WO2023225812A1 - 移动设备及其速度控制方法、装置、存储介质 - Google Patents

移动设备及其速度控制方法、装置、存储介质 Download PDF

Info

Publication number
WO2023225812A1
WO2023225812A1 PCT/CN2022/094525 CN2022094525W WO2023225812A1 WO 2023225812 A1 WO2023225812 A1 WO 2023225812A1 CN 2022094525 W CN2022094525 W CN 2022094525W WO 2023225812 A1 WO2023225812 A1 WO 2023225812A1
Authority
WO
WIPO (PCT)
Prior art keywords
mobile device
speed
target
distance
line segment
Prior art date
Application number
PCT/CN2022/094525
Other languages
English (en)
French (fr)
Inventor
李东方
Original Assignee
北京小米机器人技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米机器人技术有限公司 filed Critical 北京小米机器人技术有限公司
Priority to PCT/CN2022/094525 priority Critical patent/WO2023225812A1/zh
Priority to CN202280004174.8A priority patent/CN117480463A/zh
Priority to EP22938741.0A priority patent/EP4318162A4/en
Publication of WO2023225812A1 publication Critical patent/WO2023225812A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60Intended control result
    • G05D1/644Optimisation of travel parameters, e.g. of energy consumption, journey time or distance
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20Control system inputs
    • G05D1/24Arrangements for determining position or orientation
    • G05D1/243Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20Control system inputs
    • G05D1/24Arrangements for determining position or orientation
    • G05D1/246Arrangements for determining position or orientation using environment maps, e.g. simultaneous localisation and mapping [SLAM]
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60Intended control result
    • G05D1/617Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
    • G05D1/622Obstacle avoidance
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60Intended control result
    • G05D1/65Following a desired speed profile
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2107/00Specific environments of the controlled vehicles
    • G05D2107/70Industrial sites, e.g. warehouses or factories
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00Types of controlled vehicles
    • G05D2109/10Land vehicles
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2111/00Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
    • G05D2111/10Optical signals

Definitions

  • the present disclosure relates to the field of intelligent robot technology, and specifically to a mobile device and its speed control method, device, and storage medium.
  • autonomous mobile devices are widely used in various industrial and daily life scenarios, such as logistics robots, food delivery robots, sweeping robots, etc.
  • the motion control planning of the mobile device directly determines the operating effect and safety level of the mobile device.
  • the movement speed control effect of the mobile device is poor, resulting in low safety and movement efficiency of the mobile device.
  • embodiments of the present disclosure provide a mobile equipment and its speed control method, device, and storage medium.
  • embodiments of the present disclosure provide a speed control method, applied to mobile devices, and the method includes:
  • the mobile device is controlled to move at the target speed.
  • the obtaining the cost map of the movement area and the target path of the mobile device moving in the movement area includes:
  • a cost map of the mobile area is obtained based on the obstacle information in the environment map, and the target path of the mobile device is determined based on the cost map and the current location.
  • determining the current target distance between the mobile device and the obstacle based on the cost map includes:
  • the target distance is obtained according to the first distance and the second distance.
  • determining the turning curvature of the mobile device when moving along the target path includes:
  • the cost map Based on the cost map, determine the first reference line segment and the second reference line segment within the preset range in front of the mobile device; wherein the first reference line segment and the second reference line segment are both perpendicular to the target path, And there is a preset distance between the first reference line segment and the second reference line segment;
  • the current turning angle of the mobile device is determined according to the angle between the first reference line segment and the second reference line segment.
  • determining the current turning angle of the mobile device based on the angle between the first reference line segment and the second reference line segment includes:
  • the intersection coordinates of the first reference line segment and the second reference line segment are determined based on the cost map, and based on the intersection coordinates and the predetermined Assume that the distance determines the angle between the first reference line segment and the second reference line segment, and the angle is determined as the bending degree;
  • the curvature is determined to be zero.
  • determining the target speed of the mobile device based on the target distance, the turning angle, and the maximum speed limit of the mobile device includes:
  • the turning speed component of the mobile device is determined according to the turning degree and the maximum speed limit; wherein the turning speed component is negatively related to the turning degree;
  • a weighted fusion process is performed on the straight speed component and the turning speed component to obtain the target speed of the mobile device.
  • the target distance includes a first distance perpendicular to the target path and a second distance parallel to the target path; and determining the straight speed component of the mobile device based on the target distance, include:
  • the straight ahead speed component is obtained based on the first speed component and the second speed component.
  • controlling the mobile device to move at the target speed includes:
  • the mobile device In response to the target speed satisfying the preset speed range, the mobile device is controlled to move at the target speed.
  • inventions of the present disclosure provide a speed control device, which is applied to mobile equipment.
  • the device includes:
  • An acquisition module configured to acquire a cost map of the movement area and a target path for the mobile device to move in the movement area
  • a first determination module configured to determine, based on the cost map, the current target distance between the mobile device and the obstacle, and the turning curvature of the mobile device when moving along the target path;
  • a second determination module configured to determine the target speed of the mobile device according to the target distance, the turning angle, and the maximum speed limit of the mobile device
  • a control module configured to control the mobile device to move at the target speed.
  • the acquisition module is configured to:
  • the first determining module is configured as:
  • the target distance is obtained according to the first distance and the second distance.
  • the first determining module is configured as:
  • the cost map Based on the cost map, determine the first reference line segment and the second reference line segment within the preset range in front of the mobile device; wherein the first reference line segment and the second reference line segment are both perpendicular to the target path, And there is a preset distance between the first reference line segment and the second reference line segment;
  • the current turning angle of the mobile device is determined according to the angle between the first reference line segment and the second reference line segment.
  • the first determining module is configured as:
  • the intersection coordinates of the first reference line segment and the second reference line segment are determined based on the cost map, and based on the intersection coordinates and the predetermined Assume that the distance determines the angle between the first reference line segment and the second reference line segment, and the angle is determined as the bending degree;
  • the curvature is determined to be zero.
  • the second determination module is configured as:
  • the turning speed component of the mobile device is determined according to the turning degree and the maximum speed limit; wherein the turning speed component is negatively related to the turning degree;
  • a weighted fusion process is performed on the straight speed component and the turning speed component to obtain the target speed of the mobile device.
  • the second determination module is configured as:
  • the straight ahead speed component is obtained based on the first speed component and the second speed component.
  • control module is configured to:
  • the mobile device In response to the target speed satisfying the preset speed range, the mobile device is controlled to move at the target speed.
  • an embodiment of the present disclosure provides a mobile device, including:
  • the memory stores computer instructions for causing the processor to execute the method according to any implementation manner of the first aspect.
  • an embodiment of the present disclosure provides a storage medium that stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any embodiment of the first aspect.
  • the speed control method in the disclosed embodiment includes obtaining a cost map of the moving area and a target path for the mobile device to move in the moving area, determining the target distance and turning angle between the mobile device and the obstacle based on the cost map, and determining the target distance and turning angle according to the target distance and turning angle. And the maximum speed limit determines the target speed and controls the mobile device to move at the target speed.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • the target distance between obstacles is also combined with the curvature of the target path of the mobile device itself to avoid overturning due to excessive turning speed, reduce the risk of accidents caused by blind spots in the corner, and further improve the speed control effect.
  • Figure 1 is a structural block diagram of a mobile device according to some embodiments of the present disclosure.
  • Figure 2 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 3 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 4 is a schematic diagram of a speed control method according to some embodiments of the present disclosure.
  • Figure 5 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 6 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 7 is a schematic diagram of a speed control method according to some embodiments of the present disclosure.
  • Figure 8 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 9 is a flowchart of a speed control method according to some embodiments of the present disclosure.
  • Figure 10 is a structural block diagram of a speed control device according to some embodiments of the present disclosure.
  • mobile devices such as sweeping robots, logistics robots, food delivery robots, and legged robots can move autonomously in preset operating spaces to meet corresponding operating requirements.
  • Speed control of mobile equipment is an important part of motion planning. If the mobile equipment moves too fast, the risk of accidents and losses caused by accidents increase; if the mobile equipment moves too slowly, its operating efficiency will also decrease.
  • the operating area of the mobile device can be pre-divided and speed-limited.
  • the entire moving area of the mobile device can be pre-divided into three partitions: A, B, and C.
  • Each partition is based on obstacle conditions, Different maximum speed limits are preset based on factors such as mobile device density, so that when a mobile device runs to a certain partition, it runs at the maximum speed limit specified in that partition.
  • the mobile device cannot adaptively adjust the movement speed according to changes in obstacles, and can only operate according to the speed limited by the partition.
  • obstacles or equipment density are reduced in a zone with a lower speed limit, mobile devices still operate at a lower speed limit, resulting in reduced operating efficiency of mobile devices.
  • obstacles or equipment density increase in a zone with a higher speed limit, mobile devices will still operate at a higher speed limit, resulting in a greatly increased risk of accidents such as collisions and scratches on mobile devices.
  • the mobile device can only control the moving speed in the set partitions, and cannot realize speed adaptive control in other moving areas, so the adaptability of the mobile device is very poor.
  • the embodiments of the present disclosure provide a mobile device and its speed control method, device, and storage medium, aiming to realize speed adaptive control of the mobile device, reduce the risk of accidents of the mobile device, and improve the mobility of the mobile device. Device security and mobile efficiency.
  • embodiments of the present disclosure provide a speed control method, which can be applied to mobile devices.
  • the mobile device in the embodiment of the present disclosure can be any type of device with autonomous movement capabilities that is suitable for implementation, such as a footed robot, a sweeping robot, a logistics robot, a food delivery robot, an intelligent mobile trash can, etc., and the present disclosure does not limit this. .
  • a mobile device 600 of an example of the present disclosure includes a processor 601 , a memory 602 , a scene awareness system 604 and a driving device 605 .
  • the processor 601, the memory 602, the scene sensing system 604 and the driving device 605 establish a communicable connection between any two of them through the bus 603.
  • the processor 601 can be any type of processor with one or more processing cores. It can perform single-threaded or multi-threaded operations and is used to parse instructions to perform operations such as obtaining data, performing logical operation functions, and issuing operation processing results.
  • Memory 602 may include non-volatile computer-readable storage media, such as at least one disk storage device, flash memory device, distributed storage device remotely located relative to processor 601, or other non-volatile solid-state storage device.
  • the memory may have a program storage area for storing non-volatile software programs, non-volatile computer executable programs and modules for the processor 601 to call to cause the processor 601 to perform one or more method steps.
  • the memory 602 may also include a storage part such as a volatile random access storage medium or a hard disk as a data storage area for storing operation processing results and data output by the processor 601.
  • the scene sensing system 604 is a sensor system used by mobile devices to obtain current scene data.
  • the scene sensing system 604 collects relevant data of the current scene, so that the mobile device can realize functions such as device positioning and map construction.
  • the scene awareness system 604 may be a SLAM (Simultaneous Localization and Mapping) system.
  • the SLAM system can include multiple sensors, such as monocular cameras, binocular cameras, lidar, IMU (Inertial Measurement Unit) sensors, ToF (Time of flight, time of flight) sensors, etc. These sensors collect data during the movement of the mobile device in real time, and use the SLAM algorithm to achieve positioning and mapping of the device based on the collected data.
  • the cost map during the movement of the mobile device can be established through the data collected by the scene sensing system 604, so as to realize the path planning and speed control of the mobile device.
  • the methods of this disclosure will be specifically described below and will not be described in detail here.
  • the driving device 605 is the power system of the mobile device and is used to drive the mobile device 600 to generate displacement.
  • the driving device 605 may include mechanical structures such as motors, transmission mechanisms, and rollers. Those skilled in the art will undoubtedly understand and fully implement this, and will not be described in detail in this disclosure. Of course, those skilled in the art can understand that the mobile device 600 may also include various other electrical components and mechanical components, which will not be described in detail in the embodiments of this disclosure.
  • embodiments of the present disclosure provide a speed control method for real-time control of the speed of the mobile device 600 when moving.
  • This method can be executed by the processor 601 of the mobile device 600, as follows Description will be made with reference to the embodiment of FIG. 2 .
  • the speed control method of the present disclosure includes
  • Cost Map is a virtual map calculated based on the environment map and the data collected by the mobile device sensor. It represents the cost of moving the mobile device in a specific way.
  • the path planning problem of the mobile device is stipulated as On the cost map, the path with the least cost.
  • the movement area refers to the preset range area that allows mobile devices to move autonomously.
  • the mobile device is a sweeping robot
  • the moving area is the working area of the sweeping robot.
  • the scene data of the mobile device during its movement can be collected in real time according to the scene sensing system 604 of the mobile device.
  • the scene data may include image data in front of the mobile device, lidar data, and pose data of the mobile device's own movement. , speed data, etc.
  • the cost map of the area in front of the mobile device can be obtained, as well as the target path of the mobile device in the next period of time.
  • the target distance refers to the distance between the current position of the mobile device and the obstacle in front
  • the turning angle refers to the turning angle of the mobile device when moving along the target path
  • the cost map it is not only necessary to determine the target distance between the current position of the mobile device and the obstacle in front, but also to determine the turning angle of the mobile device when moving along the target path.
  • the turning degree can reflect the size of the turning angle. When the target path is a straight line and the mobile device is moving in a straight line, the corresponding turning degree is zero.
  • the target distance between the mobile device and the obstacle includes two mutually perpendicular components: a first distance and a second distance.
  • the first distance refers to the distance component of the perpendicular line between the obstacle and the target path. Since the mobile device itself has a certain volume width, when the mobile device moves along the target path, if the distance component of the perpendicular line between the obstacle in front and the target path is relatively large, Small, the risk of collision or scratching between mobile equipment and obstacles is higher.
  • the second distance refers to the distance component parallel to the target path between the obstacle and the target path.
  • the line connecting the current position of the mobile device and the position of the obstacle can also be directly used as the target distance, that is, there is no need to calculate the above-mentioned first distance component and second distance component. No restrictions.
  • two normal line segments separated by a preset distance can be constructed as reference line segments for the target path within a preset range in front of the mobile device, that is, a first reference line segment and a second reference line segment.
  • first reference line segment and the second reference line segment are always perpendicular to the target path, when the target path is a straight line, the first reference line segment and the second reference line segment are in a mutually parallel positional relationship and will not intersect.
  • the first reference line segment and the second reference line segment are no longer parallel to each other, and as the curvature of the target path increases, the first reference line segment and the second reference line segment will intersect to form an included angle.
  • the greater the curvature of the target path the greater the angle value. Therefore, the angle value can be used to determine the curvature of the mobile device when moving along the target path.
  • the degree of turning represents the degree of turning of the mobile device when moving along the target path.
  • the degree of turning is not limited to the above method, and any other suitable method may be used to determine the degree of turning.
  • the implementation method is as long as the curvature parameter that represents the curvature of the target path can be obtained.
  • the curvature of the target path within a preset range in front of the mobile device can also be directly calculated based on the cost map to obtain the curvature of the target path. . This disclosure does not limit this.
  • the maximum speed limit V max of the mobile device represents the maximum operating speed that the mobile device is allowed to travel. For the speed control task of the mobile device, it can be understood as the process of adjusting the maximum speed limit of the mobile device. By adaptively adjusting the mobile device The maximum speed limit of the device allows the mobile device to maintain an appropriate moving speed under different road conditions.
  • the maximum deflection of the mobile device can be calculated based on the target distance and the deflection.
  • the speed limit V max is adjusted to obtain the corresponding target speed.
  • the target distance reflects the proximity of the mobile device to the obstacle.
  • the smaller the target distance the higher the risk of an accident to the mobile device, so the target speed should be lower.
  • the curvature reflects the curvature of the mobile device's own movement path. The greater the curvature, the higher the risk of an accident for the mobile device, so the target speed should be lower.
  • the maximum speed limit of the mobile device can be comprehensively adjusted based on the target distance and turning angle to obtain the target speed of the mobile device.
  • the straight speed component of the mobile device can be determined based on the target distance and the maximum speed limit, and the turning speed component of the mobile device can be determined based on the turning angle and the maximum speed limit, and then the straight speed component and the turning speed component can be weighted. Sum up to get the final target speed. This will be described in the following embodiments of the present disclosure and will not be described in detail here.
  • the mobile device can be controlled to move at the target speed.
  • the processor 601 can generate corresponding control instructions according to the target speed, and send the control instructions to the driving device 605.
  • the driving device 605 outputs motor torque according to the control instructions, thereby controlling the mobile device to move at the target speed.
  • the above description takes the speed control process of a mobile device in one control cycle as an example.
  • the above method and process are repeatedly executed to achieve speed control during the autonomous movement of the mobile device.
  • the control frequency of the mobile device is 5 Hz, that is, the above method is executed every 200 ms to achieve speed control of the mobile device.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • speed control not only Taking into account the target distance between the mobile device and the obstacle, and also combining the curvature of the target path of the mobile device itself, the risk of accidents caused by blind spots in the corner of the vision is reduced, and the speed control effect is further improved.
  • the process of obtaining the cost map of the moving area and the target path includes:
  • the scene sensing system 604 can collect scene data in the current state.
  • the scene perception system 604 is a VSLAM system based on computer vision.
  • the scene data collected by the VSLAM system may include scene image data of the moving area in front of the mobile device, physical depth data, motion information of the mobile device itself, etc.
  • the scene perception system 604 can also be other systems, such as lidar, etc., and this disclosure is not limited to this.
  • S320 Position and map the mobile device according to the scene data to obtain the current location and environment map of the mobile device.
  • the simultaneous positioning and mapping SLAM algorithm can be used according to the scene data including image data, physical depth data, lidar data, IMU data, etc.
  • the mobile device is positioned and the map of the moving area in front of the mobile device is reconstructed, thereby obtaining the current location of the mobile device and the environment map of the moving area.
  • the cost map is a virtual map used for path planning of the mobile device.
  • the cost map may be a local 2D cost map within a preset range in front of the mobile device.
  • the obstacle information in the environment map can be determined by combining, for example, lidar data or physical depth data, and then the corresponding cost map can be obtained based on the obstacle information and the environment map.
  • the target path of the mobile device within the cost map range can be determined based on the current location of the mobile device and the preset global path of the mobile device.
  • the target path is the planned movement path of the mobile device in the next period of time.
  • the cost map may be as shown in FIG. 4 , the current position of the mobile device 600 is S, the target position is G, and the curve SG is the target path.
  • the moving area includes a total of three obstacles, namely obstacle O 1 , obstacle O 2 and obstacle O 3 .
  • FIG. 4 is only used as an illustration of the embodiment of the present disclosure and does not limit the present disclosure.
  • the process of determining the current target distance between the mobile device and the obstacle includes:
  • the preset range in front of the mobile device refers to the preset forward-looking range area located in front of the moving direction of the mobile device.
  • the preset range described in this disclosure is the forward-looking range area of the mobile device.
  • the preset range 400 area in front of the mobile device 600 is the rectangular range area shown by the dotted line in the figure. As the mobile device 600 moves, the preset range 400 is always located in front of the moving direction of the mobile device 600 .
  • the size of the preset range is 2R*P, where the specific values of R and P can be set according to the size of the mobile device, scene requirements and other factors, and this disclosure does not limit this.
  • the preset range 400 in Figure 4 is only an example of the implementation of the present disclosure.
  • the preset range 400 is not limited to the rectangular range area shown in Figure 4, and can also be, for example, a fan shape. Range area, etc., this disclosure does not limit this.
  • the obstacle data includes the position coordinates of the obstacle in the image coordinate system.
  • the target distance between the mobile device and the obstacle includes two mutually perpendicular components, the first distance and the second distance.
  • the first distance refers to the distance obtained by drawing the obstacle perpendicular to the target path
  • the second distance refers to the distance between the obstacle and the mobile device in a direction parallel to the target path.
  • the obstacle O 2 is located in the preset range 400, so that the first distance L 1 between the obstacle and the target path and the second distance between the obstacle and the mobile device can be determined on the cost map based on the obstacle data. L2 .
  • the first distance refers to the shortest distance L 1 obtained by drawing a perpendicular line from the obstacle O 2 to the target path SG.
  • the second path refers to the shortest distance L 2 between the obstacle O 2 and the mobile device 600 in a direction parallel to the target path, that is, the first distance L 1 and the second distance L 2 are perpendicular to each other.
  • the target distance between the mobile device and the obstacle includes the above-mentioned first distance L 1 and second distance L 2 , so that after obtaining the first distance L 1 and the second distance L 2 , the first distance L is 1 and the second distance L 2 are determined as the target distance between the mobile device and the obstacle.
  • the speed control method of the present disclosure example determines the turning angle of the mobile device when moving along the target path, including:
  • two normal line segments separated by a preset distance are made as reference line segments for the target path, which are respectively defined as the first reference line segment and the second reference line segment.
  • reference line segments for the target path which are respectively defined as the first reference line segment and the second reference line segment.
  • first reference line segment K 1 and the second reference line segment K 2 are drawn for the target path, namely, the first reference line segment K 1 and the second reference line segment K 2 .
  • the first reference line segment K 1 and the second reference line segment K 2 are separated by a preset distance d. It can be understood that the line segment lengths of the first reference line segment K 1 and the second reference line segment K 2 can be set according to specific scene requirements, and this disclosure does not limit this.
  • the target path is a straight line at this time. Since the first reference line segment K 1 and the second reference line segment K 2 are both perpendicular to the target path, the first reference line segment K 1 and the second reference line segment K 2 are parallel to each other, the two will not intersect, and there will be no included angle.
  • the current position of the mobile device 600 is S 1 and the target path ahead is a curve. Since the first reference line segment K 1 and the second reference line segment K 2 are always perpendicular to the target path, the first reference line segment K 1 and the second reference line segment K 1 The reference line segment K 2 will intersect, the intersection point is Q, and the two have an angle ⁇ .
  • first reference line segment K 1 and the second reference line segment K 2 are both line segments, that is, they are not infinitely extended, therefore, even if the target path is curved, the first reference line segment K 1 and the second reference line segment K 2
  • the reference line segment K 2 is no longer parallel, but when the curvature is small, the first reference line segment K 1 and the second reference line segment K 2 still do not intersect.
  • the first reference line segment and the second reference line segment do not intersect, it means that the target path within the preset range is a straight line or has a small curvature.
  • the first reference line segment and the second reference line segment The line segments have no included angles, and the curvature of the target path can be defined as zero.
  • the target distance and turning angle between the current position of the mobile device and the obstacle can be determined, and then the maximum speed limit of the mobile device is adjusted according to the target distance and turning angle, which will be described in detail below.
  • the speed control method of the present disclosure example determines the target speed of the mobile device based on the target distance, turning angle, and maximum speed limit, including:
  • the maximum speed limit can be adaptively adjusted according to the size of the target distance to obtain the straight speed component.
  • the target distance is positively correlated with the straight-going speed component. That is, the larger the target distance, the farther the current distance between the mobile device and the obstacle is, the lower the risk of an accident, and thus the greater the straight-going speed component. On the contrary, the smaller the target distance is, the closer the current distance between the mobile device and the obstacle is, the higher the risk of an accident, and thus the smaller the straight speed component.
  • the corresponding relationship between the target distance and the straight-going speed component can be established in advance, and the size of the straight-going speed component can be determined by looking up the corresponding relationship.
  • the target distance includes the first distance L 1 and the second distance L 2 , therefore, the straight speed component in the embodiment of the present disclosure also includes the first speed component and the second speed component. .
  • the straight speed component in the embodiment of the present disclosure also includes the first speed component and the second speed component.
  • the process of determining the straight speed component according to the target distance includes:
  • the first distance L 1 between the mobile device 600 and the obstacle O 2 and the second distance L 2 between the mobile device 600 and the obstacle O 2 can be obtained through the aforementioned embodiments.
  • the first velocity component and the second velocity component can be expressed as:
  • V 1 represents the first velocity component
  • V 2 represents the second velocity component
  • L 1 represents the first distance
  • L 2 represents the second distance
  • R represents half of the preset range width
  • P represents the length of the preset range
  • V max represents the maximum speed limit of the mobile device.
  • the first speed component V 1 and the second speed component V 2 of the mobile device can be calculated, and then the first speed component V 1 and the second speed component V 2 are determined to be straight. velocity component.
  • S820 Determine the turning speed component of the mobile device according to the turning degree and the maximum speed limit.
  • the maximum speed limit can be adaptively adjusted according to the magnitude of the curvature to obtain the turning speed component.
  • the turning angle is negatively related to the turning speed component, that is, the larger the turning angle, the higher the risk of accidents caused by the mobile equipment, and therefore the turning speed component should be smaller.
  • the smaller the turning angle the lower the risk of accidents caused by the mobile device, and thus the greater the turning speed component.
  • the calculation process of the turning speed component can be expressed as:
  • V 3 represents the turning speed component
  • represents the turning degree
  • V max represents the maximum speed limit
  • the straight speed component represents the straight speed of the mobile device under current road conditions
  • the turning speed component represents the turning speed of the mobile device under current road conditions.
  • a weighted fusion process can be performed on the straight traveling speed component and the turning speed component to obtain the final target speed.
  • the straight speed weight includes a first weight value a and a second weight value b
  • the turning speed weight includes a third weight value c. Therefore, the target speed can be expressed as:
  • V a*V 1 +b*V 2 +c*V 3 (4)
  • V represents the target speed
  • V 1 represents the first speed component
  • a represents the first weight value of the first speed component
  • V 2 represents the second speed component
  • b represents the second weight of the second speed component
  • value V 3 represents the turning speed component
  • c represents the third weight value of the turning speed component.
  • the first speed component, the second speed component and the turning speed component can be fused to obtain the target speed corresponding to the mobile device.
  • V max , the turning speed component V 3 calculated based on equation (3) is less than V max , and the target speed V obtained by substituting into equation (4) should also be less than V max , that is, the speed of the mobile device is adaptively reduced.
  • the first speed component V 1 , the second speed component V 2 and the turning speed component can be calculated based on the aforementioned formulas (1) to (3).
  • V 3 is all smaller than V max , and the target speed V obtained by substituting into equation (4) should also be smaller than V max , that is, the speed of the mobile device is adaptively reduced.
  • the speed of the mobile device is not only adjusted based on the distance between the mobile device and the obstacle, but also further combined with the turning rate to adjust the speed of the mobile device.
  • the speed of the mobile device is adjusted. Obstacles will still reduce the speed of mobile devices to avoid overturning due to excessive turning speed, or reduce the risk of accidents caused by blind spots in turning vision.
  • a preset speed range of the mobile device in order to ensure the normal operation of the mobile device, can be set in advance.
  • the preset speed range can limit the minimum speed limit V min and the maximum speed limit V max of the mobile device, that is, The movement speed of the mobile device should be within the preset speed range [V min , V max ].
  • the mobile device can be controlled to move at the minimum speed limit V min .
  • the target speed is greater than the maximum speed limit V max , the mobile device can be controlled to move at the maximum speed limit V max .
  • the target speed is within the preset speed range [V min , V max ], the mobile device can be controlled to move at the target speed.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • speed control not only Consider the target distance between the mobile device and the obstacle, and also combine the curvature of the target path of the mobile device itself to avoid overturning due to excessive turning speed, reduce the risk of accidents caused by blind spots in the corner, and further improve the speed control effect. .
  • embodiments of the present disclosure provide a speed control device, which can be applied in mobile devices.
  • the mobile device in the embodiment of the present disclosure can be any type of device with autonomous movement capabilities that is suitable for implementation, such as a sweeping robot, a logistics robot, a food delivery robot, a smart mobile trash can, etc., and the present disclosure is not limited to this.
  • the speed control device of the present disclosure includes:
  • the acquisition module 10 is configured to obtain the cost map of the movement area and the target path of the mobile device moving in the movement area;
  • the first determination module 20 is configured to determine the current target distance between the mobile device and the obstacle based on the cost map, and the turning angle of the mobile device when moving along the target path;
  • the second determination module 30 is configured to determine the target speed of the mobile device according to the target distance, the turning angle, and the maximum speed limit of the mobile device;
  • the control module 40 is configured to control the mobile device to move at the target speed.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • speed control not only Taking into account the target distance between the mobile device and the obstacle, and also combining the curvature of the target path of the mobile device itself, the risk of accidents caused by blind spots in the corner of the vision is reduced, and the speed control effect is further improved.
  • the acquisition module 10 is configured to:
  • a cost map of the mobile area is obtained based on the obstacle information in the environment map, and the target path of the mobile device is determined based on the cost map and the current location.
  • the first determining module 20 is configured as:
  • the target distance is obtained according to the first distance and the second distance.
  • the first determining module 20 is configured as:
  • the cost map Based on the cost map, determine the first reference line segment and the second reference line segment within the preset range in front of the mobile device; wherein the first reference line segment and the second reference line segment are both perpendicular to the target path, And there is a preset distance between the first reference line segment and the second reference line segment;
  • the current turning angle of the mobile device is determined according to the angle between the first reference line segment and the second reference line segment.
  • the first determining module 20 is configured as:
  • the intersection coordinates of the first reference line segment and the second reference line segment are determined based on the cost map, and based on the intersection coordinates and the predetermined Assume that the distance determines the angle between the first reference line segment and the second reference line segment, and the angle is determined as the bending degree;
  • the curvature is determined to be zero.
  • the second determination module 30 is configured as:
  • the turning speed component of the mobile device is determined according to the turning degree and the maximum speed limit; wherein the turning speed component is negatively related to the turning degree;
  • a weighted fusion process is performed on the straight speed component and the turning speed component to obtain the target speed of the mobile device.
  • the second determination module 30 is configured as:
  • the straight ahead speed component is obtained based on the first speed component and the second speed component.
  • control module 40 is configured to:
  • the mobile device In response to the target speed satisfying the preset speed range, the mobile device is controlled to move at the target speed.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • speed control not only Consider the target distance between the mobile device and the obstacle, and also combine the curvature of the target path of the mobile device itself to avoid overturning due to excessive turning speed, reduce the risk of accidents caused by blind spots in the corner, and further improve the speed control effect. .
  • an embodiment of the present disclosure provides a mobile device, including:
  • the memory stores computer instructions for causing the processor to execute the method according to any implementation manner of the first aspect.
  • an embodiment of the present disclosure provides a storage medium that stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any embodiment of the first aspect.
  • the current moving speed is controlled by the target distance and turning angle between the mobile device and the obstacle, and the moving speed can be adaptively adjusted according to the current road conditions to reduce the risk of accidents.
  • speed control not only Consider the target distance between the mobile device and the obstacle, and also combine the curvature of the target path of the mobile device itself to avoid overturning due to excessive turning speed, reduce the risk of accidents caused by blind spots in the corner, and further improve the speed control effect. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

本公开涉及智能机器人技术领域,具体提供了一种移动设备及其速度控制方法、装置、存储介质。一种速度控制方法,所述方法包括:获取移动区域的代价地图以及移动设备的目标路径;基于代价地图,确定移动设备当前与障碍物的目标距离以及转弯曲度;根据目标距离、转弯曲度以及移动设备的最大限速,确定移动设备的目标速度;控制移动设备以目标速度移动。本公开实施方式,对移动设备进行自适应速度控制,提高速度控制效果。

Description

移动设备及其速度控制方法、装置、存储介质 技术领域
本公开涉及智能机器人技术领域,具体涉及一种移动设备及其速度控制方法、装置、存储介质。
背景技术
目前,自主移动设备广泛应用于各种工业及生活场景中,例如物流机器人、送餐机器人、扫地机器人等。移动设备的运动控制规划,直接决定了移动设备的运行效果及安全等级,相关技术中,移动设备的移动速度控制效果较差,导致移动设备的安全性和移动效率较低。
发明内容
为提高移动设备的速度控制效果,本公开实施方式提供了一种移动设备及其速度控制方法、装置、存储介质。
第一方面,本公开实施方式提供了一种速度控制方法,应用于移动设备,所述方法包括:
获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径;
基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,以及所述移动设备当前沿所述目标路径移动时的转弯曲度;
根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度;
控制所述移动设备以所述目标速度移动。
在一些实施方式中,所述获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径,包括:
获取通过所述移动设备的传感器采集到的所述移动区域的场景数据;
根据所述场景数据对所述移动设备进行定位与建图,得到所述移动设备的当前位置和环境地图;
根据所述环境地图中障碍物信息得到所述移动区域的代价地图,并根据所述代价地图和所述当前位置确定所述移动设备的所述目标路径。
在一些实施方式中,基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,包括:
基于所述代价地图,确定所述移动设备前方预设范围内的障碍物数据;
根据所述障碍物数据,确定障碍物与所述目标路径的第一距离,以及所述障碍物与所述移动设备当前位置的第二距离;其中,所述第一距离垂直于所述目标路径,所述第二距离平行于所述目标路径;
根据所述第一距离和所述第二距离得到所述目标距离。
在一些实施方式中,基于所述代价地图,确定所述移动设备当前沿所述目标路径移动时的转弯曲度,包括:
基于所述代价地图,确定所述移动设备前方预设范围内的第一参考线段和第二参考线段;其中,所述第一参考线段和所述第二参考线段均垂直于所述目标路径,且所述第一参考线段和所述第二参考线段之间间隔预设距离;
根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度。
在一些实施方式中,所述根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度,包括:
响应于所述第一参考线段与所述第二参考线段相交,基于所述代价地图确定所述第一参考线段与所述第二参考线段的交点坐标,并根据所述交点坐标以及所述预设距离确定所述第一参考线段与所述第二参考线段之间的夹角,将所述夹角确定为所述转弯曲度;
响应于所述第一参考线段与所述第二参考线段未相交,确定所述转弯曲度为零。
在一些实施方式中,所述根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度,包括:
根据所述目标距离和所述最大限速确定所述移动设备的直行速度分量;其中,所述直行速度分量与所述目标距离正相关;
根据所述转弯曲度和所述最大限速确定所述移动设备的转弯速度分量; 其中,所述转弯速度分量与所述转弯曲度负相关;
基于预先设置的直行速度权重和转弯速度权重,对所述直行速度分量和所述转弯速度分量进行加权融合处理,得到所述移动设备的目标速度。
在一些实施方式中,所述目标距离包括垂直于所述目标路径的第一距离和平行于所述目标路径的第二距离;所述根据所述目标距离确定所述移动设备的直行速度分量,包括:
根据所述第一距离和所述最大限速,确定所述移动设备的第一速度分量;
根据所述第二距离和所述最大限速,确定所述移动设备的第二速度分量;
根据所述第一速度分量和所述第二速度分量得到所述直行速度分量。
在一些实施方式中,所述控制所述移动设备以所述目标速度移动,包括:
响应于所述目标速度满足预设速度范围,控制所述移动设备以所述目标速度移动。
第二方面,本公开实施方式提供了一种速度控制装置,应用于移动设备,所述装置包括:
获取模块,被配置为获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径;
第一确定模块,被配置为基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,以及所述移动设备当前沿所述目标路径移动时的转弯曲度;
第二确定模块,被配置为根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度;
控制模块,被配置为控制所述移动设备以所述目标速度移动。
在一些实施方式中,所述获取模块被配置为:
获取通过所述移动设备的传感器采集到的所述移动区域的场景数据;
根据所述场景数据对所述移动设备进行定位与建图,得到所述移动设备的当前位置和环境地图;
根据所述环境地图中障碍物信息得到所述移动区域的代价地图,并根 据所述代价地图和所述当前位置确定所述移动设备的所述目标路径。
在一些实施方式中,所述第一确定模块,被配置为:
基于所述代价地图,确定所述移动设备前方预设范围内的障碍物数据;
根据所述障碍物数据,确定障碍物与所述目标路径的第一距离,以及所述障碍物与所述移动设备当前位置的第二距离;其中,所述第一距离垂直于所述目标路径,所述第二距离平行于所述目标路径;
根据所述第一距离和所述第二距离得到所述目标距离。
在一些实施方式中,所述第一确定模块,被配置为:
基于所述代价地图,确定所述移动设备前方预设范围内的第一参考线段和第二参考线段;其中,所述第一参考线段和所述第二参考线段均垂直于所述目标路径,且所述第一参考线段和所述第二参考线段之间间隔预设距离;
根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度。
在一些实施方式中,所述第一确定模块,被配置为:
响应于所述第一参考线段与所述第二参考线段相交,基于所述代价地图确定所述第一参考线段与所述第二参考线段的交点坐标,并根据所述交点坐标以及所述预设距离确定所述第一参考线段与所述第二参考线段之间的夹角,将所述夹角确定为所述转弯曲度;
响应于所述第一参考线段与所述第二参考线段未相交,确定所述转弯曲度为零。
在一些实施方式中,所述第二确定模块,被配置为:
根据所述目标距离和所述最大限速确定所述移动设备的直行速度分量;其中,所述直行速度分量与所述目标距离正相关;
根据所述转弯曲度和所述最大限速确定所述移动设备的转弯速度分量;其中,所述转弯速度分量与所述转弯曲度负相关;
基于预先设置的直行速度权重和转弯速度权重,对所述直行速度分量和所述转弯速度分量进行加权融合处理,得到所述移动设备的目标速度。
在一些实施方式中,所述第二确定模块,被配置为:
根据所述第一距离和所述最大限速,确定所述移动设备的第一速度分 量;
根据所述第二距离和所述最大限速,确定所述移动设备的第二速度分量;
根据所述第一速度分量和所述第二速度分量得到所述直行速度分量。
在一些实施方式中,所述控制模块,被配置为:
响应于所述目标速度满足预设速度范围,控制所述移动设备以所述目标速度移动。
第三方面,本公开实施方式提供了一种移动设备,包括:
处理器;和
存储器,存储有计算机指令,所述计算机指令用于使处理器执行根据第一方面任意实施方式所述的方法。
第四方面,本公开实施方式提供了一种存储介质,存储有计算机指令,所述计算机指令用于使计算机执行根据第一方面任意实施方式所述的方法。
本公开实施方式速度控制方法,包括获取移动区域的代价地图以及移动设备在移动区域中移动的目标路径,基于代价地图确定移动设备与障碍物的目标距离以及转弯曲度,根据目标距离、转弯曲度以及最大限速确定目标速度,控制移动设备以目标速度移动。本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,避免由于转弯速度过快导致的倾覆,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
附图说明
为了更清楚地说明本公开具体实施方式或现有技术中的技术方案,下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本公开的一些实施方式,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是根据本公开一些实施方式中移动设备的结构框图。
图2是根据本公开一些实施方式中速度控制方法的流程图。
图3是根据本公开一些实施方式中速度控制方法的流程图。
图4是根据本公开一些实施方式中速度控制方法的原理图。
图5是根据本公开一些实施方式中速度控制方法的流程图。
图6是根据本公开一些实施方式中速度控制方法的流程图。
图7是根据本公开一些实施方式中速度控制方法的原理图。
图8是根据本公开一些实施方式中速度控制方法的流程图。
图9是根据本公开一些实施方式中速度控制方法的流程图。
图10是根据本公开一些实施方式中速度控制装置的结构框图。
具体实施方式
下面将结合附图对本公开的技术方案进行清楚、完整地描述,显然,所描述的实施方式是本公开一部分实施方式,而不是全部的实施方式。基于本公开中的实施方式,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施方式,都属于本公开保护的范围。此外,下面所描述的本公开不同实施方式中所涉及的技术特征只要彼此之间未构成冲突就可以相互结合。
目前,例如扫地机器人、物流机器人、送餐机器人、足式机器人等移动设备,可以在预设的运行空间中自主移动,从而实现对应的作业需求。对移动设备的速度控制是运动规划中的重要一环,移动设备的移动速度过快,发生事故的风险以及事故带来的损失上升;移动设备的移动速度过慢,其作业效率也会降低。
相关技术中,部分场景下,可预先对移动设备的作业区域进行分区限速,例如,预先将移动设备的整个移动区域划分为A、B、C三个分区,每个分区根据障碍物情况、移动设备密度等因素预先设置不同的最大限速,从而当移动设备运行至某个分区时,以该分区规定的最大限速运行。
在这种场景下,移动设备无法根据障碍物的变化自适应调节运动速度,只能根据分区限定的速度来运行。当某个限速较低的分区障碍物或设备密度减少时,移动设备依旧按照较低的限速运行,导致移动设备的作业效率降低。反之,当某个限速较高的分区障碍物或设备密度增大时,移动设备依旧按照 较高的限速运行,导致移动设备出现碰撞、剐蹭等事故的风险大大提升。另外,移动设备只能在设定好的分区中实现移动速度的控制,对于其他移动区域无法实现速度自适应控制,因此移动设备的适应性很差。
基于上述相关技术中存在的缺陷,本公开实施方式提供了一种移动设备及其速度控制方法、装置、存储介质,旨在实现移动设备的速度自适应控制,降低移动设备的事故风险,提高移动设备的安全性和移动效率。
第一方面,本公开实施方式提供了一种速度控制方法,该方法可应用于移动设备中。本公开实施方式的移动设备,可以是任何适于实施的具有自主运动能力的设备类型,例如足式机器人、扫地机器人、物流机器人、送餐机器人、智能移动垃圾桶等,本公开对此不作限制。
如图1所示,在一些实施方式中,本公开示例的移动设备600包括处理器601、存储器602、场景感知系统604以及驱动装置605。
处理器601、存储器602、场景感知系统604以及驱动装置605,通过总线603建立任意两者之间的可通信连接。
处理器601可以为任何类型,具备一个或者多个处理核心的处理器。其可以执行单线程或者多线程的操作,用于解析指令以执行获取数据、执行逻辑运算功能以及下发运算处理结果等操作。
存储器602可包括非易失性计算机可读存储介质,例如至少一个磁盘存储器件、闪存器件、相对于处理器601远程设置的分布式存储设备或者其他非易失性固态存储器件。存储器可以具有程序存储区,用于存储非易失性软件程序、非易失性计算机可执行程序以及模块,供处理器601调用以使处理器601执行一个或者多个方法步骤。存储器602还可以包括易失性随机存储介质、或者硬盘等存储部分,作为数据存储区,用以存储处理器601下发输出的运算处理结果及数据。
场景感知系统604是移动设备用于获取当前场景数据的传感器系统,通过场景感知系统604采集当前场景的相关数据,从而移动设备实现设备定位、地图构建等功能。
在一些实施方式中,场景感知系统604可以是SLAM(Simultaneous Localization and Mapping,同步定位与建图)系统。SLAM系统可以包括多个传感器,例如单目相机、双目相机、激光雷达、IMU(Inertial Measurement Unit, 惯性测量单元)传感器、ToF(Time of flight,飞行时间)传感器等。通过这些传感器实时采集移动设备运动过程中的数据,基于采集数据利用SLAM算法实现设备的定位与建图。
本公开实施方式中,可以通过场景感知系统604的采集数据,建立移动设备移动过程中的代价地图,实现移动设备的路径规划和速度控制。本公开下文方法中进行具体说明,在此暂不详述。
驱动装置605为移动设备的动力系统,用于驱动移动设备600产生位移。在一些实施方式中,驱动装置605可以包括例如电机、传动机构以及滚轮等机械结构,本领域技术人员对此毫无疑问可以理解并充分实现,本公开不再赘述。当然,本领域技术人员可以理解,移动设备600还可以包括其他各种电气元件和机械部件,本公开实施方式对此不作赘述。
在图1所示的移动设备的基础上,本公开实施方式提供了速度控制方法,用于对移动设备600移动时的速度进行实时控制,该方法可以由移动设备600的处理器601执行,下面结合图2实施方式进行说明。
如图2所示,在一些实施方式中,本公开示例的速度控制方法,包括
S210、获取移动区域的代价地图以及移动设备在移动区域中移动的目标路径。
可以理解,代价地图(Cost Map)是根据环境地图和移动设备传感器采集数据计算得到的一张虚拟地图,表示移动设备按照特定方式移动会消耗的代价,移动设备的路径规划问题就规定为求取在代价地图上,消耗代价最少的路径。
移动区域是指允许移动设备进行自主移动的预设范围区域。例如,移动设备以扫地机器人为例,移动区域即为扫地机器人的作业区域。
本公开实施方式中,可以根据移动设备的场景感知系统604实时采集移动设备在移动过程中的场景数据,场景数据可包括移动设备前方的图像数据、激光雷达数据、移动设备自身运动的位姿数据、速度数据等。基于采集的场景数据,可以得到移动设备运动前方区域的代价地图,以及移动设备接下来一段时间移动的目标路径。
对于计算代价地图以及移动设备的目标路径的过程,本公开下文图3实施方式中进行说明,在此暂不展开。
S220、基于代价地图,确定移动设备当前与障碍物的目标距离,以及移动设备当前沿目标路径移动时的转弯曲度。
本公开实施方式中,目标距离是指移动设备的当前位置与前方障碍物之间的距离,转弯曲度是指移动设备当前沿目标路径移动时的转弯角度。
传统的机器人路径规划方案中,往往只关注于移动设备与前方障碍物的距离,当移动设备与障碍物距离较近时,为降低两者发生碰撞或剐蹭的风险,降低机器人的移动速度。
然而,本案发明人研究发现,移动设备是否会发生意外事故,一方面取决于移动设备与障碍物的距离,两者的距离越近,发生事故的风险也越高;另一方面还取决于移动设备的转弯角度,移动设备在转弯过程中常常由于视野盲区导致发生碰撞和剐蹭事故,并且移动设备的转弯角度越大,发生事故的风险也越大。
本公开实施方式中,基于代价地图,不仅需要确定移动设备当前位置与前方障碍物之间的目标距离,还需要确定移动设备当前沿目标路径移动时的转弯曲度。该转弯曲度即可反映转弯角度的大小,当目标路径为直线,移动设备当前沿直线移动时,对应的转弯曲度即为零。
在一些实施方式中,可以根据代价地图,确定移动设备当前位置的前方预设范围内是否存在障碍物,预设范围表示机器人的预设前瞻范围。若预设范围内存在障碍物,则可以基于代价地图确定障碍物与移动设备当前位置之间的距离,也即本公开实施方式所述的目标距离。
在一些实施方式中,移动设备与障碍物的目标距离包括第一距离和第二距离两个互相垂直的分量。
第一距离是指障碍物与目标路径作垂线的距离分量,由于移动设备本身具有一定的体积宽度,在移动设备沿目标路径移动时,若前方障碍物向目标路径作垂线的距离分量较小,移动设备与障碍物发生碰撞或剐蹭的风险较高。
第二距离是指障碍物与目标路径平行的距离分量,在移动设备沿目标路径移动时,若前方障碍物与目标路径平行的距离分量较小,说明移动设备当前位置与障碍物较为接近,发生碰撞或剐蹭的风险较高。
本公开下文实施方式中,对于第一距离和第二距离的具体原理和过程进行说明,在此暂不详述。
另外,可以理解,本公开实施方式中,也可以直接用移动设备当前位置与障碍物位置的连线作为目标距离,也即无需计算上述的第一距离分量和第二距离分量,本公开对此不作限制。
在一些实施方式中,可以基于代价地图,在移动设备前方预设范围内,对目标路径作两条间隔预设距离的法线段作为参考线段,也即第一参考线段和第二参考线段。
可以理解,由于第一参考线段和第二参考线段始终垂直于目标路径,因此当目标路径为直线时,第一参考线段和第二参考线段处于相互平行的位置关系,两者不会相交。
而当目标路径为曲线时,第一参考线段和第二参考线段不再相互平行,而且随着目标路径的曲率增加,第一参考线段和第二参考线段将会产生交点,形成夹角。目标路径的曲率越大,该夹角值也越大,从而,可以通过该夹角值确定移动设备当前沿目标路径移动时的转弯曲度。
对于确定转弯曲度的具体过程和原理,本公开下文实施方式中进行具体说明,在此暂不详述。
另外,可以理解,转弯曲度表示的是移动设备当前沿目标路径移动时的转弯程度的大小,本公开实施方式中,并不局限于利用上述方式确定转弯曲度,还可以采用其他任何适于实施的方式,只要能得到表征目标路径弯曲程度的转弯曲度参数即可,例如也可以基于代价地图,直接对移动设备前方预设范围内的目标路径进行曲率计算,得到目标路径的转弯曲度。本公开对此不作限制。
S230、根据目标距离、转弯曲度以及移动设备的最大限速,确定移动设备的目标速度。
移动设备的最大限速V max,表示的是移动设备允许行驶的最大运行速度,对于移动设备的速度控制任务,即可理解为对移动设备的最大限速进行调整的过程,通过自适应调整移动设备的最大限速,使得移动设备在不同的路况下保持合适的移动速度。
本公开实施方式中,在得到移动设备当前位置与前方障碍物的目标距离、以及移动设备当前沿目标路径移动时的转弯曲度之后,即可根据目标距离和转弯曲度综合对移动设备的最大限速V max进行调控,得到对应的目标速度。
可以理解,目标距离反映的是移动设备与障碍物的接近程度,目标距离越小移动设备发生事故的风险越高,从而目标速度应当越低。转弯曲度反映的是移动设备自身移动路径的弯曲程度,转弯曲度越大移动设备发生事故的风险越高,从而目标速度应当越低。
基于上述原理,可以根据目标距离和转弯曲度综合对移动设备的最大限速进行调整,得到移动设备移动的目标速度。
例如一些实施方式中,可以根据目标距离和最大限速确定移动设备的直行速度分量,同时根据转弯曲度和最大限速确定移动设备的转弯速度分量,然后对直行速度分量和转弯速度分量进行加权求和,得到最终的目标速度。本公开下文实施方式中对此进行说明,在此暂不详述。
S240、控制移动设备以目标速度移动。
本公开实施方式中,在确定移动设备的目标速度之后,即可控制移动设备以该目标速度进行移动。例如图1所示,处理器601可以根据目标速度生成对应的控制指令,并将控制指令发送至驱动装置605,驱动装置605根据控制指令输出电机转矩,从而控制移动设备以目标速度移动。
上述以移动设备一个控制周期的速度控制过程为例进行了说明,对于每个控制周期,均重复执行上述方法过程即可实现对移动设备自主移动过程中的速度控制。例如一个示例中,移动设备的控制频率为5Hz,也即每200ms执行一次上述方法过程,实现移动设备的速度控制。
通过上述可知,本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
如图3所示,在一些实施方式中,本公开示例的速度控制方法,获取移动区域的代价地图以及目标路径的过程,包括:
S310、获取通过移动设备的传感器采集到的移动区域的场景数据。
本公开实施方式中,结合图1所示,移动设备600在移动过程中,场景感知系统604可以采集到当前状态下的场景数据。
例如一个示例中,场景感知系统604为基于计算机视觉的VSLAM系统, VSLAM系统采集的场景数据可以包括移动设备前方移动区域的场景图像数据、物理深度数据、移动设备自身的运动信息等。
当然,在其他示例中,场景感知系统604还可以是其他系统,例如激光雷达等,本公开对此不作限制。
S320、根据场景数据对移动设备进行定位与建图,得到移动设备的当前位置和环境地图。
本公开实施方式中,基于前述场景感知系统604采集到的场景数据,可以根据场景数据包括的例如图像数据、物理深度数据、激光雷达数据、IMU数据等,利用同步定位与建图SLAM算法,对移动设备进行定位,以及对移动设备的前方移动区域进行地图重建,从而,得到移动设备的当前位置和移动区域的环境地图。
对于SLAM算法的原理和过程,本领域技术人员参照相关技术毫无疑问可以理解并充分实现,本公开对此不作限制。
S330、根据环境地图中障碍物信息得到移动区域的代价地图,并根据代价地图和当前位置确定移动设备的目标路径。
基于前述可知,代价地图是用于对移动设备进行路径规划的虚拟地图,在一些实施方式中,代价地图可以是移动设备前方预设范围内的局部2D代价地图。
本公开实施方式中,在得到环境地图之后,可以结合例如激光雷达数据或者物理深度数据,确定环境地图中的障碍物信息,然后根据障碍物信息和环境地图得到对应的代价地图。
然而,在得到代价地图之后,可基于移动设备当前位置以及预先设置的移动设备的全局路径,确定移动设备在代价地图范围内的目标路径。目标路径即为规划得到的,移动设备接下来一端时间的移动路径。
例如一个示例中,代价地图可如图4中所示,移动设备600当前位置为S,目标位置为G,曲线SG即为目标路径。其中,移动区域中共包括3个障碍物,也即障碍物O 1、障碍物O 2和障碍物O 3
本公开下文实施方式中,将以图4所示的代价地图,对本公开实施方式的速度控制方法进行说明。但是可以理解,图4仅作为本公开实施方式的一个示例说明,并不限制本公开方案。
如图5所示,在一些实施方式中,本公开示例的速度控制方法,确定移动设备当前与障碍物的目标距离的过程,包括:
S510、基于代价地图,确定移动设备前方预设范围内的障碍物数据。
S520、根据障碍物数据,确定障碍物与目标路径的第一距离,以及障碍物与移动设备当前位置的第二距离。
S530、根据第一距离和第二距离得到目标距离。
本公开实施方式中,移动设备前方预设范围,是指位于移动设备移动方向的前方预设的前瞻范围区域。
可以理解,移动设备在移动过程中,需要提前确定前方的路况信息,从而对移动设备的速度进行控制,也即,移动设备的速度控制和路径规划应当具有一定的前瞻性。本公开所述的预设范围,即为移动设备的前瞻范围区域。
例如图4示例中,移动设备600前方的预设范围400区域即为图中虚线所示的矩形范围区域,随着移动设备600的移动,预设范围400始终位于移动设备600移动方向的前方。本公开示例中,预设范围的尺寸为2R*P,其中,R与P的具体取值可以根据移动设备尺寸、场景需求等因素进行设置,本公开对此不作限制。
当然,本领域技术人员可以理解,图4中的预设范围400仅作为本公开实施方式的一种示例,预设范围400并不局限于图4所示的矩形范围区域,还可以是例如扇形范围区域等,本公开对此不作限制。
本公开实施方式中,在得到移动区域的代价地图之后,可基于代价地图确定移动设备当前位置前方预设范围内是否存在障碍物,若预设范围内存在障碍物,则可以根据代价地图确定障碍物数据,障碍物数据包括障碍物在图像坐标系中的位置坐标。
本公开实施方式中,移动设备与障碍物的目标距离包括第一距离和第二距离两个互相垂直的分量。第一距离是指障碍物向目标路径作垂线得到的距离,而第二距离是指障碍物在平行于目标路径方向上与移动设备的距离。
例如图4示例中,障碍物O 2位于预设范围400中,从而根据障碍物数据可以在代价地图上确定障碍物与目标路径的第一距离L 1,以及障碍物与移动设备的第二距离L 2
在本示例中,第一距离是指障碍物O 2向目标路径SG作垂线,得到的最 短距离L 1。第二路径是指障碍物O 2在平行于目标路径方向上与移动设备600的最短距离L 2,也即,第一距离L 1和第二距离L 2互相垂直。
本公开实施方式中,移动设备与障碍物的目标距离包括上述的第一距离L 1和第二距离L 2,从而在得到第一距离L 1和第二距离L 2之后,将第一距离L 1和第二距离L 2确定为移动设备与障碍物的目标距离。
上述结合图5实施方式对本公开方法中确定移动设备与障碍物的目标距离的过程进行了说明,下面结合图6、图7对本公开方法中确定转弯曲度的过程进行说明。
如图6所示,在一些实施方式中,本公开示例的速度控制方法,确定移动设备当前沿目标路径移动时的转弯曲度的过程,包括:
S610、基于代价地图,确定移动设备前方预设范围内的第一参考线段和第二参考线段。
S620、根据第一参考线段和第二参考线段之间的夹角,确定移动设备当前的转弯曲度。
本公开实施方式中,基于代价地图,在移动设备前方预设范围中,对目标路径作两条间隔预设距离的法线段作为参考线段,分别定义为第一参考线段和第二参考线段。参见图7所示的代价地图进行说明,为便于清楚说明,将代价地图中的障碍物O 1~O 3进行了隐藏。
如图7所示,在移动设备600的前方预设范围400之内,分别对目标路径作两条法线段,也即第一参考线段K 1和第二参考线段K 2。第一参考线段K 1和第二参考线段K 2间隔预设距离d。可以理解,第一参考线段K 1和第二参考线段K 2的线段长度可以根据具体场景需求进行设置,本公开对此不作限制。
继续参考图7,假设移动设备600当前位置为S 0时,此时目标路径为直线,由于第一参考线段K 1和第二参考线段K 2均垂直于目标路径,从而第一参考线段K 1和第二参考线段K 2相互平行,两者不会相交,也就不会存在夹角。
而假设移动设备600当前位置为S 1时,此时前方目标路径为曲线,由于第一参考线段K 1和第二参考线段K 2始终垂直于目标路径,从而第一参考线段K 1和第二参考线段K 2将会相交,交点为Q,两者具有夹角θ。
另外,值得注意的是,由于第一参考线段K 1和第二参考线段K 2均为线段, 也即两者并非无限延长,因此,即使目标路径存在弯曲导致第一参考线段K 1和第二参考线段K 2不再平行,但是在曲率很小的情况下,第一参考线段K 1和第二参考线段K 2仍然不会相交。通过改变第一参考线段K 1和第二参考线段K 2之间预设距离d、以及线段长度,可以对两者端部相交时目标路径的曲率边界进行调整,本领域技术人员对此可以理解并充分实现,本公开不再赘述。
基于图7可知,本公开实施方式中,当第一参考线段与第二参考线段未相交时,说明预设范围内的目标路径为直线或者曲率较小,此时第一参考线段与第二参考线段没有夹角,定义目标路径的转弯曲度为零即可。
当第一参考线段与第二参考线段相交时,基于代价地图的坐标数据可以确定第一参考线段K 1和第二参考线段K 2的交点Q的位置坐标,在得到交点Q位置坐标之后,即可确定交点Q至目标路径的距离r,圆弧d为已知的预设距离,从而利用扇形公式即可确定第一参考线段K 1和第二参考线段K 2的夹角θ的值,表示为:θ=d/r。本公开实施方式中,即可将夹角θ的值确定移动设备当前的转弯曲度。
基于上述过程,可以确定移动设备当前位置与障碍物的目标距离和转弯曲度,然后根据目标距离和转弯曲度对移动设备的最大限速进行调整,下面具体进行说明。
如图8所示,在一些实施方式中,本公开示例的速度控制方法,根据目标距离、转弯曲度以及最大限速确定移动设备的目标速度的过程,包括:
S810、根据目标距离和最大限速确定移动设备的直行速度分量。
本公开实施方式中,在得到移动设备当前与障碍物的目标距离之后,即可根据目标距离的大小对最大限速进行适应性调整,得到直行速度分量。
具体而言,目标距离与直行速度分量正相关,也即,目标距离越大,说明移动设备当前与障碍物的距离越远,产生事故的风险越低,从而直行速度分量也越大。反之,目标距离越小,说明移动设备当前与障碍物的距离越近,产生事故的风险越高,从而直行速度分量也越小。
基于上述原理,本领域技术人员毫无疑问可以实现对直行速度分量的计算,本公开对计算方法不作具体限制。例如一些实施方式中,可以预先建立目标距离与直行速度分量的对应关系,通过查找该对应关系确定直行速度分 量的大小。
本公开一些实施方式中,如上文图5所述,目标距离包括第一距离L 1和第二距离L 2,从而,本公开实施方式的直行速度分量也包括第一速度分量和第二速度分量。下面结合图9实施方式进行说明。
如图9所示,在一些实施方式中,本公开示例的速度控制方法,根据目标距离确定直行速度分量的过程包括:
S811、根据第一距离和最大限速,确定移动设备的第一速度分量。
S812、根据第二距离和最大限速,确定移动设备的第二速度分量。
S813、根据第一速度分量和第二速度分量得到直行速度分量。
结合图4中所示,通过前述实施方式可以得到移动设备600与障碍物O 2的第一距离L 1,以及移动设备600与障碍物O 2的第二距离L 2。从而,第一速度分量和第二速度分量可表示为:
Figure PCTCN2022094525-appb-000001
Figure PCTCN2022094525-appb-000002
上式(1)和(2)中,V 1表示第一速度分量,V 2表示第二速度分量,L 1表示第一距离,L 2表示第二距离,R表示预设范围宽度的一半,P表示预设范围的长度,V max表示移动设备的最大限速。
结合图4所示,在预设范围内没有障碍物时,可设置第一距离L 1=R,第二距离L 2=P,此时第一速度分量V 1=V max,第二速度分量V 2=V max
基于上式(1)和(2),即可计算得到移动设备的第一速度分量V 1和第二速度分量V 2,然后将第一速度分量V 1和第二速度分量V 2确定为直行速度分量。
S820、根据转弯曲度和最大限速确定移动设备的转弯速度分量。
本公开实施方式中,在得到移动设备当前目标路径的转弯曲度之后,即可根据转弯曲度的大小对最大限速进行适应性调整,得到转弯速度分量。
具体而言,转弯曲度与转弯速度分量负相关,也即,转弯曲度越大,说明移动设备产生事故的风险越高,从而转弯速度分量应当越小。反之,转弯曲度越小,说明移动设备产生事故的风险越低,从而转弯速度分量也越大。
基于上述原理,在一些实施方式中,转弯速度分量的计算过程可表示为:
Figure PCTCN2022094525-appb-000003
上式(3)中,V 3表示转弯速度分量,θ表示转弯曲度,V max表示最大限速。
结合图7所示,当第一参考线段K 1和第二参考线段K 2没有交点时,可以设置转弯曲度θ为零,从而通过式(3)可知,此时转弯速度分量V 3=V max
S830、基于预先设置的直行速度权重和转弯速度权重,对直行速度分量和转弯速度分量进行加权融合处理,得到移动设备的目标速度。
可以理解,直行速度分量表示移动设备在当前路况下直行速度,转弯速度分量表示移动设备在当前路况下的转弯速度。本公开实施方式中,需要同时考虑到移动设备直行情况下与障碍物发生碰撞的风险,以及转弯情况下发生事故的风险,因此,可对直行速度分量和转弯速度分量进行加权融合处理,得到最终的目标速度。
在一些实施方式中,直行速度权重包括第一权重值a和第二权重值b,转弯速度权重包括第三权重值c,从而,目标速度可表示为:
V=a*V 1+b*V 2+c*V 3           (4)
上式(4)中,V表示目标速度,V 1表示第一速度分量,a表示第一速度分量的第一权重值,V 2表示第二速度分量,b表示第二速度分量的第二权重值,V 3表示转弯速度分量,c表示转弯速度分量的第三权重值。其中,a+b+c=1。
对于第一权重值a、第二权重值b以及第三权重值c的具体数值,本领域技术人员可以根据具体场景需求进行设置,本公开对此不作限制。
通过上式(4),可以对第一速度分量、第二速度分量以及转弯速度分量进行融合处理,得到移动设备对应的目标速度。
结合公式(1)至(4),分别以下面几种场景,对本公开实施方式方法的控制原理进行说明。
当移动设备沿直线移动或者转弯曲率很小,且移动设备前方预设范围内没有障碍物时,基于前述式(1)至(3)可以计算得到第一速度分量V 1=V max、第二速度分量V 2=V max以及转弯速度分量V 3=V max,代入式(4)即可得到目标速度V=V max,也即移动设备保持最大限速运行。
当移动设备沿直线移动或者转弯曲率很小,且移动设备前方预设范围内存在障碍物时,基于前述公式(3)可以计算得到转弯速度分量V 3=V max,而第第一速度分量V 1和第二速度分量V 2均小于V max,代入式(4)得到的目标速度V也应当小于V max,也即对移动设备的速度进行自适应降低。
当移动设备沿曲线移动,且移动设备前方预设范围内没有障碍物时,基 于前述公式(1)和(2)可以计算得到第一速度分量V 1=V max、第二速度分量V 2=V max,基于式(3)计算得到转弯速度分量V 3小于V max,代入式(4)得到的目标速度V也应当小于V max,也即对移动设备的速度进行自适应降低。
当移动设备沿曲线移动,且移动设备前方预设范围内存在障碍物时,基于前述式(1)至(3)可以计算得到第一速度分量V 1、第二速度分量V 2以及转弯速度分量V 3均小于V max,代入式(4)得到的目标速度V也应当小于V max,也即对移动设备的速度进行自适应降低。
基于上述场景可以看到,本公开实施方式中,不仅基于移动设备与障碍物的距离来调整移动设备速度,还进一步结合转弯曲率来调整移动设备速度,移动设备在转弯过程中,即使前方不存在障碍物,依旧会对移动设备速度进行降低,避免由于转弯速度过快导致的倾覆,或者降低由于转弯视野盲区导致的事故风险。
在一些实施方式中,为保证移动设备的正常运行作业,可以预先设置移动设备的预设速度范围,该预设速度范围可限制移动设备的最低限速V min和最大限速V max,也即移动设备的运动速度应当位于预设速度范围[V min,V max]中。
当通过前述方法过程得到的目标速度小于最低限速V min时,可以控制移动设备以最低限速V min移动。当目标速度大于最大限速V max时,可以控制移动设备以最大限速V max移动。当目标速度位于预设速度范围[V min,V max]中时,可以控制移动设备以目标速度移动。
对于预设速度范围[V min,V max]的具体取值,本领域技术人员可以根据具体的应用场景进行设置,本公开对此不作限制。
通过上述可知,本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,避免由于转弯速度过快导致的倾覆,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
第二方面,本公开实施方式提供了一种速度控制装置,该装置可应用于移动设备中。本公开实施方式的移动设备,可以是任何适于实施的具有自 主运动能力的设备类型,例如扫地机器人、物流机器人、送餐机器人、智能移动垃圾桶等,本公开对此不作限制。
如图10所示,在一些实施方式中,本公开示例的速度控制装置,包括:
获取模块10,被配置为获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径;
第一确定模块20,被配置为基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,以及所述移动设备当前沿所述目标路径移动时的转弯曲度;
第二确定模块30,被配置为根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度;
控制模块40,被配置为控制所述移动设备以所述目标速度移动。
通过上述可知,本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
在一些实施方式中,所述获取模块10被配置为:
获取通过所述移动设备的传感器采集到的所述移动区域的场景数据;
根据所述场景数据对所述移动设备进行定位与建图,得到所述移动设备的当前位置和环境地图;
根据所述环境地图中障碍物信息得到所述移动区域的代价地图,并根据所述代价地图和所述当前位置确定所述移动设备的所述目标路径。
在一些实施方式中,所述第一确定模块20,被配置为:
基于所述代价地图,确定所述移动设备前方预设范围内的障碍物数据;
根据所述障碍物数据,确定障碍物与所述目标路径的第一距离,以及所述障碍物与所述移动设备当前位置的第二距离;其中,所述第一距离垂直于所述目标路径,所述第二距离平行于所述目标路径;
根据所述第一距离和所述第二距离得到所述目标距离。
在一些实施方式中,所述第一确定模块20,被配置为:
基于所述代价地图,确定所述移动设备前方预设范围内的第一参考线 段和第二参考线段;其中,所述第一参考线段和所述第二参考线段均垂直于所述目标路径,且所述第一参考线段和所述第二参考线段之间间隔预设距离;
根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度。
在一些实施方式中,所述第一确定模块20,被配置为:
响应于所述第一参考线段与所述第二参考线段相交,基于所述代价地图确定所述第一参考线段与所述第二参考线段的交点坐标,并根据所述交点坐标以及所述预设距离确定所述第一参考线段与所述第二参考线段之间的夹角,将所述夹角确定为所述转弯曲度;
响应于所述第一参考线段与所述第二参考线段未相交,确定所述转弯曲度为零。
在一些实施方式中,所述第二确定模块30,被配置为:
根据所述目标距离和所述最大限速确定所述移动设备的直行速度分量;其中,所述直行速度分量与所述目标距离正相关;
根据所述转弯曲度和所述最大限速确定所述移动设备的转弯速度分量;其中,所述转弯速度分量与所述转弯曲度负相关;
基于预先设置的直行速度权重和转弯速度权重,对所述直行速度分量和所述转弯速度分量进行加权融合处理,得到所述移动设备的目标速度。
在一些实施方式中,所述第二确定模块30,被配置为:
根据所述第一距离和所述最大限速,确定所述移动设备的第一速度分量;
根据所述第二距离和所述最大限速,确定所述移动设备的第二速度分量;
根据所述第一速度分量和所述第二速度分量得到所述直行速度分量。
在一些实施方式中,所述控制模块40,被配置为:
响应于所述目标速度满足预设速度范围,控制所述移动设备以所述目标速度移动。
通过上述可知,本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降 低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,避免由于转弯速度过快导致的倾覆,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
第三方面,本公开实施方式提供了一种移动设备,包括:
处理器;和
存储器,存储有计算机指令,所述计算机指令用于使处理器执行根据第一方面任意实施方式所述的方法。
第四方面,本公开实施方式提供了一种存储介质,存储有计算机指令,所述计算机指令用于使计算机执行根据第一方面任意实施方式所述的方法。
通过上述可知,本公开实施方式中,通过移动设备与障碍物的目标距离和转弯曲度控制当前移动速度,可以根据当前路况自适应调整移动速度,降低事故风险,并且,在速度控制时,不仅考虑移动设备与障碍物之间的目标距离,还结合移动设备自身的目标路径的弯曲程度,避免由于转弯速度过快导致的倾覆,降低由于转弯处视野盲区导致的事故风险,进一步提高速度控制效果。
显然,上述实施方式仅仅是为清楚地说明所作的举例,而并非对实施方式的限定。对于所属领域的普通技术人员来说,在上述说明的基础上还可以做出其它不同形式的变化或变动。这里无需也无法对所有的实施方式予以穷举。而由此所引伸出的显而易见的变化或变动仍处于本公开创造的保护范围之中。

Claims (11)

  1. 一种速度控制方法,其特征在于,应用于移动设备,所述方法包括:
    获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径;
    基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,以及所述移动设备当前沿所述目标路径移动时的转弯曲度;
    根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度;
    控制所述移动设备以所述目标速度移动。
  2. 根据权利要求1所述的方法,其特征在于,所述获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径,包括:
    获取通过所述移动设备的传感器采集到的所述移动区域的场景数据;
    根据所述场景数据对所述移动设备进行定位与建图,得到所述移动设备的当前位置和环境地图;
    根据所述环境地图中障碍物信息得到所述移动区域的代价地图,并根据所述代价地图和所述当前位置确定所述移动设备的所述目标路径。
  3. 根据权利要求1所述的方法,其特征在于,基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,包括:
    基于所述代价地图,确定所述移动设备前方预设范围内的障碍物数据;
    根据所述障碍物数据,确定障碍物与所述目标路径的第一距离,以及所述障碍物与所述移动设备当前位置的第二距离;其中,所述第一距离垂直于所述目标路径,所述第二距离平行于所述目标路径;
    根据所述第一距离和所述第二距离得到所述目标距离。
  4. 根据权利要求1所述的方法,其特征在于,基于所述代价地图,确定所述移动设备当前沿所述目标路径移动时的转弯曲度,包括:
    基于所述代价地图,确定所述移动设备前方预设范围内的第一参考线段和第二参考线段;其中,所述第一参考线段和所述第二参考线段均垂直 于所述目标路径,且所述第一参考线段和所述第二参考线段之间间隔预设距离;
    根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度。
  5. 根据权利要求4所述的方法,其特征在于,所述根据所述第一参考线段和所述第二参考线段之间的夹角,确定所述移动设备当前的所述转弯曲度,包括:
    响应于所述第一参考线段与所述第二参考线段相交,基于所述代价地图确定所述第一参考线段与所述第二参考线段的交点坐标,并根据所述交点坐标以及所述预设距离确定所述第一参考线段与所述第二参考线段之间的夹角,将所述夹角确定为所述转弯曲度;
    响应于所述第一参考线段与所述第二参考线段未相交,确定所述转弯曲度为零。
  6. 根据权利要求1所述的方法,其特征在于,所述根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度,包括:
    根据所述目标距离和所述最大限速确定所述移动设备的直行速度分量;其中,所述直行速度分量与所述目标距离正相关;
    根据所述转弯曲度和所述最大限速确定所述移动设备的转弯速度分量;其中,所述转弯速度分量与所述转弯曲度负相关;
    基于预先设置的直行速度权重和转弯速度权重,对所述直行速度分量和所述转弯速度分量进行加权融合处理,得到所述移动设备的目标速度。
  7. 根据权利要求6所述的方法,其特征在于,所述目标距离包括垂直于所述目标路径的第一距离和平行于所述目标路径的第二距离;所述根据所述目标距离确定所述移动设备的直行速度分量,包括:
    根据所述第一距离和所述最大限速,确定所述移动设备的第一速度分量;
    根据所述第二距离和所述最大限速,确定所述移动设备的第二速度分量;
    根据所述第一速度分量和所述第二速度分量得到所述直行速度分量。
  8. 根据权利要求1所述的方法,其特征在于,所述控制所述移动设备以所述目标速度移动,包括:
    响应于所述目标速度满足预设速度范围,控制所述移动设备以所述目标速度移动。
  9. 一种速度控制装置,其特征在于,应用于移动设备,所述装置包括:
    获取模块,被配置为获取移动区域的代价地图以及所述移动设备在所述移动区域中移动的目标路径;
    第一确定模块,被配置为基于所述代价地图,确定所述移动设备当前与障碍物的目标距离,以及所述移动设备当前沿所述目标路径移动时的转弯曲度;
    第二确定模块,被配置为根据所述目标距离、所述转弯曲度以及所述移动设备的最大限速,确定所述移动设备的目标速度;
    控制模块,被配置为控制所述移动设备以所述目标速度移动。
  10. 一种移动设备,其特征在于,包括:
    处理器;和
    存储器,存储有计算机指令,所述计算机指令用于使处理器执行根据权利要求1至8任一项所述的方法。
  11. 一种存储介质,其特征在于,存储有计算机指令,所述计算机指令用于使计算机执行根据权利要求1至8任一项所述的方法。
PCT/CN2022/094525 2022-05-23 2022-05-23 移动设备及其速度控制方法、装置、存储介质 WO2023225812A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/CN2022/094525 WO2023225812A1 (zh) 2022-05-23 2022-05-23 移动设备及其速度控制方法、装置、存储介质
CN202280004174.8A CN117480463A (zh) 2022-05-23 2022-05-23 移动设备及其速度控制方法、装置、存储介质
EP22938741.0A EP4318162A4 (en) 2022-05-23 2022-05-23 MOBILE DEVICE AND SPEED CONTROL METHOD AND DEVICE THEREFOR, AND STORAGE MEDIUM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/094525 WO2023225812A1 (zh) 2022-05-23 2022-05-23 移动设备及其速度控制方法、装置、存储介质

Publications (1)

Publication Number Publication Date
WO2023225812A1 true WO2023225812A1 (zh) 2023-11-30

Family

ID=88918174

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/094525 WO2023225812A1 (zh) 2022-05-23 2022-05-23 移动设备及其速度控制方法、装置、存储介质

Country Status (3)

Country Link
EP (1) EP4318162A4 (zh)
CN (1) CN117480463A (zh)
WO (1) WO2023225812A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016024766A (ja) * 2014-07-24 2016-02-08 日本精工株式会社 案内用ロボット
CN106325275A (zh) * 2016-09-14 2017-01-11 广州今甲智能科技有限公司 一种机器人导航的系统、方法及装置
CN107421538A (zh) * 2016-05-23 2017-12-01 华硕电脑股份有限公司 导航系统及导航方法
CN109212973A (zh) * 2018-11-05 2019-01-15 北京交通大学 一种基于强化学习的仿人智能控制的避障控制方法
CN112445222A (zh) * 2019-09-05 2021-03-05 阿里巴巴集团控股有限公司 导航方法、装置、存储介质以及终端

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0778507B1 (de) * 1995-12-04 2002-02-27 Volkswagen Aktiengesellschaft Verfahren zur Geschwindigkeitsregelung eines Kraftfahrzeuges
US10429847B2 (en) * 2017-09-22 2019-10-01 Locus Robotics Corp. Dynamic window approach using optimal reciprocal collision avoidance cost-critic

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016024766A (ja) * 2014-07-24 2016-02-08 日本精工株式会社 案内用ロボット
CN107421538A (zh) * 2016-05-23 2017-12-01 华硕电脑股份有限公司 导航系统及导航方法
CN106325275A (zh) * 2016-09-14 2017-01-11 广州今甲智能科技有限公司 一种机器人导航的系统、方法及装置
CN109212973A (zh) * 2018-11-05 2019-01-15 北京交通大学 一种基于强化学习的仿人智能控制的避障控制方法
CN112445222A (zh) * 2019-09-05 2021-03-05 阿里巴巴集团控股有限公司 导航方法、装置、存储介质以及终端

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4318162A4 *

Also Published As

Publication number Publication date
EP4318162A1 (en) 2024-02-07
CN117480463A (zh) 2024-01-30
EP4318162A4 (en) 2024-06-12

Similar Documents

Publication Publication Date Title
US10591926B2 (en) Smooth road reference for autonomous driving vehicles based on 2D constrained smoothing spline
US10606277B2 (en) Speed optimization based on constrained smoothing spline for autonomous driving vehicles
JP4037722B2 (ja) 車外監視装置、及び、この車外監視装置を備えた走行制御装置
WO2018209864A1 (zh) 移动控制方法、装置、机器人及存储介质
US20190266779A1 (en) Analysis of point cloud data using polar depth maps and planarization techniques
JP4682973B2 (ja) 移動経路作成方法、自律移動体および自律移動体制御システム
EP4296133A1 (en) Intelligent driving method and apparatus, and storage medium and computer program
JP7346499B2 (ja) 情報処理装置、情報処理方法、およびプログラム
JP7082940B2 (ja) 走行軌道決定処理及び自動運転装置
US20140207325A1 (en) Efficient data flow algorithms for autonomous lane changing, passing and overtaking behaviors
JP4670807B2 (ja) 移動経路作成方法、自律移動体および自律移動体制御システム
WO2023024503A1 (zh) 应用于垂直车位的泊车控制方法、电子设备、车辆及存储介质
JP2018112989A (ja) 運転補助装置及び運転補助方法
CN117184060B (zh) 轨迹修正方法和装置、无人车和存储介质
US11724717B2 (en) Implementation of dynamic cost function of self-driving vehicles
JP2009080527A (ja) 自律移動装置
CN114610042A (zh) 机器人路径动态规划方法、装置及机器人
CN115328153A (zh) 传感器数据处理方法、系统及可读存储介质
JP2021041754A (ja) 運転制御方法及び運転制御装置
WO2023225812A1 (zh) 移动设备及其速度控制方法、装置、存储介质
CN107479561B (zh) 一种控制机器人的方法
JP2012168990A (ja) 自律移動装置
CN115919214A (zh) 清扫机器人的控制方法、机器人及计算机可读存储介质
US20210074037A1 (en) Dynamic parameter architecture for qp smoother
JP7258677B2 (ja) 運転制御方法及び運転制御装置

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280004174.8

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 2022938741

Country of ref document: EP

Effective date: 20231102