Self-adaptive obstacle recognition method, device, equipment, medium and product

Abstract

The invention provides a self-adaptive obstacle recognition method and device, equipment, a medium and a product. The method comprises the following steps: acquiring a first coordinate of a to-be-recognized obstacle in an area array laser radar coordinate system; acquiring the real-time pose of the vehicle body and the real-time pose of the area array laser radar; according to the relation between the real-time pose of the area array laser radar and the real-time pose of the vehicle body, converting a first coordinate of the obstacle to be recognized in the area array laser radar coordinate system into a second coordinate in the vehicle body coordinate system; judging whether the to-be-recognized obstacle is a slope or not based on the second coordinate of the to-be-recognized obstacle in the vehicle body coordinate system; under the condition that the obstacle to be recognized is a slope, a slope angle threshold value is adjusted according to the real-time motion state of the vehicle; according to the relation between the slope angle of the slope and the adjusted slope angle threshold value, whether the slope can pass or not is judged. According to the method, the slope angle threshold value can be adjusted in real time according to different motion states of the vehicle, and the flexibility and accuracy of obstacle recognition of the system are improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an adaptive obstacle recognition method, device, equipment, medium and product. Background Art

[0002] Autonomous driving technology covers multiple key technical fields, among which obstacle recognition is one of the key technologies to ensure the safe driving of unmanned vehicles. Its main goal is to detect and identify various obstacles on the road ahead and take corresponding obstacle avoidance measures.

[0003] Existing obstacle detection algorithms usually judge whether an object is an obstacle based on a fixed threshold, but fail to fully consider the changes in sensor data under different vehicle postures and motion states. In some cases, the vehicle's tilt and uneven height changes will cause distortion of the on-board sensor data. For example, the viewing angle and detection distance of the lidar or camera will shift due to changes in the vehicle's posture, causing the perception system to misjudge the height and position of obstacles on the road ahead. This misjudgment may cause the vehicle to falsely alarm or miss key obstacles, thereby affecting the vehicle's path planning and obstacle avoidance strategies. Summary of the invention

[0004] The present invention provides an adaptive obstacle recognition method, device, equipment, medium and product, which are used to solve the defect in the prior art that a vehicle in motion easily causes distortion of sensor data, thereby leading to misjudgment of obstacles, and to adjust the obstacle discrimination threshold in real time according to the vehicle's motion state, thereby improving the vehicle's obstacle discrimination accuracy.

[0005] The present invention provides an adaptive obstacle recognition method, comprising the following steps.

[0006] Obtain the first coordinate of the obstacle to be identified in the area array laser radar coordinate system; Obtaining the real-time posture of the vehicle body and the real-time posture of the area array laser radar; According to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body, converting the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body; Based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determining whether the obstacle to be identified is a slope; When the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle; Whether the slope is passable is determined based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0007] According to an adaptive obstacle recognition method provided by the present invention, the real-time motion state includes the real-time speed of the vehicle; when the obstacle to be recognized is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the real-time speed of the vehicle is lower than a preset low-speed threshold, lowering the slope angle threshold; If the real-time speed of the vehicle is higher than a preset high-speed threshold, increasing the slope angle threshold; If the real-time speed of the vehicle is between the preset low-speed threshold and the preset high-speed threshold, the slope angle threshold is maintained unchanged.

[0008] According to an adaptive obstacle recognition method provided by the present invention, the real-time motion state includes the real-time posture of the vehicle; when the obstacle to be recognized is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the real-time posture of the vehicle indicates that the vehicle is in a forward leaning state, lowering the slope angle threshold; If the real-time posture of the vehicle indicates that the vehicle is in a backward tilt state, the slope angle threshold is increased.

[0009] According to an adaptive obstacle recognition method provided by the present invention, the real-time motion state includes the road condition information ahead; when the obstacle to be recognized is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the front road condition information indicates that the vehicle is traveling on a slope, the slope angle threshold is reduced based on the slope angle of the front slope.

[0010] According to an adaptive obstacle recognition method provided by the present invention, the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar is converted into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body, including: Generate a rotation matrix according to the real-time position and posture of the area array laser radar and the rotation order of the area array laser radar; Calculating the offset of the original position of the area array laser radar relative to the origin of the vehicle body coordinate system along the three axis directions of the vehicle body coordinate system; Based on the rotation matrix and the offset, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is converted into the second coordinate of the obstacle to be identified in the vehicle body coordinate system.

[0011] According to an adaptive obstacle identification method provided by the present invention, the planar array laser radar includes a plurality of array points; the second coordinate includes ranging data of each array point of the plurality of array points to the obstacle to be identified; and judging whether the obstacle to be identified is a slope based on the second coordinate of the obstacle to be identified includes: Calculating, according to the second coordinates of the obstacle to be identified, a distance value from the distance measurement data of each array point of the plurality of array points to the obstacle to be identified to a preset reference plane in the vehicle body coordinate system; Calculating the difference between the distance measurement values ​​corresponding to two adjacent array points to obtain a first distance between the two adjacent array points; If the errors between any two of all the first distances in the plurality of array points are within a preset range, it is determined that the obstacle to be identified is a slope.

[0012] The present invention also provides an adaptive obstacle recognition device, comprising the following modules: A first coordinate acquisition module, used to acquire the first coordinate of the obstacle to be identified in the area array laser radar coordinate system; A posture acquisition module, used to acquire the real-time posture of the vehicle body and the real-time posture of the area array laser radar; A second coordinate conversion module is used to convert the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body; a slope determination module, configured to determine whether the obstacle to be identified is a slope based on a second coordinate of the obstacle to be identified in the vehicle body coordinate system; A slope angle threshold adjustment module, used to adjust the slope angle threshold according to the real-time motion state of the vehicle when the obstacle to be identified is a slope; The pass determination module is used to determine whether the slope is passable based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the adaptive obstacle recognition method described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the adaptive obstacle recognition method as described above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-mentioned adaptive obstacle recognition methods.

[0016] The adaptive obstacle identification method, device, equipment, medium and product provided by the present invention obtain the first coordinate of the obstacle to be identified in the planar array laser radar coordinate system; obtain the real-time posture of the vehicle body, and obtain the real-time posture of the planar array laser radar; according to the relationship between the real-time posture of the planar array laser radar and the real-time posture of the vehicle body, convert the first coordinate of the obstacle to be identified in the planar array laser radar coordinate system into the second coordinate of the obstacle to be identified in the vehicle body coordinate system; based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determine whether the obstacle to be identified is a slope; in the case where the obstacle to be identified is a slope, adjust the slope angle threshold according to the real-time motion state of the vehicle; according to the relationship between the slope angle of the slope and the adjusted slope angle threshold, determine whether the slope is passable. Compared with the traditional method of using a fixed threshold to determine obstacles, this method can adjust the slope angle threshold in real time and adaptively according to different motion states of the vehicle, including information such as vehicle speed, posture, road conditions, etc., to improve the flexibility and accuracy of the system in identifying obstacles and reduce the probability of misjudgment. This adaptive mechanism is particularly helpful for safe driving and path planning of vehicles in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a schematic diagram of an application scenario of the adaptive obstacle recognition method provided by the present invention.

[0019] Figure 2 It is a schematic diagram of the structure of the area array laser radar provided by the present invention.

[0020] Figure 3 It is a flow chart of the adaptive obstacle recognition method provided by the present invention.

[0021] Figure 4 It is a schematic diagram of a coordinate system constructed on a planar laser radar provided by the present invention.

[0022] Figure 5 It is a flow chart of the ramp identification process provided by the present invention.

[0023] Figure 6It is a flow chart of the obstacle identification and adjustment process provided by the present invention.

[0024] Figure 7 It is a structural schematic diagram of the adaptive obstacle recognition device provided by the present invention.

[0025] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Combine the following Figure 1-Figure 7 Specific embodiments of the present invention are described.

[0028] like Figure 1 As shown, Figure 1 is a schematic diagram of the application scenario of the present application, which shows the installation position of the vehicle-mounted sensors, wherein the array laser radars 101 and 102 are respectively installed on the left and right sides of the front of the unmanned vehicle 103; the inertial measurement unit 104 is installed on the front of the chassis of the unmanned vehicle 103; this figure is only an example, and the specific installation position is not limited to Figure 1 Installation orientation shown.

[0029] It should be noted that the chassis of the unmanned vehicle 103 is parallel to the ground; the inertial measurement unit 104 is parallel to the chassis; the area array laser radar 101 has an inclination angle toward the right and downward, and the area array laser radar 102 has an inclination angle toward the left and downward, which is used to sense small obstacles on the ground.

[0030] Figure 2 The basic structural diagram of the area array laser radar 101 or 102 is shown. The area array laser radar used in the present application can be, for example, 8×8 with a total of 64 ranging points, each ranging point represents a laser radar transmitter, and its field of view angle is θ, θ can be, for example, 45 degrees; the ranging value of each ranging point at the corresponding depth also represents the shortest distance within a rectangular area.

[0031] Figure 3 is one of the flow charts of the adaptive obstacle recognition method provided by the present invention, such as Figure 3 As shown, the method includes the following.

[0032] Step 301: Obtain the first coordinates of the obstacle to be identified in the area array laser radar coordinate system.

[0033] Among them, the coordinate system of the area array laser radar is based on the center of the array as the origin, and a three-dimensional coordinate system is established, such as Figure 4 As shown, it is used to calculate the coordinates of the obstacle to be identified in the area array laser radar coordinate system.

[0034] Specifically, let the current time be T1, and take the laser radar with a field of view angle of 45° as an example. At the current time, when the ranging depth is D, the range represented by the ranging point at the corresponding depth is a rectangle with a side length L of Taking the center of the array laser as the origin, take the ranging point corresponding to the second column to the right of the center of the origin and the second row on the upper side as an example: the ranging information measured by the ranging point can obtain four coordinates.

[0035] ; ; ; .

[0036] The area enclosed by these four coordinates is considered to have a ranging depth of D.

[0037] The coordinate information given by the 64 ranging points is calculated as the first coordinate of the obstacle to be identified in the area array laser radar coordinate system.

[0038] Step 302, obtaining the real-time posture of the vehicle body and the real-time posture of the area array laser radar.

[0039] Specifically, the real-time posture θ1 of the vehicle body is read by the inertial measurement unit 104 , where θ1 includes a heading angle yaw1 , a pitch angle pitch1 , and a roll angle roll1 .

[0040] Since the area array laser radar is installed on the vehicle body, the original pose (i.e., the installation pose) of the area array laser radar is denoted as θ2. Therefore, the real-time pose θ0 of the area array laser radar is based on the real-time pose θ1 of the vehicle body, superimposed with the original pose θ2 (including yaw2, pitch2 and roll2). In summary, the real-time pose θ0 of the area array laser radar is: yaw0=yaw1+yaw2; pitch0=pitch1+pitch2; roll0=roll1+roll2.

[0041] Step 303 , based on the relationship between the real-time posture θ0 of the area array laser radar and the real-time posture θ1 of the vehicle body, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is converted into the second coordinate of the obstacle to be identified in the vehicle body coordinate system.

[0042] This step 303 specifically includes: generating a rotation matrix according to the real-time posture of the area array laser radar and the rotation order of the area array laser radar; calculating the offset of the original posture of the area array laser radar relative to the origin of the vehicle body coordinate system along the three-axis directions of the vehicle body coordinate system; based on the rotation matrix R and the offset, converting the first coordinate of the obstacle to be identified in the area array laser radar coordinate system into the second coordinate of the obstacle to be identified in the vehicle body coordinate system.

[0043] Specifically, according to the rotation sequence of the array laser radar at the above time T1, the rotation matrix R from the array laser radar coordinate system to the vehicle body coordinate system can be obtained. It should be noted that the rotation matrix R changes in real time. Taking the rotation sequence of ZYX as an example, the formula of the rotation matrix R is as follows.

[0044] Among them, yaw is the heading angle around the X-axis, pitch is the pitch angle around the Y-axis, and roll is the roll angle around the Z-axis.

[0045] Through coordinate transformation, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is Converted into the second coordinate of the obstacle to be identified in the vehicle body coordinate system , the conversion relationship is as follows.

[0046] ; in, It is the installation position offset of the area array laser radar compared to the vehicle body coordinate system.

[0047] It should be noted that the transformation relationship between different coordinates in the same frame area array laser radar coordinate system is fixed, and the transformation relationship is only determined by the position and rotation sequence of the area array laser radar and the installation displacement of the area array laser radar.

[0048] The above step 303 can achieve the alignment between the area array laser radar coordinate system and the vehicle body coordinate system, providing data foundation for subsequent slope recognition.

[0049] Step 304 : Based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determine whether the obstacle to be identified is a slope.

[0050] Specifically, combined Figure 4According to the schematic diagram of the ramp identification process shown, the above-mentioned area array laser radar includes multiple array points; step 304 includes: according to the second coordinates of the obstacle to be identified, calculating the ranging value of the ranging data from each array point of the multiple array points to the obstacle to be identified to a preset reference plane in the vehicle body coordinate system; calculating the difference between the ranging values ​​corresponding to two adjacent array points to obtain the first distance between the two adjacent array points; if the errors between all the first distances of the multiple array points are within a preset range, it is determined that the obstacle to be identified is a slope.

[0051] Specifically, the first coordinate information measured at each ranging point in the area array laser radar array is converted into the second coordinate in the vehicle body coordinate system to perform slope recognition. The following conditions must be met to be recognized as a slope.

[0052] ; ; … ; in, It represents the distance measurement value of the distance measurement point in the nth row and the mth column in the vehicle body coordinate system, that is, .

[0053] In step 304, the distance differences between the multiple array points are similar, so that the slope can be automatically identified, providing an effective judgment basis for automatic driving.

[0054] Step 305: if the obstacle to be identified is a slope, adjust the slope angle threshold according to the real-time motion state of the vehicle. .

[0055] Specifically, combined Figure 5 From the obstacle identification adjustment process diagram shown, if the above-mentioned obstacle to be identified is identified as a slope, it is also necessary to determine whether the slope is passable. This application uses a dynamic threshold to determine whether the above-mentioned slope is passable. For example, the vehicle speed and acceleration information is obtained. When the vehicle speed is lower than the preset low-speed threshold, the obstacle recognition threshold is lowered to reduce the excessive recognition of unnecessary obstacles in the low-speed state; when the vehicle speed is higher than the preset high-speed threshold, the recognition threshold is appropriately increased to perceive distant obstacles in advance for earlier avoidance; for example, the vehicle posture information is obtained. If it is detected that the vehicle is in a forward leaning state, the recognition threshold is lowered to enhance the sensitivity to obstacles in front; if the vehicle is in a backward leaning state, the recognition threshold is increased to avoid misidentifying the ground or low objects in front as obstacles; for example, the road condition information ahead is obtained. When the vehicle is driving on a slope, the recognition threshold is adjusted according to the slope angle to prevent the ramp from being misidentified as an obstacle.

[0056] Step 306: Determine whether the slope is passable based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0057] Specifically, the slope is calculated based on the coordinates of the two adjacent rows of array ranging points in the same column of the area array laser radar array. , the calculation method is.

[0058] ; Where L is the side length of the rectangle of a single laser point at the corresponding depth D . Slope angle threshold for unmanned vehicles to pass Can be flexibly set, when satisfied When , the current slope is judged to be impassable, and the slope is identified as an obstacle; when , it is determined that the current slope is passable.

[0059] In the above embodiment, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is obtained; the real-time posture of the vehicle body is obtained, and the real-time posture of the area array laser radar is obtained; according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is converted into the second coordinate of the obstacle to be identified in the vehicle body coordinate system; based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, it is determined whether the obstacle to be identified is a slope; in the case where the obstacle to be identified is a slope, the slope angle threshold is adjusted according to the real-time motion state of the vehicle; according to the relationship between the slope angle of the slope and the adjusted slope angle threshold, it is determined whether the slope is passable. Compared with the traditional method of using a fixed threshold to determine obstacles, this method can adjust the slope angle threshold in real time and adaptively according to different motion states of the vehicle, including vehicle speed, posture, road conditions and other information, thereby improving the flexibility and accuracy of the system in identifying obstacles and reducing the probability of misjudgment. This adaptive mechanism is particularly helpful for safe driving and path planning of vehicles in complex environments.

[0060] In one embodiment, the real-time motion state includes the real-time speed of the vehicle, and the step 305 includes: if the real-time speed of the vehicle is lower than a preset low-speed threshold, the slope angle threshold is lowered; if the real-time speed of the vehicle is higher than a preset high-speed threshold, the slope angle threshold is increased; if the real-time speed of the vehicle is between the preset low-speed threshold and the preset high-speed threshold, the slope angle threshold is maintained unchanged.

[0061] Specifically, the vehicle real-time speed v and acceleration information are obtained, and the basic slope angle threshold is , let the adjusted slope angle threshold be T; when the real-time speed of the vehicle is low, the recognition threshold of the slope angle is lowered to avoid excessive recognition of unnecessary obstacles at low speed; when the real-time speed of the vehicle is high, it is necessary to recognize slopes farther away, so the threshold is increased. The corresponding slope angle threshold adjustment model is as follows.

[0062] ; Among them, α and β are adjustment factors, To preset the low speed threshold, It is the preset high speed threshold.

[0063] The above embodiment can sense distant obstacles for earlier avoidance by appropriately increasing the recognition threshold when the real-time speed of the vehicle is high. When the vehicle speed is lower than the preset low-speed threshold, the slope angle recognition threshold is lowered to reduce the excessive recognition of unnecessary obstacles in the low-speed state.

[0064] In one embodiment, the real-time operating status includes the real-time posture of the vehicle, and the step 305 includes: if the real-time posture of the vehicle indicates that the vehicle is in a forward tilt state, then lowering the slope angle threshold; if the real-time posture of the vehicle indicates that the vehicle is in a backward tilt state, then increasing the slope angle threshold.

[0065] Specifically, the real-time posture of the vehicle is obtained. If it is detected that the vehicle is in a forward leaning state, the recognition threshold is lowered to enhance the sensitivity to obstacles in front. If the vehicle is in a backward leaning state, the recognition threshold is increased to avoid misidentifying the ground or low objects in front as obstacles. The corresponding threshold adjustment model is as follows.

[0066] ; Where k is the attitude adjustment coefficient, is the basic slope angle threshold, The real-time posture of the vehicle.

[0067] In the above embodiment, if it is detected that the vehicle is in a forward leaning state, the recognition threshold is lowered to enhance the sensitivity to obstacles ahead; if the vehicle is in a backward leaning state, the recognition threshold is increased to avoid misidentifying the ground or low objects ahead as obstacles, thereby improving the flexibility and accuracy of obstacle recognition during autonomous driving.

[0068] In one embodiment, the real-time motion status includes forward road condition information, and the step 305 includes: if the forward road condition information indicates that the vehicle is traveling on a slope, reducing the slope angle threshold based on the slope angle of the forward slope.

[0069] Specifically, let the slope angle of the front slope be ,When the vehicle is driving on a slope, the slope angle threshold is adjusted according to the slope angle to reduce the probability of the slope being misidentified as an obstacle.,The model for adjusting the slope angle threshold based on the front slope is as follows.

[0070] ; Where m is the ramp adjustment factor, is the preset maximum slope angle.

[0071] In the above embodiment, when the vehicle is driving on a slope, the discrimination threshold is adjusted according to the slope angle ahead to prevent the ramp from being mistakenly identified as an obstacle. The greater the slope angle, the higher the risk of misidentification. At this time, the threshold is appropriately lowered to improve the accuracy of recognition.

[0072] The adaptive obstacle recognition device provided by the present invention is described below. The adaptive obstacle recognition device described below and the adaptive obstacle recognition method described above can be referred to each other.

[0073] like Figure 7 As shown, Figure 7 A structural schematic diagram of an adaptive obstacle recognition device is shown, which includes:

[0074] The first coordinate acquisition module 701 is used to acquire the first coordinate of the obstacle to be identified in the area array laser radar coordinate system; A posture acquisition module 702 is used to acquire the real-time posture of the vehicle body and the real-time posture of the area array laser radar; A second coordinate conversion module 703 is used to convert the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body; A slope determination module 704, configured to determine whether the obstacle to be identified is a slope based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system; A slope angle threshold adjustment module 705, configured to adjust the slope angle threshold according to the real-time motion state of the vehicle when the obstacle to be identified is a slope; The pass determination module 706 is used to determine whether the slope is passable based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0075] In one embodiment, the real-time motion state includes the real-time speed of the vehicle; the above-mentioned slope angle threshold adjustment module 705 is further used to: if the real-time speed of the vehicle is lower than a preset low-speed threshold, then lower the slope angle threshold; if the real-time speed of the vehicle is higher than a preset high-speed threshold, then increase the slope angle threshold; if the real-time speed of the vehicle is between the preset low-speed threshold and the preset high-speed threshold, then maintain the slope angle threshold unchanged.

[0076] In one embodiment, the real-time motion state includes the real-time posture of the vehicle; the above-mentioned slope angle threshold adjustment module 705 is further used to: if the real-time posture of the vehicle indicates that the vehicle is in a forward leaning state, then lower the slope angle threshold; if the real-time posture of the vehicle indicates that the vehicle is in a backward leaning state, then increase the slope angle threshold.

[0077] In one embodiment, the real-time motion state includes the road condition information ahead; the slope angle threshold adjustment module 705 is further used to: if the road condition information ahead indicates that the vehicle is traveling on a slope, then reduce the slope angle threshold based on the slope angle of the slope ahead.

[0078] In one embodiment, the above-mentioned second coordinate conversion module 603 is further used to: generate a rotation matrix according to the real-time posture of the area array laser radar and the rotation order of the area array laser radar; calculate the offset of the original posture of the area array laser radar relative to the origin of the vehicle body coordinate system along the three-axis directions of the vehicle body coordinate system; based on the rotation matrix and the offset, convert the first coordinate of the obstacle to be identified in the area array laser radar coordinate system into the second coordinate of the obstacle to be identified in the vehicle body coordinate system.

[0079] In one embodiment, the area array laser radar includes multiple array points; the above-mentioned slope judgment module 704 is further used to: calculate the ranging value of the ranging data from each array point of the multiple array points to the obstacle to be identified to a preset reference plane in the vehicle body coordinate system according to the second coordinate of the obstacle to be identified; calculate the difference between the ranging values ​​corresponding to two adjacent array points to obtain the first distance between the two adjacent array points; if the errors between all the first distances in the multiple array points are within a preset range, then determine that the obstacle to be identified is a slope.

[0080] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the adaptive obstacle recognition method, which includes: obtaining the first coordinate of the obstacle to be recognized in the planar array laser radar coordinate system; obtaining the real-time posture of the vehicle body, and obtaining the real-time posture of the planar array laser radar; according to the relationship between the real-time posture of the planar array laser radar and the real-time posture of the vehicle body, converting the first coordinate of the obstacle to be recognized in the planar array laser radar coordinate system into the second coordinate of the obstacle to be recognized in the vehicle body coordinate system; based on the second coordinate of the obstacle to be recognized in the vehicle body coordinate system, determining whether the obstacle to be recognized is a slope; in the case where the obstacle to be recognized is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle; and determining whether the slope is passable according to the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0081] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0082] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the adaptive obstacle recognition method provided by the above methods, which includes: obtaining a first coordinate of an obstacle to be identified in a planar array laser radar coordinate system; obtaining a real-time posture of a vehicle body, and obtaining a real-time posture of the planar array laser radar; according to the relationship between the real-time posture of the planar array laser radar and the real-time posture of the vehicle body, converting the first coordinate of the obstacle to be identified in the planar array laser radar coordinate system into a second coordinate of the obstacle to be identified in the vehicle body coordinate system; based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determining whether the obstacle to be identified is a slope; in the case where the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle; and determining whether the slope is passable according to the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0083] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the adaptive obstacle recognition method provided by the above-mentioned methods, the method comprising: obtaining a first coordinate of an obstacle to be identified in a planar laser radar coordinate system; obtaining a real-time posture of a vehicle body, and obtaining a real-time posture of the planar laser radar; according to the relationship between the real-time posture of the planar laser radar and the real-time posture of the vehicle body, converting the first coordinate of the obstacle to be identified in the planar laser radar coordinate system into a second coordinate of the obstacle to be identified in the vehicle body coordinate system; based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determining whether the obstacle to be identified is a slope; in the case where the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle; and determining whether the slope is passable according to the relationship between the slope angle of the slope and the adjusted slope angle threshold.

[0084] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive obstacle recognition method, characterized in that: include: Obtain the first coordinate of the obstacle to be identified in the area array laser radar coordinate system; Obtaining the real-time posture of the vehicle body and the real-time posture of the area array laser radar; According to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body, converting the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body; Based on the second coordinate of the obstacle to be identified in the vehicle body coordinate system, determining whether the obstacle to be identified is a slope; When the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle; Whether the slope is passable is determined based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

2. The adaptive obstacle recognition method according to claim 1, characterized in that: The real-time motion state includes the real-time speed of the vehicle; when the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the real-time speed of the vehicle is lower than a preset low-speed threshold, lowering the slope angle threshold; If the real-time speed of the vehicle is higher than a preset high-speed threshold, increasing the slope angle threshold; If the real-time speed of the vehicle is between the preset low-speed threshold and the preset high-speed threshold, the slope angle threshold is maintained unchanged.

3. The adaptive obstacle recognition method according to claim 1, characterized in that: The real-time motion state includes the real-time posture of the vehicle; when the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the real-time posture of the vehicle indicates that the vehicle is in a forward leaning state, lowering the slope angle threshold; If the real-time posture of the vehicle indicates that the vehicle is in a backward tilt state, the slope angle threshold is increased.

4. The adaptive obstacle recognition method according to claim 1, characterized in that: The real-time motion state includes the road condition information ahead; when the obstacle to be identified is a slope, adjusting the slope angle threshold according to the real-time motion state of the vehicle includes: If the front road condition information indicates that the vehicle is traveling on a slope, the slope angle threshold is reduced based on the slope angle of the front slope.

5. The adaptive obstacle recognition method according to claim 1, characterized in that: The method of converting the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body comprises: Generate a rotation matrix according to the real-time posture of the area array laser radar and the rotation order of the area array laser radar; Calculating the offset of the original position of the area array laser radar relative to the origin of the vehicle body coordinate system along the three axis directions of the vehicle body coordinate system; Based on the rotation matrix and the offset, the first coordinate of the obstacle to be identified in the area array laser radar coordinate system is converted into the second coordinate of the obstacle to be identified in the vehicle body coordinate system.

6. The adaptive obstacle recognition method according to claim 1, characterized in that: The area array laser radar includes a plurality of array points; the second coordinate includes the ranging data of each array point of the plurality of array points to the obstacle to be identified; The determining, based on the second coordinate of the obstacle to be identified, whether the obstacle to be identified is a slope includes: Calculating, according to the second coordinates of the obstacle to be identified, a distance value from the distance measurement data of each array point of the plurality of array points to the obstacle to be identified to a preset reference plane in the vehicle body coordinate system; Calculating the difference between the distance measurement values ​​corresponding to two adjacent array points to obtain a first distance between the two adjacent array points; If the errors between any two of all the first distances in the plurality of array points are within a preset range, it is determined that the obstacle to be identified is a slope.

7. An adaptive obstacle recognition device, characterized in that: include: A first coordinate acquisition module, used to acquire the first coordinate of the obstacle to be identified in the area array laser radar coordinate system; A posture acquisition module, used to acquire the real-time posture of the vehicle body and the real-time posture of the area array laser radar; A second coordinate conversion module is used to convert the first coordinate of the obstacle to be identified in the coordinate system of the area array laser radar into the second coordinate of the obstacle to be identified in the coordinate system of the vehicle body according to the relationship between the real-time posture of the area array laser radar and the real-time posture of the vehicle body; a slope determination module, configured to determine whether the obstacle to be identified is a slope based on a second coordinate of the obstacle to be identified in the vehicle body coordinate system; A slope angle threshold adjustment module, used to adjust the slope angle threshold according to the real-time motion state of the vehicle when the obstacle to be identified is a slope; The pass determination module is used to determine whether the slope is passable based on the relationship between the slope angle of the slope and the adjusted slope angle threshold.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the adaptive obstacle recognition method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the adaptive obstacle recognition method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the adaptive obstacle recognition method according to any one of claims 1 to 6 is implemented.

Images