, enables the computer to perform the collision detection method of any one of the embodiments of the present application.

[0105] Figure 9is a schematic diagram of a hardware structure of an electronic device for performing a collision detection method according to another embodiment of the present application, as shown in the figure, the device includes: Figure 9

[0106] one or more processors 910 and a memory 920, Figure 9 The one or more processors 910 and the memory 920 are connected through a bus or other means,

[0107] The device for performing the collision detection method can also include an input device 930 and an output device 940.

[0108] The processor 910, the memory 920, the input device 930 and the output device 940 can be connected through a bus or other means, Figure 9 The one or more processors 910 and the memory 920 are connected through a bus or other means,

[0109] The memory 920 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the collision detection method in the embodiments of the present application. The processor 910 performs various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 920, that is, implements the collision detection method of the above method embodiments.

[0110] The memory 920 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the collision detection device, etc. In addition, the memory 920 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 920 can optionally include a memory remotely arranged with respect to the processor 910, which can be connected to the collision detection device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0111] The input device 930 can receive input digital or character information, and generate signals related to user settings and function control of the collision detection device. The output device 940 can include a display device such as a display screen.

[0112] The one or more modules are stored in the memory 920, and when executed by the one or more processors 910, perform the collision detection method in any of the above method embodiments.

[0113] ​The product can execute the method provided in the embodiments of the present application, has the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the embodiments can be referred to the method provided in the embodiments of the present application.

[0114] The electronic device of the embodiments of the present application exists in various forms, including but not limited to:

[0115] (1) Mobile communication device: The feature of this kind of device is to have mobile communication function, and to provide voice and data communication as the main target. This kind of terminal includes: smart phone (such as iPhone), multimedia phone, functional phone, and low-end phone, etc.

[0116] (2) Ultra-mobile personal computer device: This kind of device belongs to the category of personal computer, has computing and processing function, and generally has mobile Internet feature. This kind of terminal includes: PDA, MID and UMPC device, such as iPad.

[0117] (3) Portable entertainment device: This kind of device can display and play multimedia content. This kind of device includes: audio and video player (such as iPod), palm game machine, electronic book, and smart toy and portable vehicle navigation device.

[0118] (4) Other onboard electronic devices with data interaction function, such as vehicle-mounted device installed on vehicle.

[0119] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0120] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions essentially or say the part that contributes to the related art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment or some part of the embodiment.

[0121] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A collision detection method, comprising: generating a first distance transform map according to map information within a preset range around a mobile device; generating a second distance transform map according to real-time information around the mobile device detected by a sensor of the mobile device; determining whether a to-be-detected point is passable according to the first distance transform map, to obtain a first collision detection result; determining whether the to-be-detected point is passable according to the second distance transform map, to obtain a second collision detection result; determining that the to-be-detected point is a collision point when the first collision detection result and / or the second collision detection result indicates that the to-be-detected point is not passable; comparing whether a distance between the mobile device and the to-be-detected point is less than a preset distance threshold; if not, the determining whether the to-be-detected point is passable according to the second distance transform map, to obtain the second collision detection result, comprises: determining a perception distance change value of the to-be-detected point according to the second distance transform map, the perception distance change value being a distance of the to-be-detected point to a nearest obstacle; correcting the perception distance change value by a perception correction value, to obtain a corrected perception distance change value; and determining whether the corrected perception distance change value is greater than a minimum safety distance, to obtain the second collision detection result. 2.The method of claim 1, wherein the determining whether the to-be-detected point is passable according to the first distance transform map, to obtain the first collision detection result, comprises: determining a map distance change value of the to-be-detected point according to the first distance transform map, the map distance change value being a distance of the to-be-detected point to a nearest obstacle; and determining whether the map distance change value is greater than the minimum safety distance, to obtain the first collision detection result. 3.The method of claim 1, wherein the determining whether the to-be-detected point is passable according to the first distance transform map, to obtain the first collision detection result, comprises: determining a map distance change value of the to-be-detected point according to the first distance transform map, the map distance change value being a distance of the to-be-detected point to a nearest obstacle; correcting the map distance change value by a positioning correction value, to obtain a corrected map distance change value; and determining whether the corrected map distance change value is greater than the minimum safety distance, to obtain the first collision detection result; and further comprising: comparing whether the distance between the mobile device and the to-be-detected point is less than the preset distance threshold; if yes, the determining whether the to-be-detected point is passable according to the second distance transform map, to obtain the second collision detection result, comprises: determining a perception distance change value of the to-be-detected point according to the second distance transform map, the perception distance change value being a distance of the to-be-detected point to a nearest obstacle; and determining whether the perception distance change value is greater than the minimum safety distance, to obtain the second collision detection result. The generating the first distance transform map according to map information within a preset range around a mobile device comprises: generating a first grid map according to map information within a preset range around a mobile device, the first grid map containing marked passable areas and impassable areas. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 4. The method according to any one of claims 1 to 3, characterized in that, ​ ​ ​ ​ ​ 5. The method of claim 1, wherein, ​ ​ The first raster map is converted into a first distance transform map by using a preset algorithm, and the first distance transform map includes distance values of each detection point to the nearest obstacle.

6. The method of claim 1, wherein, The second distance transform map is generated according to real-time information around the mobile device detected by sensors of the mobile device, and the second distance transform map includes: The second raster map is generated according to real-time information around the mobile device detected by sensors of the mobile device, and the second raster map includes marked passable areas and impassable areas. The second raster map is converted into a second distance transform map by using a preset algorithm, and the second distance transform map includes distance values of each detection point to the nearest obstacle.

7. An electronic device comprising: At least one processor, and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the collision detection method of any one of claims 1-6. 8.A mobile device comprising a body and the electronic device of claim 7 mounted on the body.

9. A computer-readable storage medium, characterized in that, A program or instructions, when executed on a computer, implement the collision detection method of any one of claims 1-6.

10. A computer program product, characterised in that, When the computer program product is executed on a computer, the computer is caused to perform the collision detection method of any one of claims 1-6.

Images