Non-structural terrain safety semantic segmentation method considering vehicle-terrain coupling

Abstract

The invention discloses an unstructured terrain safety semantic segmentation method considering vehicle-terrain coupling. The method comprises the following steps: pre-scanning a target to construct an unstructured terrain point cloud; constructing a digital elevation model and a digital gradient model based on the non-structural terrain point cloud model, and dividing a terrain obstacle area in the non-structural terrain; calculating to obtain a critical obstacle height capable of passing through the terrain by using a static kinematic model, and realizing semantic segmentation of risk obstacles in a terrain obstacle area; a steady-state margin angle index is designed in combination with the dynamic roll movement process of the hinged engineering vehicle, and the dynamic stable state of the hinged engineering vehicle is judged; and constructing a vehicle-terrain coupling resolving method, and segmenting the safety semantics of the non-structural terrain into a safety area, a first-level dangerous area and a second-level dangerous area. The method has the beneficial effects that the semantic information dimension of the unstructured terrain is expanded, multi-level danger early warning information is effectively provided for the driving operation of the working vehicle, and the vehicle is guided to operate safely and efficiently.

Description

Technical Field

[0001] The present application relates to the technical field of unstructured terrain point cloud mapping, and in particular to a method for safe semantic segmentation of unstructured terrain considering vehicle-terrain coupling. Background Art

[0002] Unmanned engineering vehicles have shown great application potential in non-structured terrain environments such as large-scale construction, tunnel operations, and disaster relief. High-precision maps are the basic function of unmanned driving systems. They not only rely on high-resolution terrain data, but also require real-time and accurate semantic information to ensure that unmanned vehicles can plan operations safely and effectively.

[0003] In unstructured terrain environments, engineering vehicles travel at a low speed when performing work tasks, mainly because the irregularity of the terrain may cause the vehicle to become unstable and roll over. The center of mass of most engineering vehicles is high, which limits the driver's field of vision. Inaccurate assessment of the terrain's traversability increases the risk of vehicle rollover. By establishing a vehicle-terrain coupling model, the vehicle's driving posture information can be predicted more accurately and the risk warning status of the engineering vehicle can be obtained. However, the real-time calculation of this coupling model has a large time lag and cannot provide sufficient vehicle control decision-making and feedback response time. To this end, by dividing the safety warning status of the point cloud data of unstructured terrain and integrating these warning states as semantic information into high-precision maps, the regional driving safety information and control response feedback can be directly provided to the vehicle in advance, optimizing the operating performance of unmanned engineering vehicles while ensuring safety. Summary of the invention

[0004] One of the objectives of the present application is to provide a non-structural terrain safety semantic segmentation method considering vehicle-terrain coupling that can solve at least one of the defects in the above-mentioned background technology.

[0005] In order to achieve at least one of the above-mentioned purposes, the technical solution adopted in the present application is: a method for safe semantic segmentation of unstructured terrain considering vehicle-terrain coupling, pre-scanning the target to construct an unstructured terrain point cloud, and the safe semantic segmentation method implemented by the unstructured terrain point cloud model includes the following steps.

[0006] Step 1: Build a digital model.

[0007] A digital elevation model and a digital gradient model are constructed based on the unstructured terrain point cloud model, and terrain obstacle areas in the unstructured terrain are divided by the digital gradient model.

[0008] Step 2: Semantic segmentation of risk obstacles.

[0009] The static kinematic model of the articulated engineering vehicle is used to calculate the critical obstacle height of the passable terrain. Based on this, the semantic segmentation of risk obstacles is achieved in the terrain obstacle area.

[0010] Step 3: Determine the dynamic stability state of the articulated engineering vehicle.

[0011] Combined with the dynamic roll motion process of articulated engineering vehicles, a simple and easy-to-use steady-state margin angle index is designed. Based on this, the dynamic stability state judgment of articulated engineering vehicles is realized.

[0012] Step 4: Unstructured Terrain Safe Semantic Segmentation.

[0013] A vehicle-terrain coupling solution method is constructed, and the safety semantics of unstructured terrain is segmented into three levels according to the solved steady-state margin angle index: safe area, primary danger area and secondary danger area.

[0014] Preferably, when the index object in the unstructured terrain point cloud model in step 1 is an elevation value, the digital elevation model can be used, and the specific calculation is as follows:

[0015]

[0016] in, z ( x , y ) is the elevation value of the index; N is the total number of points in the neighborhood point cloud model of unstructured terrain; d is the rasterized edge length, i.e. the model resolution; point cloud ( x i , y i , z i ) is the point cloud ( x , y , z ) nearby neighboring points.

[0017] The discrete gradient of the digital elevation model is expressed as:

[0018] \forall f=\left [ {{^{{g}_{x}}_{{g}_{y}}}} \right ]=\left [ {\frac {\partial f} {\partial x}\, \frac {\partial f} {\partial y}} \right ]=\left [ {f(x+1,y)-f(x,y)\, f(x,y+1)-f(x,y)} \right ]{\,}^{T}

[0019] in, g x , g y They are points ( x , y )exist x , y Directional gradient component.

[0020] The gradient component of the digital gradient model is calculated as:

[0021]

[0022]

[0023] in, l is the side length of the operator grid.

[0024] By calculating the gradient of the digital elevation model, the terrain obstacle area in the unstructured terrain can be divided.

[0025] Preferably, in step 2, the steering hinge point is selected as the vehicle coordinate origin to construct a kinematic model of the articulated engineering vehicle; the vehicle mass mainly includes the front body mass G 1 , front wheel mass G 2 , front swing arm mass G 3 , rear body mass G 4 and rear wheel mass G5; the center of gravity of the vehicle G(x0, y0, z0) is:

[0026]

[0027] Among them, M n is the mass of each body part; G n The coordinates of each body part.

[0028] The contact points of each tire are obtained through geometric motion relationships. P 1l (x 1l , y 1l , z 1l ) , right front wheel P 1r (x 1r , y 1r , z 1r) , left rear wheel P 2l (x 2l , y 2l , z 2l ) and right rear wheel P 2r (x 2r , y 2r , z 2r ) The ground coordinates are:

[0029]

[0030]

[0031] {R}_{1}=\left [ {{^{^{\cos {\theta}}_{\sin {\theta}}}_{{\,}^{0}_{\,}}{^{{\,}^{-\sin {\theta}}_{\cos {\theta}}}_{{\,}^{0}_{\,}}{^{^{0}_{0}\,}_{^{1}_{\,}\,}\,}}}} \right ] , {R}_{2}=\left [ {{^{^{\cos {\alpha}}_{\, \, \, 0}}_{{\,}^{-\sin {\alpha}}_{\,}}{{}^{^{0}_{1}\,}_{{\,}^{0}_{\,}}{^{^{\sin {\alpha}}_{0}\,}_{^{\cos {\alpha}}_{\,}\,}\,}}}} \right ]

[0032] in, W 1 / 2 wheelbase width; L 1 is the distance from the front axle to the center of gravity; L 2 is the distance from the rear axle to the center of gravity; H is the height of the steering hinge point; θ is the articulated steering angle; α is the rear axle swing angle.

[0033] During the static rollover motion of an articulated construction vehicle, the roll angle generated at low speed φ Defined as:

[0034]

[0035] in, h is the obstacle height; D From the tire contact point P 1l Projected distance to the roll axis.

[0036] Then, take a safety factor δ , the critical obstacle height can be derived h 0 for:

[0037]

[0038] in, φ max is the limit rollover angle.

[0039] Preferably, the critical obstacle height of the passable terrain is obtained by calculating the maximum rollover angle of the articulated engineering vehicle; the critical obstacle height of the passable terrain is compared with the actual obstacle elevation value obtained in the digital elevation model, and when the actual obstacle elevation value is less than the critical obstacle height, the invalid obstacle is filtered out, and finally the risk obstacle is further segmented in the unstructured terrain.

[0040] Preferably, in step 3, by constructing the angle between the vehicle mass force vector and the state surface normal vector, the steady-state margin angle of the articulated engineering vehicle is expressed as:

[0041] ,

[0042] in, ψ 1 is the primary steady-state margin angle, which is the minimum angle between the resultant force vector and the primary instability plane; ψ 2 is the secondary stable margin angle, which is the minimum angle between the resultant force vector and the secondary instability plane; is the plane normal vector corresponding to the first-level instability state; is the plane normal vector corresponding to the secondary instability state; is the vehicle mass force vector.

[0043] Based on the steady-state margin angle index, the driving state of articulated engineering vehicles can be divided into three categories: ψ 1 <0, ψ 2 <0 is a stable state; ψ 1 >0, ψ 2 <0 is the first-level instability state; ψ 1 >0, ψ 2 When >0, it is the secondary instability state.

[0044] Preferably, in step 4, the steady-state margin angle solution process is: first, calculate the X / Y coordinates of the four vehicle tire contact points, the coordinates of the vehicle center of gravity and the rear axle hinge point; then, index the digital elevation model to determine their elevation values ​​in the Z direction; finally, obtain the steady-state margin angle through real-time dynamic solution of the normal vector and resultant force vector of each state surface, thereby realizing the stable state judgment of the articulated engineering vehicle.

[0045] Preferably, the vehicle steering angle is set to three situations: straight driving, maximum left turn and maximum right turn, and the vehicle heading angle is set to eight directions: east, south, west, north, southeast, southwest, northwest and northeast; a total of 24 state combinations are constructed to solve the stability of the vehicle in different movement directions. After solving, the steady-state margin angle with the worst driving state among the 24 combinations is selected to judge the current vehicle stability state.

[0046] Preferably, according to the stable state, the primary instability state and the secondary instability state of the steady-state margin angle, the safety semantics of the non-structural terrain are respectively divided into three levels: a safe area, a primary dangerous area and a secondary dangerous area.

[0047] Compared with the prior art, the beneficial effects of this application are:

[0048] (1) The present invention constructs a kinematic model that takes into account the static rollover characteristics of articulated engineering vehicles and obtains the critical obstacle height that can be passed through the terrain. Based on this, risk obstacles are effectively marked and distinguished in terrain mapping.

[0049] (2) The present invention designs a simple and easy-to-use steady-state margin angle indicator. Through the vehicle-terrain coupling solution method, the indicator can effectively characterize the dynamic rollover stability of articulated engineering vehicles and improve the safety semantic segmentation accuracy of unstructured terrain.

[0050] (3) The method of the present invention divides the safety semantics of unstructured terrain into three levels: safe area, primary danger area and secondary danger area, which expands the semantic information dimension of unstructured terrain, effectively provides multi-level danger warning information for working vehicle driving operations, and guides vehicles to operate safely and efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flow chart of the method of this application.

[0052] Figure 2 This is a schematic diagram of the digital gradient model after grayscale in this application.

[0053] Figure 3 Schematic diagram of the coordinate system of the articulated engineering vehicle in this application.

[0054] Figure 4 Schematic diagram of the static rollover process of the articulated engineering vehicle in this application.

[0055] Figure 5 Schematic diagram of the steady-state margin angle of the articulated engineering vehicle in this application.

[0056] Figure 6 Schematic diagram of the steady-state margin angle calculation process in this application.

[0057] Figure 7 Schematic diagram of safe semantic segmentation of unstructured terrain in this application. DETAILED DESCRIPTION

[0058] Below, the present application is further described in conjunction with specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0059] In the description of the present application, it should be noted that directional words, such as the terms "center", "lateral", "longitudinal", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", etc., indicating directions and positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of narrating the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and cannot be understood as limiting the specific scope of protection of the present application.

[0060] It should be noted that the terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0061] The terms "including" and "having" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0062] One aspect of the present application provides a method for safety semantic segmentation of unstructured terrain considering vehicle-terrain coupling. First, in order to generate an unstructured terrain point cloud model for safety semantic segmentation, a method such as a vehicle-mounted laser radar or unmanned aerial vehicle oblique photography is used to obtain scanning point cloud data of unstructured terrain. After obtaining the scanning point cloud data, the abnormal noise points and invalid weed points of the point cloud are filtered by a filtering method. Finally, an optimized and reconstructed unstructured terrain point cloud model is obtained.

[0063] In this embodiment, if Figure 1 As shown, the steps to implement the secure semantic segmentation process in the unstructured terrain point cloud model are as follows.

[0064] Step 1: Construct digital elevation model and digital gradient model.

[0065] Specifically, a digital elevation model and a digital gradient model are constructed based on the unstructured terrain point cloud model, and the terrain obstacle area in the unstructured terrain is divided by the digital gradient model.

[0066] First, when the index object in the unstructured terrain point cloud model is an elevation value, it is a digital elevation model. It is obtained through the two-dimensional grid data of the unstructured terrain, which contains the geometric space coordinates of the X / Y / Z axes. The elevation value can be obtained by processing the grid voxelization mean of the nearby neighborhood point cloud. The specific process is as follows:

[0067]

[0068] in, z ( x , y ) is the elevation value of the index; N is the total number of points in the neighborhood point cloud model of unstructured terrain; d is the rasterized edge length, i.e. the model resolution; point cloud ( x i , y i , z i ) is the point cloud ( x , y , z ) nearby neighboring points.

[0069] Then, based on the digital elevation model, the gradient value of each point in the unstructured terrain point cloud model is calculated to obtain the digital gradient model. x and y The gradient value of the direction, the discrete gradient of the digital elevation model is expressed as:

[0070] \forall f=\left [ {{^{{g}_{x}}_{{g}_{y}}}} \right ]=\left [ {\frac {\partial f} {\partial x}\, \frac {\partial f} {\partial y}} \right ]=\left [ {f(x+1,y)-f(x,y)\, f(x,y+1)-f(x,y)} \right ]{\,}^{T}

[0071] Among them, g x , g y are the gradient components of the point (x, y) in the x and y directions respectively.

[0072] Furthermore, the gradient component can be obtained by calculating the Sobel operator, which is usually used for image edge detection and segmentation. In order to approximately solve the absolute gradient, an improved Sobel operator is designed in this application to establish a digital gradient model, and its operation matrix is ​​described as:

[0073]

[0074]

[0075] in, l is the side length of the operator grid.

[0076] Specifically, by calculating the gradient of the digital elevation model, the grayscale digital gradient model is as follows: Figure 2 As shown, Figure 2 The contour area of ​​terrain obstacles can be clearly observed, thus effectively dividing the terrain obstacle area in unstructured terrain.

[0077] Step 2: Semantic segmentation of risk obstacles.

[0078] In order to distinguish risk obstacles from terrain obstacles, the static rollover stability of engineering vehicles needs to be further considered. Considering the static kinematic model of articulated engineering vehicles, the critical obstacle height that can pass through the terrain is calculated, and based on this, the semantic segmentation of risk obstacles is further realized in the terrain obstacle area.

[0079] Firstly, the articulated engineering vehicle is taken as the working object in the unstructured terrain environment, the steering hinge point is selected as the vehicle coordinate origin, and the kinematic model of the articulated engineering vehicle is constructed. Figure 3 As shown, the vehicle mass mainly includes the front body mass G 1 , front wheel mass G 2, front swing arm mass G 3 , rear body mass G 4 and rear wheel mass G 5 The specific vehicle's center of gravity G ( x 0 , y 0 , z 0 ) is calculated as:

[0080]

[0081] Among them, M n is the mass of each body part; G n The coordinates of each body part.

[0082] Furthermore, in order to obtain the tire contact point, the left front wheel P 1l ( x 1l , y 1l , z 1l ), right front wheel P 1r ( x 1r , y 1r , z 1r ), left rear wheel P 2l ( x 2l , y 2l , z 2l ) and right rear wheel P 2r ( x 2r , y 2r , z 2r )’s ground coordinates are:

[0083]

[0084]

[0085] {R}_{1}=\left [ {{^{^{\cos {\theta}}_{\sin {\theta}}}_{{\,}^{0}_{\,}}{^{{\,}^{-\sin {\theta}}_{\cos {\theta}}}_{{\,}^{0}_{\,}}{^{^{0}_{0}\,}_{^{1}_{\,}\,}\,}}}} \right ] , {R}_{2}=\left [ {{^{^{\cos {\alpha}}_{\, \, \, 0}}_{{\,}^{-\sin {\alpha}}_{\,}}{{}^{^{0}_{1}\,}_{{\,}^{0}_{\,}}{^{^{\sin {\alpha}}_{0}\,}_{^{\cos {\alpha}}_{\,}\,}\,}}}} \right ]

[0086] in, W 1 / 2 wheelbase width; L 1 is the distance from the front axle to the center of gravity; L 2 is the distance from the rear axle to the center of gravity; H is the height of the steering hinge point; θ is the articulated steering angle; α is the rear axle swing angle.

[0087] It should be noted that in order to consider the impact of obstacle height on vehicle trafficability, in this application, by calculating the roll angle threshold when the vehicle passes over an obstacle, invalid obstacles that do not affect the driving stability of the engineering vehicle are eliminated. To this end, a critical height threshold is defined to determine whether the terrain obstacle height obtained by the digital elevation model will cause the vehicle to roll over.

[0088] Specifically, the static rollover process of an articulated engineering vehicle is as follows: Figure 4 When the left front wheel of the vehicle is driving on an obstacle, the roll angle caused by the wheel being lifted is less than the maximum constraint angle of the rear swing bridge. Figure 4 (a) and Figure 4 As shown in (b), the body will surround P 1r P 2 The axle rolls. The roll angle at low speed φ Defined as:

[0089]

[0090] in, h is the obstacle height; D From point P 1l arrive P 1r P 2 The projection distance of the axis.

[0091] Furthermore, when the roll angle exceeds the maximum constraint angle of the rear swing axle, the vehicle body will rotate around P 1r P 2r The axle reaches the critical state of rollover, as shown in the following example: Figure 4 As shown in (c) in the figure, at this time D =2 W After the vehicle goes through these two roll motions in sequence, it will be at risk of rollover. The limit rollover angle can be calculated by the vehicle geometric parameters. δ , the critical obstacle height can be derived h 0 , h 0 The calculation method of is as follows.

[0092]

[0093] in, φ max is the limit rollover angle.

[0094] It can be understood that by calculating the limit rollover angle of the articulated engineering vehicle, the critical obstacle height that can pass through the terrain is obtained. By comparing it with the actual obstacle elevation value obtained in the digital elevation model, when the actual obstacle elevation value is less than the critical obstacle height, the invalid obstacle is filtered out, and finally the risk obstacle is further segmented in the unstructured terrain.

[0095] Step 3: Determine the dynamic stability state of the articulated engineering vehicle.

[0096] Driving safety in complex unstructured terrain environments should further consider the dynamic motion relationship between the vehicle and the terrain. To this end, in combination with the dynamic roll motion process of the articulated engineering vehicle, the present invention designs a simple and easy-to-use steady-state margin angle index, based on which the dynamic stability state judgment of the articulated engineering vehicle is realized.

[0097] Specifically, Figure 5 As shown in (a) in the figure, when the vehicle is in a stable state, the resultant force F Located by plane Δ GP 1lP 1r , Δ GP 1l P 2 and Δ GP 1r P 2 The envelope is within the stable range. Figure 5 As shown in (b) in the figure, when the resultant force F Located by plane Δ GP 1l P 2 , Δ GP 1r P 2 , Δ GP 1l P 2l , Δ GP 1r P 2r and Δ GP 2l P 2r When the vehicle is within the roll range, the vehicle will roll around the lateral roll axis, and the vehicle motion state is defined as the first-level instability state. Figure 5 As shown in (c) in the figure, if the resultant force F Beyond the plane Δ GP 1l P 1r , Δ GP 1l P 2l , Δ GP 2l P 2r and Δ GP 1r P 2r When the maximum roll interval is reached, the vehicle will roll over, and the vehicle motion state is defined as the secondary instability state.

[0098] Furthermore, the steady-state margin angle can be obtained by calculating the angle between the normal vectors of each plane. The plane normal vector corresponding to the primary instability state is It can be calculated by the following formula.

[0099] ,

[0100] Furthermore, the plane normal vector corresponding to the secondary instability state is The resultant force vector can be calculated by the same method. It can be calculated by vehicle gravity and lateral acceleration and can be expressed as:

[0101]

[0102] Finally, the steady-state margin angle of the articulated engineering vehicle is expressed as:

[0103] ,

[0104] in, ψ 1 is the primary steady-state margin angle, which is the minimum angle between the resultant force vector and the primary instability plane; ψ 2 is the secondary stable margin angle, which is the minimum angle between the resultant force vector and the secondary instability plane.

[0105] Through the above calculations, based on the steady-state margin angle index, the driving states of articulated engineering vehicles can be divided into three categories: ψ 1 <0, ψ 2 <0 is a stable state; ψ 1 >0, ψ 2 <0 is the first-level instability state; ψ 1 >0, ψ 2 When >0, it is the secondary instability state.

[0106] Step 4: Unstructured Terrain Safe Semantic Segmentation.

[0107] By constructing a vehicle-terrain coupling solution method, the steady-state margin angle index is further solved based on the static risk obstacles, and the safety semantics of the unstructured terrain are divided into three levels according to the dynamic stability state: safe area, primary danger area and secondary danger area.

[0108] Specifically, Figure 6 As shown, through step 2, the X / Y coordinates of the four vehicle tire contact points, the coordinates of the vehicle center of gravity and the rear axle articulation point can be calculated, and then the digital elevation model is indexed to determine their elevation values ​​in the Z direction. Finally, through step 3, the normal vector and resultant force vector of each state surface can be obtained, and the steady-state margin angle can be obtained by real-time dynamic solution, thereby realizing the stable state judgment of the articulated engineering vehicle.

[0109] Furthermore, since the vehicle will have different tire contact points in different directions of movement, in order to solve the stable state within all driving areas at each vehicle coordinate, the vehicle steering angle is set to three situations: straight driving, maximum left turn and maximum right turn, and the vehicle heading angle is set to eight directions: east, south, west, north, southeast, southwest, northwest and northeast. A total of 24 state combinations are constructed to solve the stable state of the vehicle in different directions of movement. After solving, the stable margin angle with the worst driving state among the 24 combinations is selected to determine the current vehicle stability state.

[0110] Specifically, Figure 7 As shown, an actual terrain is selected and calculated according to the method in this application. According to the stable state, primary instability state, and secondary instability state of the steady-state margin angle, the safety semantics of the non-structural terrain can be divided into three levels: safe area, primary danger area, and secondary danger area. Figure 7 It can be seen that with the increase of the slope of unstructured terrain, the first-level danger area and the second-level danger area increase significantly, and the second-level danger area appears in the slope terrain with a larger slope, which increases the risk of vehicle rollover. At this time, the driving safety will be greatly reduced, which effectively provides danger warning information for the driving operation of working vehicles and guides the safe operation of vehicles.

[0111] The above describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited by the above embodiments. The above embodiments and the description only describe the principles of the present application. The present application may have various changes and improvements without departing from the spirit and scope of the present application. These changes and improvements fall within the scope of the present application for which protection is sought. The scope of protection claimed by the present application is defined by the attached claims and their equivalents.

Claims

1. A safety semantic segmentation method for unstructured terrain considering vehicle-terrain coupling, characterized in that: The target is scanned in advance to construct an unstructured terrain point cloud. The secure semantic segmentation method implemented by the unstructured terrain point cloud model includes the following steps: Step 1: Build a digital model; Building a digital elevation model and a digital gradient model based on the unstructured terrain point cloud model, and dividing terrain obstacle areas in the unstructured terrain by using the digital gradient model; Step 2: Semantic segmentation of risk obstacles; The static kinematic model of the articulated engineering vehicle is used to calculate the critical obstacle height that can pass through the terrain. Based on this, the semantic segmentation of risk obstacles is achieved in the terrain obstacle area. Step 3: Determine the dynamic stability state of the articulated engineering vehicle; Combined with the dynamic roll motion process of articulated engineering vehicles, a simple and easy-to-use steady-state margin angle index is designed, based on which the dynamic stability state judgment of articulated engineering vehicles is realized; Step 4: Unstructured terrain safety semantic segmentation; A vehicle-terrain coupling solution method is constructed, and the safety semantics of unstructured terrain is segmented into three levels according to the solved steady-state margin angle index: safe area, primary danger area and secondary danger area.

2. The method for safe semantic segmentation of unstructured terrain considering vehicle-terrain coupling according to claim 1, characterized in that: When the index object in the unstructured terrain point cloud model in step 1 is an elevation value, the digital elevation model is used, and the specific calculation is as follows: ; in, z ( x , y ) is the elevation value of the index; N is the total number of points in the neighborhood point cloud model of unstructured terrain; d is the rasterized edge length, i.e. the model resolution; point cloud ( x i , y i , z i ) is the point cloud ( x , y , z ) nearby neighboring points; The discrete gradient of the digital elevation model is expressed as: ； in, g x , g y They are points ( x , y )exist x , y Directional gradient component; The gradient component of the digital gradient model is calculated as: ； ； in, l is the side length of the operator grid; By calculating the gradient of the digital elevation model, the terrain obstacle area in the unstructured terrain can be divided.

3. The method for safe semantic segmentation of unstructured terrain considering vehicle-terrain coupling according to claim 1, characterized in that: In step 2, the steering hinge point is selected as the vehicle coordinate origin to construct the kinematic model of the articulated engineering vehicle; the vehicle mass mainly includes the front body mass G1, the front wheel mass G2, the front swing arm mass G3, the rear body mass G4 and the rear wheel mass G5; the center of gravity G(x0, y0, z0) of the vehicle is: ； in, M n is the mass of each body part; G n is the coordinates of each body part; The contact points of each tire are obtained through geometric motion relationships. P 1l ( x 1l , y 1l , z 1l ), right front wheel P 1r ( x 1r , y 1r , z 1r ), left rear wheel P 2l ( x 2l , y 2l , z 2l ) and right rear wheel P 2r ( x 2r , y 2r , z 2r )’s ground coordinates are: ； ； , ； in, W 1 / 2 wheelbase width; L 1 is the distance from the front axle to the center of gravity; L 2 is the distance from the rear axle to the center of gravity; H is the height of the steering hinge point; θ is the articulated steering angle; α is the swing angle of the rear axle; During the static rollover motion of an articulated construction vehicle, the roll angle generated at low speed φ Defined as: ； in, h is the obstacle height; D From the tire contact point P 1l Projected distance to the roll axis; Then, take a safety factor δ , the critical obstacle height can be derived h 0 is: ； in, φ max is the limit rollover angle.

4. The method for safe semantic segmentation of non-structural terrain considering vehicle-terrain coupling as claimed in claim 3, characterized in that: By calculating the maximum rollover angle of the articulated engineering vehicle, the critical obstacle height of the passable terrain is obtained; the critical obstacle height of the passable terrain is compared with the actual obstacle elevation value obtained in the digital elevation model. When the actual obstacle elevation value is less than the critical obstacle height, the invalid obstacle is filtered out, and finally the risk obstacle is further segmented in the unstructured terrain.

5. The method for safe semantic segmentation of unstructured terrain considering vehicle-terrain coupling according to claim 1, characterized in that: In step 3, by constructing the angle between the vehicle mass force vector and the state surface normal vector, the steady-state margin angle of the articulated engineering vehicle is expressed as: ， ； in, ψ 1 is the primary steady-state margin angle, which is the minimum angle between the resultant force vector and the primary instability plane; ψ 2 is the secondary stable margin angle, which is the minimum angle between the resultant force vector and the secondary instability plane; is the plane normal vector corresponding to the first-level instability state; is the plane normal vector corresponding to the secondary instability state; is the vehicle mass force vector; Based on the steady-state margin angle index, the driving state of articulated engineering vehicles can be divided into three categories: ψ 1<0, ψ 2<0 is a stable state; ψ 1>0, ψ When 2<0, it is the first-level instability state; when ψ 1>0, ψ When 2>0, it is the secondary instability state.

6. The method for safe semantic segmentation of non-structural terrain considering vehicle-terrain coupling as claimed in claim 5, characterized in that: The process of solving the steady-state margin angle is as follows: first, calculate the X / Y coordinates of the four vehicle tire contact points, the coordinates of the vehicle center of gravity and the rear axle articulation point; then, index the digital elevation model to determine their elevation values ​​in the Z direction; finally, the steady-state margin angle is obtained through real-time dynamic solution of the normal vector and resultant force vector of each state surface to realize the stable state judgment of the articulated engineering vehicle.

7. The method for safe semantic segmentation of non-structural terrain considering vehicle-terrain coupling as claimed in claim 6, characterized in that: The vehicle steering angle is set to three situations: straight driving, maximum left turn and maximum right turn, and the vehicle heading angle is set to eight directions: east, south, west, north, southeast, southwest, northwest and northeast. A total of 24 state combinations are constructed to solve the stability of the vehicle in different movement directions. After solving, the steady-state margin angle with the worst driving state among the 24 combinations is selected to determine the current vehicle stability state.

8. The method for safe semantic segmentation of non-structural terrain considering vehicle-terrain coupling as claimed in claim 7, characterized in that: According to the stable state, primary instability state and secondary instability state of the steady-state margin angle, the safety semantics of the non-structural terrain are divided into three levels: safe area, primary dangerous area and secondary dangerous area.

Images