Collision detection method and apparatus, autonomous mobile device, storage medium

Abstract

Embodiments of the present application provide a collision detection method and device, an autonomous mobile device and a storage medium, and relate to the technical field of autonomous mobile devices. The collision detection method comprises the following steps: acquiring a contour point, a current speed and a preset parameter of the autonomous mobile device in a vehicle body coordinate system; calculating a new contour point of the autonomous mobile device in a motion coordinate system according to the contour point of the autonomous mobile device in the vehicle body coordinate system, the new contour point of the autonomous mobile device forming a new contour of the autonomous mobile device; sequentially constructing an emergency stop area, a soft stop area and a deceleration area according to the new contour of the autonomous mobile device, the current speed and the preset parameter; and performing collision detection according to the emergency stop area, the soft stop area and the deceleration area, so that a suddenly appearing obstacle can be quickly and accurately detected, so as to quickly respond to the suddenly appearing obstacle, and thus the movement safety of the autonomous mobile device is ensured.

Description

Technical Field

[0001] This application relates to the field of autonomous mobile device technology, and more specifically, to a collision detection method and apparatus, an autonomous mobile device, and a storage medium. Background Technology

[0002] In recent years, autonomous mobile devices, such as Autonomous Mobile Robots (AMRs) or Automated Guided Vehicles (AGVs), have been widely used in various scenarios, such as intelligent logistics warehousing, due to their autonomy and high efficiency.

[0003] Currently, collision detection methods typically employ either map-based methods or radar-integrated safety programmable logic controllers (PLCs) to respond to obstacles and ensure the safety of autonomous mobile devices. Map-based collision detection is highly dependent on the accuracy and stability of the autonomous mobile device's positioning module, and is affected by map resolution, introducing resolution errors that lead to false obstacle detections. The radar-integrated safety PLC-based collision detection scheme has complex and simplistic computational logic, making recovery difficult and struggling to handle diverse and complex scenarios, failing to adapt to various user needs, and exhibiting poor versatility. In other words, current collision detection methods suffer from both poor accuracy and limited versatility. Summary of the Invention

[0004] In view of the above problems, this application proposes a key detection circuit, method, device, home appliance, and storage medium to improve the problems of poor collision detection accuracy and poor versatility of current collision detection methods.

[0005] In a first aspect, embodiments of this application provide a collision detection method, the method comprising: acquiring the contour points, current speed, and preset parameters of an autonomous mobile device in a vehicle coordinate system; calculating new contour points of the autonomous mobile device in a motion coordinate system based on the contour points of the autonomous mobile device in the vehicle coordinate system, the new contour points of the autonomous mobile device forming a new contour of the autonomous mobile device; sequentially constructing an emergency stop region, a soft stop region, and a deceleration region based on the new contour of the autonomous mobile device, the current speed, and the preset parameters; and performing collision detection based on the emergency stop region, the soft stop region, and the deceleration region.

[0006] Secondly, embodiments of this application provide a collision detection device, which includes: a contour point acquisition module for acquiring contour points of an autonomous mobile device in a vehicle coordinate system; a coordinate calculation module for calculating new contour points of the autonomous mobile device in a motion coordinate system based on the contour points of the autonomous mobile device in the vehicle coordinate system, wherein the new contour points of the autonomous mobile device form a new contour of the autonomous mobile device; a region construction module for sequentially constructing an emergency stop region, a soft stop region, and a deceleration region based on the new contour of the autonomous mobile device; and a collision detection module for performing collision detection based on the emergency stop region, the soft stop region, and the deceleration region.

[0007] Thirdly, embodiments of this application provide an autonomous mobile device, which includes a memory and a processor. The memory stores an application program that is used to execute the method provided in embodiments of this application when invoked by the processor.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which, when invoked by a processor, causes the processor to execute the method provided in embodiments of this application.

[0009] The collision detection method, apparatus, autonomous mobile device, and storage medium provided in this application can convert the contour points of the autonomous mobile device in the vehicle coordinate system into new contour points in the motion coordinate system. Based on the new contour points formed by the autonomous mobile device, the current speed, and preset parameters, emergency stop regions, soft stop regions, and deceleration regions are constructed in real time. Collision detection is performed based on these constructed regions, enabling rapid and accurate detection of suddenly appearing obstacles, allowing for quick responses and ensuring the mobile safety of the autonomous mobile device. Compared to current map-based collision detection methods, the collision detection method in this application has lower dependence on the positioning module and is not affected by map resolution, resulting in higher collision detection accuracy. Compared to current collision detection methods based on radar-integrated PLCs, the collision detection method in this application has simpler computational logic, can handle various application scenarios, and has high versatility. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments and drawings obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] Figure 1 A schematic flowchart of the collision detection method provided in an embodiment of this application is shown;

[0012] Figure 2 This illustration shows a schematic diagram of an actual scenario corresponding to the current splicing path provided by an exemplary embodiment of this application;

[0013] Figure 3 This illustration shows a schematic diagram of an actual scenario corresponding to the current splicing path provided by another exemplary embodiment of this application;

[0014] Figure 4 This illustration shows a schematic diagram of an actual scenario corresponding to the current splicing path provided by yet another exemplary embodiment of this application;

[0015] Figure 5 A schematic diagram of the vehicle coordinate system and motion coordinate system provided in an embodiment of this application is shown;

[0016] Figure 6 This illustration shows a schematic diagram of an emergency stop area, a soft stop area, and a deceleration area provided in an exemplary embodiment of this application.

[0017] Figure 7 This illustration shows a schematic diagram of an emergency stop area, a soft stop area, and a deceleration area provided in another exemplary embodiment of this application;

[0018] Figure 8 A flowchart illustrating a collision detection method provided in an exemplary embodiment of this application is shown.

[0019] Figure 9 A schematic diagram of the collision detection device provided in an embodiment of this application is shown;

[0020] Figure 10 A schematic diagram of the structure of the autonomous mobile device provided in an embodiment of this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] Please see Figure 1 , Figure 1 A schematic flowchart of a collision detection method according to an embodiment of this application is shown. This collision detection method can be applied to a collision detection device or an autonomous mobile device (e.g., an AGV or AMR). The collision detection method may include the following steps S110 to S140.

[0023] Step S110: Obtain the contour points, current speed, and preset parameters of the autonomous mobile device in the vehicle coordinate system.

[0024] The vehicle coordinate system takes the rear axle center of the autonomous mobile device as its origin, the front of the autonomous mobile device (i.e., the direction of the vehicle's front) as the positive direction of the x-axis, and the left side of the autonomous mobile device as the positive direction of the y-axis. The contour points of the autonomous mobile device at least include a rectangle representing the autonomous mobile device (e.g.,...). Figure 2-4 The rectangle (JKML) shown has four vertices. The length of the rectangle is greater than or equal to the maximum length of the autonomous mobile device, and the width of the rectangle is greater than or equal to the maximum width of the autonomous mobile device. A positioning module is installed on the autonomous mobile device, which can sense and output the coordinates of the contour points of the autonomous mobile device in the vehicle coordinate system in real time.

[0025] The current velocity of the autonomous mobile device is a vector, and the current velocity has a direction of motion. The current rotational speed of the autonomous mobile device can be read as the current velocity value, and the direction of motion of the current velocity can be represented by the angle between the current orientation of the autonomous mobile device's tires and the x-axis of the vehicle coordinate system.

[0026] Preset parameters are parameters that are pre-set and stored, and can be directly recalled during the movement of the autonomous mobile device. Preset parameters may include pre-set safety distances, speed compensation parameters, the first maximum deceleration corresponding to the emergency stop zone, the second maximum deceleration corresponding to the soft stop zone, and the deceleration distance corresponding to the deceleration zone. The second maximum deceleration is less than the first maximum deceleration. For example, the first maximum deceleration could be 2 m / s², and the second maximum deceleration could be 3.5 m / s². The speed compensation parameters can be determined comprehensively based on factors such as the actual vehicle model, communication latency, and the actual ground friction coefficient; different vehicle models may have different speed compensation parameters. For example, the speed compensation parameter could be 0.2 seconds.

[0027] The safety distance has a pre-established mapping relationship with each segment of the global path of the autonomous mobile device. Different segments correspond to different safety distances. Each segment of the global path is pre-configured with safety distances in four directions: front, back, left, and right. These safety distances form the safety zone, which will be discussed later. The safety distance in the front-back direction can be set to be greater than the safety distance in the left-right direction. The safety distances in the front-back direction can be the same or different; for example, the safety distance in front can be set to be greater than the safety distance behind. The safety distances in the left-right direction can also be the same or different.

[0028] In some implementations, to improve collision detection accuracy, safety distances in the four directions (front, back, left, and right) can be set for each segment of the splicing path based on the actual road conditions. This ensures that the autonomous mobile device can perform collision detection based on the actual road conditions when moving to different splicing paths, thereby ensuring that the autonomous mobile device can cope with different actual road conditions and improving the autonomy of the autonomous mobile device in various scenarios.

[0029] In some examples, such as Figure 2 As shown, if the width of the drivable area C1C2C3C4 corresponding to the current stitching path is much larger than the short side A1A2 or A4A3 of the rectangle A1A2A3A4 representing the autonomous mobile device, for example, if the width of the drivable area is greater than or equal to twice the short side of the rectangle representing the autonomous mobile device, then it can be determined that the actual road conditions corresponding to the current stitching path are wide. In this case, a larger safety distance can be configured for the current stitching path, such as... Figure 2 As shown, the safe distances for the autonomous mobile device on the left and right sides of the current stitching path can be configured as L1, L2, L3, and L4, respectively. The safe area formed by these four safe distances L1-L4 is then defined as follows: Figure 2 The gray area in the diagram refers to the area between rectangles A1A2A3A4 and B1B2B3B4.

[0030] In other examples, such as Figure 3 As shown, if the width of the drivable area C1C2C3C4 corresponding to the current stitching path is slightly larger than the short side A1A2 or A4A3 of the rectangle A1A2A3A4 representing the autonomous mobile device, for example, if the width of the drivable area is greater than or equal to the short side of the rectangle representing the autonomous mobile device but less than twice the short side of the rectangle representing the autonomous mobile device, then it can be determined that the actual road conditions corresponding to the current stitching path are narrow. In this case, a smaller safety distance can be configured for the current stitching path, such as... Figure 3 As shown, the safe distances for the autonomous mobile device on the left and right sides of the current stitching path can be configured as L1, L2, L3, and L4, respectively. The safe area formed by these four safe distances L1-L4 is then defined as follows: Figure 3 The gray area in the diagram refers to the area between rectangles A1A2A3A4 and B1B2B3B4.

[0031] In some other examples, such as Figure 4As shown, if the width C1C2 or C4C3 of the drivable area C1C2C3C4 corresponding to the current stitching path of the autonomous mobile device is almost the same as the short side A1A2 or A4A3 of the rectangle A1A2A3A4 representing the autonomous mobile device, for example, if the width of the drivable area is equal to or approximately equal to the short side of the rectangle representing the autonomous mobile device, then the actual scene road condition corresponding to the current stitching path can be determined as a special road condition. Special road conditions may include situations where the autonomous mobile device needs to travel close to obstacles (such as walls) to pass through the actual scene corresponding to the current stitching path. Considering that there may be errors in the detection of obstacles by sensing devices (such as cameras and laser sensors), in this example of a special road condition scenario, the left and right safety distances corresponding to the current stitching path can be set to negative numbers, such as... Figure 4 As shown, the safety distance to the left of the current stitching path can be set to -L1, the safety distance to the right to -L2, the safety distance in front to L3, and the safety distance behind to L4. This ensures that the robot can continue to execute subsequent collision detection methods in this special road condition scenario. The safe area formed by the four safety distances L1-L4 is [missing information]. Figure 4 The gray area shown is the area between rectangles A1A2A3A4 and B1B2B3B4.

[0032] To facilitate understanding of the application scenarios of negative safety distances, an example is provided here for illustration, specifically for scenarios where autonomous mobile devices need to travel close to obstacles (such as...). Figure 4 As shown in the diagram, the actual distance between the obstacle and the autonomous mobile device is Lr, but the sensor may detect a distance of Ld (Ld is less than or equal to Lr). If the left and right safety distances of the autonomous mobile device are set to zero or greater than zero, the subsequent collision detection method will misjudge that there is a collision risk between the autonomous mobile device and the obstacle in a scenario where the autonomous mobile device needs to travel close to it. This will cause the autonomous mobile device to brake. However, in reality, the autonomous mobile device can travel close to the obstacle in such scenarios. Therefore, the left and right safety distances corresponding to the current stitching path in such scenarios can be set to negative numbers, such as... Figure 4 As shown, this avoids the problem of the autonomous mobile device stopping in a scenario where it can move due to sensor errors, and ensures that the autonomous mobile device can move normally even in special scenarios such as when it needs to move close to obstacles.

[0033] During the movement of the autonomous mobile device, the safe distance corresponding to the current stitching path can be obtained according to the pre-established mapping relationship between the stitching path and the safe distance. The safe distance corresponding to the current stitching path is pre-determined based on the actual scenario corresponding to the current stitching path.

[0034] Step S120: Based on the contour points of the autonomous mobile device in the vehicle coordinate system, calculate the new contour points of the autonomous mobile device in the motion coordinate system. The new contour points of the autonomous mobile device form the new contour of the autonomous mobile device.

[0035] It can obtain the current direction of motion of the autonomous mobile device (direction of motion at the current speed); determine the angle between the current direction of motion and the front of the autonomous mobile device; and calculate the new contour points of the autonomous mobile device in the motion coordinate system based on this angle and the contour points of the autonomous mobile device in the vehicle coordinate system. The front of the autonomous mobile device can be represented by the angle between the direction the vehicle's front is facing and the x-axis of the vehicle coordinate system. For an example, please refer to [link to example]. Figure 5 , Figure 5 In the diagram, O represents the rear axle center of the autonomous mobile device. Rectangles A1A2A3A4 represent the autonomous mobile device, with a solid white arrow indicating the front of the device. The coordinate system X1-O-Y1 represents the vehicle coordinate system. Rectangle D1D2D3D4 is the rectangle formed by the new contour points, with a solid black arrow indicating the current direction of movement of the autonomous mobile device. The coordinate system X2-O-Y2 represents the motion coordinate system. The angle between the current direction of movement and the front of the autonomous mobile device is α, which is also the current angle between the motion coordinate system and the vehicle coordinate system. (x, y) represents the coordinates of the contour vertices of the autonomous mobile device in the vehicle coordinate system, and (X, Y) represents the coordinates of the contour vertices of the autonomous mobile device in the motion coordinate system. The method for calculating the new contour points of the autonomous mobile device can be expressed as follows:

[0036] X = xcos(a) - ysin(a)

[0037] Y = xsin(a) + ycos(a)

[0038] like Figure 5 As shown, the coordinates of the contour points A1, A2, A3, and A4 of the autonomous mobile device in the vehicle coordinate system, after coordinate transformation according to the above expression, can be obtained as follows: Figure 5 The coordinates of the new contour points D1, D2, D3, and D4 are shown.

[0039] By performing coordinate system transformation, the collision detection method provided in this application embodiment is compatible with motion models such as the Ackerman model, differential model, and omnidirectional model, thereby improving the versatility of the collision detection method provided in this application embodiment. It should be noted that when the autonomous mobile device adopts a differential vehicle model, the angle between the vehicle coordinate system and the motion coordinate system is 0 degrees.

[0040] The autonomous mobile device is equipped with multiple sensors, including laser sensors, cameras, point laser sensors, and ultrasonic sensors. During the movement of the autonomous mobile device, multiple sensors can be used to fuse perception of obstacles around the autonomous mobile device within the obstacle detection area, acquiring all contour points of the obstacles in the vehicle coordinate system. Based on all contour points of the obstacles in the vehicle coordinate system, all new contour points of the obstacles in the motion coordinate system are calculated. The new contour of the obstacle is formed by all these new contour points and is used for subsequent collision detection. The obstacle detection area can be pre-set based on a comprehensive consideration of multiple factors such as the actual sensor detection range, safety distance, and computational data volume. For example, the obstacle detection area can be a region formed by expanding forward and backward by 4 meters and left and right by 2 meters, centered on a rectangle representing the autonomous mobile device. The obstacle detection area is larger than the emergency stop area, soft stop area, and deceleration area mentioned later. During subsequent obstacle perception, only obstacles within the obstacle detection area can be detected, thereby ensuring the safety of the autonomous mobile device while reducing the computational load. The method for calculating all new contour points of obstacles is the same as the method for calculating new contour points of autonomous mobile devices. Please refer to the relevant content above, and it will not be repeated here.

[0041] Step S130: Based on the new outline of the autonomous mobile device, the current speed, and preset parameters, construct the emergency stop area, soft stop area, and deceleration area in sequence.

[0042] In this embodiment, the emergency stop area can be constructed as follows: the first stopping distance corresponding to the emergency stop area is calculated based on the safety distance, the first maximum deceleration, the speed compensation parameter, and the current speed; the emergency stop area is constructed based on the new outline of the autonomous mobile device and the first stopping distance.

[0043] Specifically, based on the safety distances in the four directions (front, back, left, and right) corresponding to the current splicing path, the first maximum deceleration, the speed compensation parameter, and the current speed, the first stopping distances of the new contour in the four directions (front, back, left, and right) can be calculated respectively, resulting in four first stopping distances, with one first stopping distance corresponding to each direction.

[0044] For example, the first parking distance in the four directions (front, back, left, and right) of the new contour can be calculated using the following expressions:

[0045] d1 = v*v / 2 / a1 + s1 + offset*v

[0046] d2 = v*v / 2 / a1 + s2 + offset*v

[0047] d3 = v*v / 2 / a1 + s3 + offset*v

[0048] d4=v*v / 2 / a1+s4+offset*v

[0049] Where d1 represents the first stopping distance ahead; d2 represents the first stopping distance behind; d3 represents the first stopping distance to the left; d4 represents the first stopping distance behind; v represents the current speed; a1 represents the first maximum deceleration; s1 represents the safe distance ahead; s2 represents the safe distance behind; s3 represents the safe distance to the left; s4 represents the safe distance behind; offset represents the speed compensation parameter.

[0050] After obtaining the four initial parking distances, the first parking distance corresponding to the front can be expanded forward, the first parking distance corresponding to the rear can be expanded backward, the first parking distance corresponding to the left can be expanded to the left, and the first parking distance corresponding to the right can be expanded to the right, forming a first region. The emergency stop region is the area within the first region excluding the area occupied by the new contour and the aforementioned safety region. For an example, please refer to [link / reference]. Figure 6 The solid black arrow indicates the direction of movement of the autonomous mobile device. Rectangle D1D2D3D4 represents the new outline. Rectangle E1E2E3E4 represents the safe area. Rectangle F1F2F3F4 is the first area. The diagonal line filling area between rectangles E1E2E3E4 and F1F2F3F4 is the emergency stop area.

[0051] In this embodiment, the soft stop area can be constructed as follows: the second stopping distance corresponding to the emergency stop area is calculated based on the safety distance, the second maximum deceleration, the speed compensation parameter, and the current speed; the emergency stop area is constructed based on the new outline of the autonomous mobile device and the second stopping distance.

[0052] Specifically, based on the safety distances in the four directions (front, back, left, and right) corresponding to the current stitching path, the second maximum deceleration, the speed compensation parameter, and the current speed, the second stopping distances of the new contour in each of the four directions are calculated, resulting in four second stopping distances, one for each direction. The second stopping distances in each of the four directions are each less than the corresponding first stopping distance in each of the four directions.

[0053] For example, the second parking distance in the four directions (front, back, left, and right) of the new contour can be calculated using the following expressions:

[0054] d5 = v*v / 2 / a2 + s1 + offset*v

[0055] d6=v*v / 2 / a2+s2+offset*v

[0056] d7=v*v / 2 / a2+s3+offset*v

[0057] d8 = v*v / 2 / a2 + s4 + offset*v

[0058] Where d5 represents the second stopping distance ahead; d6 represents the second stopping distance behind; d7 represents the second stopping distance to the left; d8 represents the second stopping distance behind; v represents the current speed; a2 represents the second maximum deceleration; s1 represents the safe distance ahead; s2 represents the safe distance behind; s3 represents the safe distance to the left; s4 represents the safe distance behind; offset represents the speed compensation parameter.

[0059] After obtaining the four first parking distances, the second parking distance corresponding to the new contour can be expanded forward, backward, to the left, and to the right, centered on the new contour, forming a second region. The soft parking region is the area within the second region excluding the area occupied by the new contour, the aforementioned safety region, and the aforementioned emergency parking region (i.e., the area within the second region excluding the aforementioned first region is the soft parking region). For an example, please refer to [link to example]. Figure 6 The solid black arrow indicates the direction of movement of the autonomous mobile device. Rectangle F1F2F3F4 is the first region, and rectangle G1G2G3G4 is the second region. The horizontal line filling area between rectangle G1G2G3G4 and rectangle F1F2F3F4 is the soft stop area.

[0060] It should be noted that, since the emergency stop area and soft stop area in the embodiments of this application are related to the current speed of the autonomous mobile device, the emergency stop area and soft stop area are different for different current speeds. Taking the first stopping distance and the second stopping distance in front as examples, the first stopping distance corresponding to different current speeds is shown in Table 1, and the second stopping distance corresponding to different current speeds is shown in Table 2.

[0061] Table 1

[0062]

[0063] Table 2

[0064]

[0065] In Tables 1 and 2, m / s is in meters per second, m is in meters, and s is in seconds. The offset in Tables 1 and 2 is 4 seconds. a1 is 2 m / s², and a2 is 3.5 m / s². As shown in Table 1, the first stopping distance ahead is the sum of the braking distance for an emergency stop, the speed compensation distance, and the corresponding safe distance ahead. As shown in Table 2, the second stopping distance ahead is the sum of the braking distance for a soft stop, the speed compensation distance, and the corresponding safe distance ahead.

[0066] By adjusting the sizes of the emergency stop zone and the soft stop zone in real time based on the current speed, the computational load can be adjusted while ensuring the movement safety of the autonomous mobile device, thus making rational use of its resources. Furthermore, by setting up a soft stop zone and triggering a stop using the second maximum deceleration of that zone when an obstacle is detected, the vehicle can be stopped as smoothly as possible while ensuring its movement safety, preventing objects loaded on the autonomous mobile device (such as goods or pallets used for loading goods) from slipping off due to emergency stops.

[0067] In this embodiment, the deceleration region can be constructed as follows: Based on the new contour of the autonomous mobile device and the deceleration distance, the deceleration region is constructed. The deceleration region includes deceleration distances in four directions: front, back, left, and right. Similar to the safety distance, the deceleration distance for each direction is set according to the actual scenario corresponding to the current stitching path, which can handle various real-world scenarios and improve the versatility and flexibility of the collision detection method.

[0068] In some implementations, the deceleration distances in the four directions (front, back, left, and right) are each greater than the corresponding first stopping distance in each of the four directions. A third region can be formed by expanding the deceleration distance corresponding to the front direction forward, the rear direction backward, the left direction left, and the right direction right, centered on the new contour. The area within this third region, excluding the second region (i.e., the area occupied by the new contour, the safety zone, the emergency stop zone, and the soft stop zone), is the deceleration zone. For an example, please refer to [link to example]. Figure 6 The solid black arrows indicate the direction of movement of the autonomous mobile device. Rectangles H1H2H3H4 are the third region, and rectangles G1G2G3G4 are the second region. The vertical line filling area between rectangles H1H2H3H4 and H1H2H3H4 is the deceleration region.

[0069] In other implementations, after the soft stop region, the deceleration zone can be expanded forward, backward, left, and right, centered on the soft stop region, by the corresponding deceleration distance. In this case, the expansion of the area centered on the soft stop region in all directions forms the deceleration zone. Figure 6 The vertical line filling area between rectangles H1H2H3H4 and H1H2H3H4 is the deceleration area.

[0070] In some implementations, to simplify calculations, the emergency stop region, soft stop region, and deceleration region can be constructed only in the direction of motion; please refer to [link to relevant documentation]. Figure 7 The movement direction can be close to the new contour D1D2D3D4 (e.g.) Figure 7 Using the direction indicated by the solid black arrow (D1D2) as the starting point for expansion, and using the width of the safety area E1E2E3E4 as the expansion width, the expansion extends forward to the current direction of movement of the new contour (i.e., in front of the new contour) by the corresponding first stopping distance, forming the first region F1F2F3F4. The diagonally filled area E1E2E3E4 within the first region F1F2F3F4, excluding the safety area, is the emergency stopping area. The direction of movement of the new contour D1D2D3D4 towards the new contour (e.g., in front of the new contour) can be used as the starting point for expansion. Figure 7 Using the direction indicated by the solid black arrow (D1D2) as the expansion starting point, and the width of the safety area E1E2E3E4 as the expansion width, the second stopping distance corresponding to the current movement direction of the new contour is expanded forward, forming the second region G1G2F3F4. The horizontal line-filled area G1G2F2F1 within the second region G1G2F3F4, excluding the first region F1F2F3F4, is the soft-stop region. In some embodiments, the corresponding deceleration distance is greater than the corresponding first stopping distance, and the movement direction of the new contour D1D2D3D4 towards the new contour (e.g., the direction of movement of the new contour D1D2D3D4 towards the new contour) can be used as the expansion starting point. Figure 7 Using the direction indicated by the solid black arrow as the starting point of expansion (D1D2), and taking the width of the safe area E1E2E3E4 as the expansion width, the expansion extends forward to the current direction of movement of the new contour, corresponding to the deceleration distance, forming the third region H1H2F3F4. The horizontal line filling area H1H2G2G1 in the third region H1H2F3F4, excluding the second region G1G2F3F4, is the deceleration area.

[0071] It should be noted that although the above implementation method describes a deceleration region, in actual applications, multiple deceleration regions can be set according to actual needs. The construction method of each deceleration region is similar, and you can refer to the deceleration region construction section above, which will not be repeated here.

[0072] Step S140: Collision detection is performed based on the emergency stop area, soft stop area, and deceleration area.

[0073] In this embodiment, the safety protection strategy for the emergency stop zone may include: performing a stop operation according to a first maximum deceleration. The safety protection strategy for the soft stop zone may include: performing a stop operation according to a second maximum deceleration. The safety protection strategy for the deceleration zone may include: performing a deceleration operation according to the speed limit corresponding to the deceleration zone, wherein the speed limit may include, but is not limited to, a maximum speed limit and a maximum acceleration limit.

[0074] In some implementations, if an obstacle (new outline) is detected in the emergency stop zone, the safety protection strategy corresponding to the emergency stop zone is triggered; if an obstacle (new outline) is detected in the soft stop zone, the safety protection strategy corresponding to the soft stop zone is triggered; if an obstacle (new outline) is detected in the deceleration zone, the safety protection strategy corresponding to the deceleration zone is triggered.

[0075] In some implementations, the response levels of the emergency stop zone, soft stop zone, and deceleration zone can be set to decrease sequentially. If a new outline of the obstacle is detected in at least two of the emergency stop zone, soft stop zone, and deceleration zone, the safety protection strategy corresponding to the zone with the highest response level in at least two of the at least two zones is triggered, thereby dealing with the situation where an obstacle is detected in at least two zones simultaneously.

[0076] The collision detection method provided in this application converts the contour points of an autonomous mobile device in the vehicle coordinate system into new contour points in the motion coordinate system. Based on the new contour points formed by the autonomous mobile device, the current speed, and preset parameters, an emergency stop region, a soft stop region, and a deceleration region are constructed in real time. Collision detection is performed based on these constructed regions, enabling rapid and accurate detection of suddenly appearing obstacles and facilitating a quick response to ensure the mobile safety of the autonomous mobile device. Compared to current map-based collision detection methods, the collision detection method in this application has a lower dependence on the positioning module and is not affected by map resolution, resulting in higher collision detection accuracy. Compared to current collision detection methods based on radar-integrated PLCs, the collision detection method in this application has simpler computational logic, can handle various application scenarios, and has high versatility.

[0077] Please see Figure 8 , Figure 8This diagram illustrates a flowchart of a collision detection method provided in an exemplary embodiment of this application. An autonomous mobile device is equipped with a laser sensor, a camera, an ultrasonic sensor, and a point laser sensor. The laser sensor transmits acquired laser data to the autonomous mobile device. The camera transmits acquired camera data to the autonomous mobile device. The ultrasonic sensor transmits acquired ultrasonic data to the autonomous mobile device. The point laser sensor transmits acquired point laser data to the autonomous mobile device in real time. The autonomous mobile device, through an obstacle perception module, acquires all contour points of obstacles based on the laser data, camera data, ultrasonic data, and point laser data, and performs collision detection based on all contour points of the obstacles. If an obstacle is detected in an emergency stop zone, the autonomous mobile device adopts an emergency stop strategy, immediately decelerating using a first maximum deceleration; if an obstacle is detected in a soft stop zone, the autonomous mobile device adopts a soft stop strategy, immediately decelerating using a second maximum deceleration; if an obstacle is detected in a deceleration zone, the autonomous mobile device adopts a deceleration strategy, decelerating using the speed limit corresponding to the deceleration zone.

[0078] Please see Figure 9 , Figure 9 A schematic diagram of the collision detection device provided in this application embodiment is shown. This collision detection device 100 can be applied to autonomous mobile devices, such as AGVs or AMRs. The collision detection device 100 may include a contour point acquisition module 110, a coordinate calculation module 120, a region construction module 130, and a collision detection module 140. The contour point acquisition module 110 is used to acquire the contour points of the autonomous mobile device in the vehicle coordinate system. The coordinate calculation module 120 is used to calculate new contour points of the autonomous mobile device in the motion coordinate system based on the contour points in the vehicle coordinate system, and the new contour points of the autonomous mobile device form a new contour of the autonomous mobile device. The region construction module 130 is used to sequentially construct an emergency stop region, a soft stop region, and a deceleration region based on the new contour of the autonomous mobile device. The collision detection module 140 is used to perform collision detection based on the emergency stop region, the soft stop region, and the deceleration region.

[0079] In some embodiments, the coordinate calculation module 120 is also used to obtain the current direction of motion of the autonomous mobile device; determine the angle between the current direction of motion and the front of the autonomous mobile device; and calculate the new contour point of the autonomous mobile device in the motion coordinate system based on the angle and the contour point of the autonomous mobile device in the vehicle coordinate system.

[0080] In some embodiments, the region construction module 130 is further configured to calculate a first stopping distance corresponding to the emergency stop region based on the safety distance, the first maximum deceleration, the speed compensation parameter, and the current speed; and construct the emergency stop region based on the new profile of the autonomous mobile device and the first stopping distance.

[0081] In some embodiments, the region construction module 130 is further configured to calculate a second stopping distance corresponding to the emergency stop region based on the safety distance, the second maximum deceleration, the speed compensation parameter, and the current speed; and to construct the emergency stop region based on the new profile of the autonomous mobile device and the second stopping distance.

[0082] In some embodiments, the region construction module 130 is further configured to obtain the safe distance corresponding to the stitching path where the autonomous mobile device is currently located, based on a pre-established mapping relationship between stitching paths and safe distances. The stitching path comes from the global path of the autonomous mobile device, and different stitching paths correspond to different safe distances.

[0083] In some embodiments, the region construction module 130 is also configured to construct a deceleration region based on the new profile of the autonomous mobile device and the deceleration distance.

[0084] In some embodiments, the collision detection module 140 is further configured to trigger a safety protection strategy corresponding to the emergency stop region if an obstacle is detected in the emergency stop region; trigger a safety protection strategy corresponding to the soft stop region if the obstacle is detected in the soft stop region; and trigger a safety protection strategy corresponding to the deceleration region if the obstacle is detected in the deceleration region.

[0085] In some embodiments, the collision detection module 140 is further configured to trigger a safety protection strategy corresponding to the region with the highest response level among the at least two regions if the obstacle is detected in at least two regions of the emergency stop region, the soft stop region, and the deceleration region.

[0086] In some embodiments, the contour point acquisition module 110 is further configured to acquire the contour points of the obstacle in the vehicle coordinate system; calculate the new contour points of the obstacle in the motion coordinate system based on the contour points of the obstacle in the vehicle coordinate system, and form the new contour of the obstacle with the new contour points of the obstacle, which is used for collision detection.

[0087] In some embodiments, the contour point acquisition module 110 is also used to use multiple sensors to fuse and perceive the obstacles around the autonomous mobile device to obtain the contour points of the obstacles in the vehicle coordinate system.

[0088] Those skilled in the art will clearly understand that the collision detection device provided in the embodiments of this application can implement the collision detection method provided in the embodiments of this application. The specific working process of the described device and modules can be found in the corresponding process of the method in the embodiments of this application, and will not be repeated here.

[0089] In the embodiments provided in this application, the coupling, direct coupling, or communication connection between the modules shown or discussed may be indirect coupling or communication coupling through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms. The embodiments of this application do not impose specific limitations on this.

[0090] Furthermore, the functional modules in the embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0091] Please see Figure 10 , Figure 10 A schematic diagram of the structure of the autonomous mobile device provided in an embodiment of this application is shown. The autonomous mobile device 200 can be a device with autonomous mobility capabilities, and the autonomous mobile device 200 can include, but is not limited to, AGV or AMR. The autonomous mobile device 200 can include a memory 210 and a processor 220. The memory 210 stores an application program, which is configured to execute the method provided in the embodiment of this application when invoked by the processor 220.

[0092] Processor 220 may include one or more processing cores. Processor 220 uses various interfaces and lines to connect to various parts within the autonomous mobile device 200, and is used to run or execute instructions, programs, code sets or instruction sets stored in memory 210, as well as to call and run or execute data stored in memory 210, and perform various functions and process data of autonomous mobile device 200.

[0093] The processor 220 can be implemented using at least one of the following hardware forms: Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 220 can integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem can also be implemented separately as a communication chip, without being integrated into the processor 220.

[0094] The memory 210 may include random access memory (RAM) or read-only memory (ROM). The memory 210 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 210 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc. The data storage area may store data created by the autonomous mobile device 200 during use.

[0095] This application also provides a computer-readable storage medium storing program code that is configured to execute the method provided in this application when invoked by a processor.

[0096] Computer-readable storage media can be electronic storage devices such as flash memory, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), hard disk, or ROM.

[0097] In some embodiments, the computer-readable storage medium includes a non-volatile computer-readable storage medium (Non-TCRSM). The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code may be compressed in an appropriate form.

[0098] 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 collision detection method, characterized in that, include: Obtain the contour points, current speed, and preset parameters of the autonomous mobile device in the vehicle coordinate system; Based on the contour points of the autonomous mobile device in the vehicle coordinate system, calculate the new contour points of the autonomous mobile device in the motion coordinate system, and the new contour points of the autonomous mobile device form the new contour of the autonomous mobile device. Based on the new outline of the autonomous mobile device, the current speed, and the preset parameters, an emergency stop region, a soft stop region, and a deceleration region are constructed sequentially. Collision detection is performed based on the emergency stop area, the soft stop area, and the deceleration area; The preset parameters include a pre-set safety distance, a first maximum deceleration, and speed compensation parameters; the emergency stop zone is constructed based on the new profile of the autonomous mobile device, the current speed, and the preset parameters, including: Obtain the safe distances in the four directions (front, back, left, and right) corresponding to the stitching path where the autonomous mobile device is currently located. The stitching path comes from the global path of the autonomous mobile device, and different stitching paths correspond to different safe distances. Determine the emergency braking distance based on the first maximum deceleration and the current speed; Determine the emergency stop speed compensation distance based on the speed compensation parameters and the current speed; The sum of the emergency braking distance, the emergency speed compensation distance, and the safety distances in the four directions (front, back, left, and right) is calculated and used as the first stopping distance in the four directions. The new contour is expanded by a safe distance in the front-back, left-right and right directions, and the resulting expanded area is the safe area. The first parking distance is expanded in the front-back, left-right and right directions of the new contour to obtain the first region; The area in the first region other than the area occupied by the safety area and the new contour is defined as the emergency stop area.

2. The method according to claim 1, characterized in that, The step of calculating the new contour points of the autonomous mobile device in the motion coordinate system based on the contour points of the autonomous mobile device in the vehicle coordinate system includes: Obtain the current direction of motion of the autonomous mobile device; Determine the angle between the current direction of motion and the front of the autonomous moving device; Based on the included angle and the contour points of the autonomous mobile device in the vehicle coordinate system, calculate the new contour points of the autonomous mobile device in the motion coordinate system.

3. The method according to claim 1, characterized in that, The preset parameters also include a second maximum deceleration, which is less than the first maximum deceleration. The step of constructing a soft-stop region based on the new profile of the autonomous mobile device, the current speed, the travel distance, and the preset parameters includes: The soft stop braking distance is determined based on the second maximum deceleration and the current speed; Determine the soft stop speed compensation distance based on the speed compensation parameters and the current speed; The soft stop braking distance, the soft stop speed compensation distance, and the safety distances in the four directions (front, back, left, and right) are calculated separately and used as the second stopping distance in the four directions. The second parking distance is expanded in the front-back, left-right and right directions of the new contour to obtain the second region; The area in the second region other than the first region is defined as the soft stop region.

4. The method according to claim 1, characterized in that, The step of obtaining the safe distances in the four directions (front, back, left, and right) corresponding to the current splicing path of the autonomous mobile device includes: Based on the pre-established mapping relationship between splicing paths and safe distances, the safe distances in the four directions (front, back, left, and right) corresponding to the splicing path where the autonomous mobile device is currently located are obtained.

5. The method according to claim 4, characterized in that, Before obtaining the safe distances in the four directions (front, back, left, and right) corresponding to the current stitching path of the autonomous mobile device based on the pre-established mapping relationship between the stitching path and the safe distance, the method further includes: If the width of the drivable area corresponding to the splicing path is greater than or equal to twice the short side of the rectangle representing the autonomous mobile device, then the actual road conditions corresponding to the splicing path are determined to be wide, and the safe distance corresponding to the wide road conditions is determined as the safe distance of the splicing path. If the width of the drivable area corresponding to the splicing path is greater than or equal to the short side of the rectangle representing the autonomous mobile device and the width is less than twice the short side, then the actual road conditions corresponding to the splicing path are determined to be narrow, and the safe distance corresponding to the narrow road conditions is determined as the safe distance of the splicing path. If the width of the drivable area corresponding to the splicing path is equal to the short side of the rectangle representing the autonomous mobile device, then the actual road conditions corresponding to the splicing path are determined to be special. The safety distance corresponding to the special road conditions is determined as the safety distance of the splicing path, wherein the safety distance in the left and right directions of the safety distance corresponding to the special road conditions is a negative number.

6. The method according to claim 1, characterized in that, The preset parameters also include a pre-set deceleration distance. The step of constructing the deceleration region based on the new profile of the autonomous mobile device, the current speed, the travel distance, and the preset parameters includes: Based on the new profile of the autonomous mobile device and the deceleration distance, a deceleration region is constructed.

7. The method according to claim 1, characterized in that, The step of performing collision detection based on the emergency stop area, the soft stop area, and the deceleration area includes: If an obstacle is detected in the emergency stop area, the safety protection strategy corresponding to the emergency stop area is triggered. If the obstacle is detected in the soft stop area, the safety protection strategy corresponding to the soft stop area is triggered. If the obstacle is detected in the deceleration zone, the safety protection strategy corresponding to the deceleration zone is triggered.

8. The method according to claim 1 or 7, characterized in that, The response levels of the emergency stop region, the soft stop region, and the deceleration region decrease sequentially. The step of performing collision detection based on the emergency stop region, the soft stop region, and the deceleration region further includes: If an obstacle is detected in at least two of the emergency stop zone, the soft stop zone, and the deceleration zone, the safety protection strategy corresponding to the zone with the highest response level among the at least two zones is triggered.

9. The method according to claim 1, characterized in that, The outline points of the autonomous mobile device include the four vertices of a rectangle representing the autonomous mobile device, the length of which is greater than or equal to the maximum length of the autonomous mobile device, and the width of which is greater than or equal to the maximum width of the autonomous mobile device.

10. The method according to claim 1, characterized in that, Before the step of performing collision detection based on the emergency stop region, the soft stop region, and the deceleration region, the method further includes: Obtain the contour points of the obstacle in the vehicle coordinate system; Based on the outline points of the obstacle in the vehicle coordinate system, a new outline point of the obstacle in the motion coordinate system is calculated. The new outline point of the obstacle forms a new outline of the obstacle, which is used for collision detection.

11. The method according to claim 10, characterized in that, The step of obtaining the contour points of the obstacle in the vehicle coordinate system includes: The obstacles around the autonomous mobile device are perceived by multiple sensors to obtain the contour points of the obstacles in the vehicle coordinate system.

12. A collision detection device, characterized in that, include: The contour point acquisition module is used to acquire the contour points, current speed, and preset parameters of the autonomous mobile device in the vehicle coordinate system; The coordinate calculation module is used to calculate the new contour points of the autonomous mobile device in the motion coordinate system based on the contour points of the autonomous mobile device in the vehicle coordinate system, and the new contour points of the autonomous mobile device form the new contour of the autonomous mobile device. The region construction module is used to sequentially construct an emergency stop region, a soft stop region, and a deceleration region based on the new outline of the autonomous mobile device, the current speed, and the preset parameters. The collision detection module is used to perform collision detection based on the emergency stop area, the soft stop area, and the deceleration area. The preset parameters include a pre-set safety distance, a first maximum deceleration, and speed compensation parameters; the emergency stop zone is constructed based on the new profile of the autonomous mobile device, the current speed, and the preset parameters, including: Obtain the safe distances in the four directions (front, back, left, and right) corresponding to the stitching path where the autonomous mobile device is currently located. The stitching path comes from the global path of the autonomous mobile device, and different stitching paths correspond to different safe distances. Determine the emergency braking distance based on the first maximum deceleration and the current speed; Determine the emergency stop speed compensation distance based on the speed compensation parameters and the current speed; The sum of the emergency braking distance, the emergency speed compensation distance, and the safety distances in the four directions (front, back, left, and right) is calculated and used as the first stopping distance in the four directions. The new contour is expanded by a safe distance in the front-back, left-right and right directions, and the resulting expanded area is the safe area. The first parking distance is expanded in the front-back, left-right and right directions of the new contour to obtain the first region; The area in the first region other than the area occupied by the safety area and the new contour is defined as the emergency stop area.

13. An autonomous mobile device, characterized in that, include: A memory and a processor, wherein an application is stored in the memory, the application being configured to perform the method as described in any one of claims 1-11 when invoked by the processor.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that is configured to execute the method as described in any one of claims 1-11 when invoked by a processor.

Images