Boundary escape method and device for unmanned sweeper
By acquiring the location information of the vehicle and the road boundary, it can determine whether the vehicle is stuck and select an escape route based on the current position relationship. This solves the problem of unmanned sweeping vehicles getting stuck due to observation and control errors and achieves automatic escape.
Patent Information
- Application Number
- CN202511087707.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-05
- Publication Date
- 2025-10-31
AI Technical Summary
During operation, the unmanned sweeper vehicle encountered interference with the boundary due to observation and control errors, and was unable to extricate itself, requiring manual rescue.
By acquiring the location information of the vehicle and the road boundary, it determines whether the vehicle is stuck, and determines the current position relationship based on the vehicle's geometric information and boundary information, and selects a preset escape path to achieve automatic escape.
It enables unmanned sweeping vehicles to automatically extricate themselves from stuck situations, avoiding manual intervention and improving work efficiency.
Smart Images
Figure CN120871866A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of unmanned driving technology, and more specifically, to a method and device for an unmanned sweeper to get out of trouble at the boundary. Background Technology
[0002] With the development of autonomous driving technology, the use of unmanned cleaning vehicles is becoming increasingly widespread. During operation, road boundaries are often the focus of cleaning, such as the boundaries between lanes and sidewalks, or lanes and green belts. Furthermore, in many cases, steps are present at these boundaries, requiring the unmanned cleaning vehicle to work close to these edges to effectively clean hard-to-reach areas.
[0003] Under normal circumstances, during the edge-keeping operation of an unmanned sweeper, its boundary contour is parallel to the road boundary, allowing the sweeper to move along the road boundary. However, in actual operation, due to observation and control errors, interference between the vehicle's collision model and the boundary is inevitable. This often results in the vehicle becoming stuck in place, awaiting manual rescue, unable to extricate itself. Therefore, how to achieve automatic boundary extrication for unmanned sweepers has become an urgent technical problem to be solved. Summary of the Invention
[0004] This application provides a method and apparatus for unmanned sweeping vehicles to escape boundary obstacles, so as to realize the automatic boundary obstacle escape of unmanned sweeping vehicles. The specific technical solution is as follows.
[0005] In a first aspect, embodiments of this application provide a method for an unmanned cleaning vehicle to escape from a boundary obstacle, the method comprising:
[0006] Obtain the vehicle's current location information and road boundary information; the road boundary information includes at least the start point and end point of the road boundary, and a directed line segment composed of the start point and the end point;
[0007] Based on the vehicle's location information and the road boundary information, determine whether the vehicle is trapped;
[0008] When it is determined that the vehicle is trapped, the current positional relationship between the vehicle and the road boundary is determined based on the vehicle's geometric information and the road boundary information; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current positional relationship includes whether the front or rear of the vehicle crosses the boundary, and whether the vehicle is located on the right or left side of the road boundary;
[0009] Obtain the pre-defined correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, which is used as the current escape path of the vehicle.
[0010] In one embodiment of this application, the step of determining whether the vehicle is trapped based on the vehicle's location information and the road boundary information includes:
[0011] Based on the vehicle's position information and the road boundary information, determine whether the vehicle's external outline geometrically intersects with the road boundary;
[0012] If they intersect, the vehicle is determined to be trapped; if they do not intersect, the vehicle is determined to be not trapped.
[0013] In one embodiment of this application, the step of determining the current positional relationship between the vehicle and the road boundary based on the vehicle's geometric information and the road boundary information includes:
[0014] Calculate the distance from the midpoint of the vehicle's front end to the road boundary.
[0015] Calculate the distance from the midpoint of the rear of the vehicle to the road boundary.
[0016] Based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle, determine the boundary that the front or rear of the vehicle crosses;
[0017] The location of the vehicle on the right or left side of the road boundary is determined based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle.
[0018] In one embodiment of this application, the step of calculating the distance from the midpoint of the vehicle's front to the road boundary includes:
[0019] The distance l_h between the midpoint of the vehicle's front and the road boundary is calculated using the following formula:
[0020] l_h=(e x -s x )*(h y -s y )-(h x -s x )*(e y -s y )
[0021] The coordinates of the midpoint of the vehicle's front are (h x h y The starting point coordinates of the road boundary are (s) x s y The endpoint coordinates of the road boundary are (e) x e y );
[0022] The distance l_t from the midpoint of the rear of the vehicle to the road boundary is calculated using the following formula:
[0023] l_t=(e x -s x )*(t y -s y )-(t x -s x )*(e y -s y )
[0024] Wherein, the coordinates of the midpoint of the rear of the vehicle are (t x , t y ).
[0025] In one embodiment of this application, the step of determining whether the vehicle's front or rear crosses a boundary based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle includes:
[0026] When the distance between the front and rear of the vehicle is less than the distance between the rear and the front of the vehicle, the boundary crossed by the front of the vehicle is determined; when the distance between the front and rear of the vehicle is greater than the distance between the rear and the front of the vehicle, the boundary crossed by the rear of the vehicle is determined.
[0027] The step of determining whether the vehicle is located on the right or left side of the road boundary based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle includes:
[0028] When the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is less than 0, the vehicle is determined to be located on the right side of the road boundary; when the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is greater than 0, the vehicle is determined to be located on the left side of the road boundary.
[0029] In one embodiment of this application, the correspondence between the positional relationships and the escape paths includes:
[0030] If the rear of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: proceed straight or turn left.
[0031] If the rear of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: proceed straight or turn right.
[0032] If the front of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: either proceed straight and reverse or turn left and reverse.
[0033] If the front of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: either proceed straight and reverse or turn right and reverse.
[0034] The straight-forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; the right-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right; the straight-backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; and the right-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right.
[0035] In one embodiment of this application, the step of determining the target escape path corresponding to the current position relationship in the correspondence relationship as the current escape path of the vehicle includes:
[0036] In the correspondence, determine the straight path corresponding to the current position relationship, and determine whether the straight path passes through an obstacle; the straight path includes a straight forward path or a straight backward path;
[0037] When the straight path does not pass through an obstacle, the straight path is determined as the vehicle's current escape path. When the straight path passes through an obstacle, the other path corresponding to the current position relationship is determined as the vehicle's current escape path.
[0038] Secondly, embodiments of this application provide a boundary escape device for an unmanned sweeper, the device comprising:
[0039] The information acquisition module is used to acquire the current location information of the vehicle and the road boundary information; the road boundary information includes at least the starting point and the ending point of the road boundary, and a directed line segment composed of the starting point and the ending point;
[0040] The vehicle entrapment determination module is used to determine whether the vehicle is entrapped based on the vehicle's location information and the road boundary information.
[0041] The position relationship determination module is used to determine the current position relationship between the vehicle and the road boundary based on the vehicle's geometric information and the road boundary information when it is determined that the vehicle is trapped; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current position relationship includes: the front or rear of the vehicle crossing the boundary, and the vehicle being located on the right or left side of the road boundary;
[0042] The escape path determination module is used to obtain the pre-set correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, as the current escape path of the vehicle.
[0043] In one embodiment of this application, the trapped determination module is specifically used for:
[0044] Based on the vehicle's position information and the road boundary information, determine whether the vehicle's external outline geometrically intersects with the road boundary;
[0045] If they intersect, the vehicle is determined to be trapped; if they do not intersect, the vehicle is determined to be not trapped.
[0046] In one embodiment of this application, the positional relationship determination module is specifically used for:
[0047] Calculate the distance from the midpoint of the vehicle's front end to the road boundary.
[0048] Calculate the distance from the midpoint of the rear of the vehicle to the road boundary.
[0049] Based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle, determine the boundary that the front or rear of the vehicle crosses;
[0050] The location of the vehicle on the right or left side of the road boundary is determined based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle.
[0051] In one embodiment of this application, the positional relationship determination module is specifically used for:
[0052] The distance l_h between the midpoint of the vehicle's front and the road boundary is calculated using the following formula:
[0053] l_h=(e x -s x )*(h y -s y )-(h x -s x )*(e y -s y )
[0054] The coordinates of the midpoint of the vehicle's front are (h x h y The starting point coordinates of the road boundary are (s) x s y The endpoint coordinates of the road boundary are (e) x e y );
[0055] The distance l_t from the midpoint of the rear of the vehicle to the road boundary is calculated using the following formula:
[0056] l_t=(e x -s x )*(t y -s y )-(t x -s x )*(e y -s y )
[0057] Wherein, the coordinates of the midpoint of the rear of the vehicle are (t x , t y ).
[0058] In one embodiment of this application, the positional relationship determination module is specifically used for:
[0059] When the distance between the front and rear of the vehicle is less than the distance between the rear and the front of the vehicle, the boundary crossed by the front of the vehicle is determined; when the distance between the front and rear of the vehicle is greater than the distance between the rear and the front of the vehicle, the boundary crossed by the rear of the vehicle is determined.
[0060] The step of determining whether the vehicle is located on the right or left side of the road boundary based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle includes:
[0061] When the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is less than 0, the vehicle is determined to be located on the right side of the road boundary; when the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is greater than 0, the vehicle is determined to be located on the left side of the road boundary.
[0062] In one embodiment of this application, the correspondence between the positional relationships and the escape paths includes:
[0063] If the rear of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: proceed straight or turn left.
[0064] If the rear of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: proceed straight or turn right.
[0065] If the front of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: either proceed straight and reverse or turn left and reverse.
[0066] If the front of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: either proceed straight and reverse or turn right and reverse.
[0067] The straight-forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; the right-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right; the straight-backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; and the right-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right.
[0068] In one embodiment of this application, the escape path determination module is specifically used for:
[0069] In the correspondence, determine the straight path corresponding to the current position relationship, and determine whether the straight path passes through an obstacle; the straight path includes a straight forward path or a straight backward path;
[0070] When the straight path does not pass through an obstacle, the straight path is determined as the vehicle's current escape path. When the straight path passes through an obstacle, the other path corresponding to the current position relationship is determined as the vehicle's current escape path.
[0071] In this embodiment of the application, when the unmanned sweeper is stuck, the path corresponding to the current position relationship between the unmanned sweeper and the road boundary can be selected as the escape path from the preset position relationship and escape path correspondence. Thus, the unmanned sweeper can automatically get out of trouble according to the escape path. In other words, the solution provided by this embodiment of the application can realize the automatic escape of the unmanned sweeper. Attached Figure Description
[0072] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.
[0073] Figure 1 A flowchart illustrating a boundary escape method for an unmanned cleaning vehicle provided in an embodiment of this application is shown.
[0074] Figure 2The following diagrams illustrate different escape paths in the embodiments of this application;
[0075] Figure 3 A schematic diagram of the structure of a boundary escape device for an unmanned sweeper provided in an embodiment of this application is shown. Detailed Implementation
[0076] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0077] It should be noted that the terms "comprising" and "having," and any variations thereof, in the embodiments and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.
[0078] This application discloses a method and apparatus for unmanned sweeping vehicles to escape boundary obstacles, which enables unmanned sweeping vehicles to automatically escape boundary obstacles. The embodiments of this application are described in detail below.
[0079] Figure 1 The illustration shows a flowchart of a boundary escape method for an unmanned cleaning vehicle according to an embodiment of this application. This method can be applied to unmanned cleaning vehicles and may include the following steps:
[0080] S110: Obtain the current location information of the vehicle and the road boundary information; the road boundary information includes at least the starting point and the ending point of the road boundary, and the directed line segment composed of the starting point and the ending point.
[0081] During the operation of unmanned sweepers, due to observation and control errors, interference between the vehicle's collision model and the boundary is inevitable. This often results in the vehicle becoming stuck in place, awaiting manual rescue, and unable to extricate itself. In this embodiment, to achieve automatic boundary extrication for the unmanned sweeper, it can acquire the vehicle's current location information and road boundary information in real time at certain intervals, such as 30 milliseconds, 50 milliseconds, and 100 milliseconds. For example, the vehicle's current location information can be obtained from the positioning module, and the road boundary information can be obtained from the map module.
[0082] The current location information may include the vehicle's outer contour and / or the coordinates of several preset points, such as the midpoint of the front and rear of the vehicle. Alternatively, the required coordinates may be obtained using an algorithm; all of these are possible, and this application does not impose specific limitations on them. The road boundary may be, for example, the outer contour of a step. The road boundary information may include the starting and ending points of the road boundary, as well as a directed line segment composed of the starting and ending points. For example, using the vehicle's center point as a reference, two points on the road boundary at a preset distance from the center point can be determined as the starting and ending points. Furthermore, the point closer to the rear of the vehicle can be used as the starting point, and the point closer to the front of the vehicle can be used as the ending point. The line segment from the starting point to the ending point can be used as the directed line segment identifying the road boundary.
[0083] S120: Determine whether the vehicle is trapped based on its location information and road boundary information.
[0084] In one implementation, the system can determine whether the vehicle's external outline geometrically intersects with the road boundary based on the vehicle's location information and road boundary information; if they intersect, the vehicle is determined to be trapped; if they do not intersect, the vehicle is determined not to be trapped.
[0085] S130: When it is determined that the vehicle is trapped, the current positional relationship between the vehicle and the road boundary is determined based on the vehicle's geometric information and the road boundary information; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current positional relationship includes whether the front or rear of the vehicle crosses the boundary, and whether the vehicle is located on the right or left side of the road boundary.
[0086] In this embodiment, when it is determined that the vehicle is stuck, automatic escape can be achieved. Specifically, the current positional relationship between the vehicle and the road boundary can be determined first, and then the corresponding escape path can be determined based on the current positional relationship. The aforementioned positional relationship includes at least two dimensions: the front or rear of the vehicle crosses the boundary, and the vehicle is located on the right or left side of the road boundary.
[0087] In one implementation, the current positional relationship between the vehicle and the road boundary can be determined according to the following steps: calculating the distance from the midpoint of the vehicle's front to the road boundary; calculating the distance from the midpoint of the vehicle's rear to the road boundary; determining whether the vehicle's front or rear crosses the boundary based on the relationship between the distances of the front and rear; and determining whether the vehicle is located on the right or left side of the road boundary based on the sum of the distances of the front and rear.
[0088] For example, such as Figure 2 As shown, the midpoint of the car's front is point h, the midpoint of the car's rear is point t, the starting point of the road boundary is point s, and the ending point is point e. The directed line segment B formed by the starting point s and the ending point e is the road boundary. The distance l_h from the midpoint of the car's front to the road boundary can be calculated using the following formula:
[0089] l_h=(e x -s x )*(h y -s y )-(h x -s x )*(e y -s y )
[0090] The coordinates of the midpoint of the vehicle's front are (h x h y The starting point coordinates of the road boundary are (s) x s y The endpoint coordinates of the road boundary are (e x e y );
[0091] Calculate the distance l_t from the midpoint of the rear of the vehicle to the road boundary using the following formula:
[0092] l_t=(e x -s x )*(t y -s y )-(t x -s x )*(e y -s y )
[0093] The coordinates of the midpoint of the rear of the vehicle are (t) x , t y ).
[0094] Along the direction of the directed line segment, the left side of the boundary is inside the boundary, and the right side of the boundary is outside the boundary. When the vehicle is on the left side of the boundary, the corresponding distance between the front and rear of the vehicle is positive, and when the vehicle is on the right side of the boundary, the corresponding distance between the front and rear of the vehicle is negative.
[0095] After calculating the distances from the midpoint of the vehicle's front to the road boundary and the distance from the midpoint of the vehicle's rear to the road boundary, the positional relationship between the vehicle and the road boundary can be determined based on these distances. Specifically, when the front distance is less than the rear distance, the vehicle's front crosses the boundary; when the front distance is greater than the rear distance, the vehicle's rear crosses the boundary. When the sum of the front and rear distances is less than 0, the vehicle is located on the right side of the road boundary; when the sum of the front and rear distances is greater than 0, the vehicle is located on the left side of the road boundary.
[0096] S140: Obtain the pre-set correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, as the current escape path of the vehicle.
[0097] In this embodiment of the application, the following correspondences between location relationships and escape paths can be pre-defined:
[0098] If the rear of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: proceed straight or turn left.
[0099] If the rear of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: proceed straight or turn right.
[0100] If the front of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: either proceed straight and reverse or turn left and reverse.
[0101] If the front of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: either proceed straight and reverse or turn right and reverse.
[0102] Among them, such as Figure 2 As shown, the straight-forward path 22 is the forward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0; the left-turn forward path 21 is the forward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; the right-turn forward path 23 is the forward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right; the straight-backward path 25 is the backward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0; the left-turn backward path 24 is the backward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; and the right-turn backward path 26 is the backward path recursively generated based on the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right.
[0103] In other words, when the rear of the unmanned sweeper vehicle crosses the boundary and the vehicle itself is on the left side of the road boundary, it can move straight or turn left to move away from the road boundary and thus escape the predicament. When the rear of the unmanned sweeper vehicle crosses the boundary and the vehicle itself is on the right side of the road boundary, it can move straight or turn right to move away from the road boundary and thus escape the predicament. When the front of the unmanned sweeper vehicle crosses the boundary and the vehicle itself is on the left side of the road boundary (e.g., ... Figure 2 As shown, it can reverse or turn left to move away from the road boundary and escape from trouble. When the front of the unmanned sweeper crosses the boundary and the vehicle is on the right side of the road boundary, it can reverse or turn right to move away from the road boundary and escape from trouble.
[0104] Furthermore, in one implementation, to reduce operational difficulty and improve the success rate of escaping trouble, the straight path is prioritized over the turning path. That is, when the autonomous sweeper determines the target escape path corresponding to its current position in the correspondence relationship, it can first determine the straight path corresponding to its current position in the correspondence relationship and determine whether the straight path passes through obstacles; the straight path includes a forward straight path or a backward straight path; when the straight path does not pass through obstacles, the straight path is determined as the vehicle's current escape path; when the straight path passes through obstacles, the other path corresponding to the current position relationship is determined as the vehicle's current escape path.
[0105] In this embodiment of the application, when the unmanned sweeper is stuck, the path corresponding to the current position relationship between the unmanned sweeper and the road boundary can be selected as the escape path from the preset position relationship and escape path correspondence. Thus, the unmanned sweeper can automatically get out of trouble according to the escape path. In other words, the solution provided by this embodiment of the application can realize the automatic escape of the unmanned sweeper.
[0106] like Figure 3 As shown, it illustrates a structural schematic diagram of a boundary escape device for an unmanned sweeper provided in an embodiment of this application. The device includes:
[0107] The information acquisition module 310 is used to acquire the current location information of the vehicle and the road boundary information; the road boundary information includes at least the starting point and the ending point of the road boundary, and a directed line segment composed of the starting point and the ending point.
[0108] The vehicle entrapment determination module 320 is used to determine whether the vehicle is entrapped based on the vehicle's location information and the road boundary information.
[0109] The position relationship determination module 330 is used to determine the current position relationship between the vehicle and the road boundary based on the vehicle's geometric information and the road boundary information when it is determined that the vehicle is trapped; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current position relationship includes: the front or rear of the vehicle crossing the boundary, and the vehicle being located on the right or left side of the road boundary;
[0110] The escape path determination module 340 is used to obtain a pre-set correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, as the current escape path of the vehicle.
[0111] In one embodiment of this application, the trapped determination module 320 is specifically used for:
[0112] Based on the vehicle's position information and the road boundary information, determine whether the vehicle's external outline geometrically intersects with the road boundary;
[0113] If they intersect, the vehicle is determined to be trapped; if they do not intersect, the vehicle is determined to be not trapped.
[0114] In one embodiment of this application, the positional relationship determination module 330 is specifically used for:
[0115] Calculate the distance from the midpoint of the vehicle's front end to the road boundary.
[0116] Calculate the distance from the midpoint of the rear of the vehicle to the road boundary.
[0117] Based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle, determine the boundary that the front or rear of the vehicle crosses;
[0118] The location of the vehicle on the right or left side of the road boundary is determined based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle.
[0119] In one embodiment of this application, the positional relationship determination module 330 is specifically used for:
[0120] The distance l_h between the midpoint of the vehicle's front and the road boundary is calculated using the following formula:
[0121] l_h=(e x -s x )*(h y -s y )-(h x -s x )*(e y -s y )
[0122] The coordinates of the midpoint of the vehicle's front are (h x h y The starting point coordinates of the road boundary are (s) x s y The endpoint coordinates of the road boundary are (e) x e y );
[0123] The distance l_t from the midpoint of the rear of the vehicle to the road boundary is calculated using the following formula:
[0124] l_t=(e x -s x )*(t y -s y )-(t x-s x )*(e y -s y )
[0125] Wherein, the coordinates of the midpoint of the rear of the vehicle are (t x , t y ).
[0126] In one embodiment of this application, the positional relationship determination module 330 is specifically used for:
[0127] When the distance between the front and rear of the vehicle is less than the distance between the rear and the front of the vehicle, the boundary crossed by the front of the vehicle is determined; when the distance between the front and rear of the vehicle is greater than the distance between the rear and the front of the vehicle, the boundary crossed by the rear of the vehicle is determined.
[0128] The step of determining whether the vehicle is located on the right or left side of the road boundary based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle includes:
[0129] When the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is less than 0, the vehicle is determined to be located on the right side of the road boundary; when the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is greater than 0, the vehicle is determined to be located on the left side of the road boundary.
[0130] In one embodiment of this application, the correspondence between the positional relationships and the escape paths includes:
[0131] If the rear of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: proceed straight or turn left.
[0132] If the rear of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: proceed straight or turn right.
[0133] If the front of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: either proceed straight and reverse or turn left and reverse.
[0134] If the front of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: either proceed straight and reverse or turn right and reverse.
[0135] The straight-forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; the right-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right; the straight-backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; and the right-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right.
[0136] In one embodiment of this application, the escape path determination module 340 is specifically used for:
[0137] In the correspondence, determine the straight path corresponding to the current position relationship, and determine whether the straight path passes through an obstacle; the straight path includes a straight forward path or a straight backward path;
[0138] When the straight path does not pass through an obstacle, the straight path is determined as the vehicle's current escape path. When the straight path passes through an obstacle, the other path corresponding to the current position relationship is determined as the vehicle's current escape path.
[0139] In this embodiment of the application, when the unmanned sweeper is stuck, the path corresponding to the current position relationship between the unmanned sweeper and the road boundary can be selected as the escape path from the preset position relationship and escape path correspondence. Thus, the unmanned sweeper can automatically get out of trouble according to the escape path. In other words, the solution provided by this embodiment of the application can realize the automatic escape of the unmanned sweeper.
[0140] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application.
[0141] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.
[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A method for an unmanned cleaning vehicle to escape from boundary obstacles, characterized in that, The method includes: Obtain the vehicle's current location information and road boundary information; the road boundary information includes at least the start point and end point of the road boundary, and a directed line segment composed of the start point and the end point; Based on the vehicle's location information and the road boundary information, determine whether the vehicle is trapped; When it is determined that the vehicle is trapped, the current positional relationship between the vehicle and the road boundary is determined based on the vehicle's geometric information and the road boundary information; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current positional relationship includes whether the front or rear of the vehicle crosses the boundary, and whether the vehicle is located on the right or left side of the road boundary; Obtain the pre-defined correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, which is used as the current escape path of the vehicle.
2. The method according to claim 1, characterized in that, The step of determining whether the vehicle is trapped based on the vehicle's location information and the road boundary information includes: Based on the vehicle's position information and the road boundary information, determine whether the vehicle's external outline geometrically intersects with the road boundary; If they intersect, the vehicle is determined to be trapped; if they do not intersect, the vehicle is determined to be not trapped.
3. The method according to claim 1, characterized in that, The step of determining the current positional relationship between the vehicle and the road boundary based on the vehicle's geometric information and the road boundary information includes: Calculate the distance from the midpoint of the vehicle's front end to the road boundary. Calculate the distance from the midpoint of the rear of the vehicle to the road boundary. Based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle, determine the boundary that the front or rear of the vehicle crosses; The location of the vehicle on the right or left side of the road boundary is determined based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle.
4. The method according to claim 3, characterized in that, The step of calculating the distance from the midpoint of the vehicle's front to the road boundary includes: The distance l_h between the midpoint of the vehicle's front and the road boundary is calculated using the following formula: l_h=(e x -s x )*(h y -s y )-(h x -s x )*(e y -s y ) The coordinates of the midpoint of the vehicle's front are (h x h y The starting point coordinates of the road boundary are (s) x s y The endpoint coordinates of the road boundary are (e) x e y ); The distance l_t from the midpoint of the rear of the vehicle to the road boundary is calculated using the following formula: l_t=(e x -s x )*(t y -s y )-(t x -s x )*(e y -s y ) Wherein, the coordinates of the midpoint of the rear of the vehicle are (t x , t y ).
5. The method according to claim 3, characterized in that, The step of determining whether the front or rear of the vehicle crosses the boundary based on the relationship between the distance between the front and rear of the vehicle includes: When the distance between the front and rear of the vehicle is less than the distance between the rear and the front of the vehicle, the boundary crossed by the front of the vehicle is determined; when the distance between the front and rear of the vehicle is greater than the distance between the rear and the front of the vehicle, the boundary crossed by the rear of the vehicle is determined. The step of determining whether the vehicle is located on the right or left side of the road boundary based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle includes: When the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is less than 0, the vehicle is determined to be located on the right side of the road boundary; when the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle is greater than 0, the vehicle is determined to be located on the left side of the road boundary.
6. The method according to any one of claims 1-5, characterized in that, The correspondence between the various locations and the escape routes includes: If the rear of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: proceed straight or turn left. If the rear of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: proceed straight or turn right. If the front of the vehicle crosses the boundary and the vehicle is located to the left of the road boundary: either proceed straight and reverse or turn left and reverse. If the front of the vehicle crosses the boundary and the vehicle is located on the right side of the road boundary: either proceed straight and reverse or turn right and reverse. The straight-forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; the right-turn forward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right; the straight-backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is 0°; the left-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the left; and the right-turn backward path is generated recursively from the vehicle's two-degree-of-freedom kinematic model when the front wheel angle is fully turned to the right.
7. The method according to claim 6, characterized in that, The step of determining the target escape path corresponding to the current position relationship in the correspondence relationship, and using it as the current escape path of the vehicle, includes: In the correspondence, determine the straight path corresponding to the current position relationship, and determine whether the straight path passes through an obstacle; the straight path includes a straight forward path or a straight backward path; When the straight path does not pass through an obstacle, the straight path is determined as the vehicle's current escape path. When the straight path passes through an obstacle, the other path corresponding to the current position relationship is determined as the vehicle's current escape path.
8. A boundary escape device for an unmanned sweeper, characterized in that, The device includes: The information acquisition module is used to acquire the current location information of the vehicle and the road boundary information; the road boundary information includes at least the starting point and the ending point of the road boundary, and a directed line segment composed of the starting point and the ending point; The vehicle entrapment determination module is used to determine whether the vehicle is entrapped based on the vehicle's location information and the road boundary information. The position relationship determination module is used to determine the current position relationship between the vehicle and the road boundary based on the vehicle's geometric information and the road boundary information when it is determined that the vehicle is trapped; the geometric information includes at least the coordinates of the midpoint of the front of the vehicle and the midpoint of the rear of the vehicle; the current position relationship includes: the front or rear of the vehicle crossing the boundary, and the vehicle being located on the right or left side of the road boundary; The escape path determination module is used to obtain the pre-set correspondence between each position relationship and the escape path, and determine the target escape path corresponding to the current position relationship in the correspondence, as the current escape path of the vehicle.
9. The apparatus according to claim 8, characterized in that, The trapped determination module is specifically used for: Based on the vehicle's position information and the road boundary information, determine whether the vehicle's external outline geometrically intersects with the road boundary; If they intersect, then it is determined that the vehicle is trapped; If they do not intersect, then it is determined that the vehicle is not trapped.
10. The apparatus according to claim 8, characterized in that, The positional relationship determination module is specifically used for: Calculate the distance from the midpoint of the vehicle's front end to the road boundary. Calculate the distance from the midpoint of the rear of the vehicle to the road boundary. Based on the relationship between the distance between the front of the vehicle and the distance between the rear of the vehicle, determine the boundary that the front or rear of the vehicle crosses; The location of the vehicle on the right or left side of the road boundary is determined based on the sum of the distance to the front of the vehicle and the distance to the rear of the vehicle.