CN112068553A - Robot obstacle avoidance processing method and device and robot - Google Patents

Robot obstacle avoidance processing method and device and robot Download PDF

Info

Publication number
CN112068553A
CN112068553A CN202010843699.3A CN202010843699A CN112068553A CN 112068553 A CN112068553 A CN 112068553A CN 202010843699 A CN202010843699 A CN 202010843699A CN 112068553 A CN112068553 A CN 112068553A
Authority
CN
China
Prior art keywords
obstacle
positioning
image
sensing module
determining
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202010843699.3A
Other languages
Chinese (zh)
Inventor
张晓龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Jiangge Robot Co Ltd
Original Assignee
Shanghai Jiangge Robot Co Ltd
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 Shanghai Jiangge Robot Co Ltd filed Critical Shanghai Jiangge Robot Co Ltd
Priority to CN202010843699.3A priority Critical patent/CN112068553A/en
Priority to JP2020193589A priority patent/JP6884312B1/en
Publication of CN112068553A publication Critical patent/CN112068553A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0259—Control of position or course in two dimensions specially adapted to land vehicles using magnetic or electromagnetic means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

The embodiment of the specification provides a robot obstacle avoidance processing method, a robot obstacle avoidance processing device and a robot, wherein the robot obstacle avoidance processing method comprises the following steps: acquiring an environment image acquired by an image sensing module; identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles; judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module; and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.

Description

Robot obstacle avoidance processing method and device and robot
Technical Field
The present document relates to the field of robot technologies, and in particular, to a robot obstacle avoidance processing method, an apparatus, and a robot.
Background
With the development of the robot technology, the working environment of the robot is more and more complicated, and in the complicated and variable and unpredictable working environment, the task to be completed by the robot is more and more complicated, and meanwhile, the requirement of the user on the robot is continuously enhanced.
For the robot, the processing of obstacle avoidance planning in the working process is a very basic and very critical task, taking the robot in the storage environment as an example, when the robot executes an order task, the robot needs to pass through between warehouse shelves according to instructions, and in the running process, not only moving obstacles such as a moving picker, other robots and the like but also fixed obstacles such as a shelf, a wall and the like exist around the robot, but in the working and running process of the robot, how to make a judgment in time to avoid collision of the robot is also a difficult point for the robot to execute the order task.
Disclosure of Invention
One or more embodiments of the present specification provide a robot obstacle avoidance processing method. The robot obstacle avoidance processing method comprises the following steps:
acquiring an environment image acquired by an image sensing module;
identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles;
judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module; and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
Optionally, the identifying an obstacle in the environment image includes:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
Optionally, the determining a location sensing module for locating the obstacle includes:
if the type of the obstacle is a fixed obstacle, determining the image sensing module as a positioning sensing module for positioning the obstacle; the image sensing module includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
if the type of the obstacle is a moving obstacle, determining a depth image sensor and the image sensing module as a positioning sensing module for positioning the obstacle;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area; and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not;
if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle;
if not, determining the image sensing module as a positioning sensing module for positioning the obstacle; wherein the image sensing module comprises: monocular camera.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area; and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance according to the corresponding relation between the distance and the positioning sensing module, which is established in advance, as a positioning sensing module for positioning the obstacle.
Optionally, the obstacle avoidance processing method for the robot further includes:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance;
if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
Optionally, the obstacle avoidance processing performed on the position information determined based on the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
Optionally, the planning a driving route based on the position information includes:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
Optionally, after the step of acquiring the environmental image collected by the image sensing module is executed, and before the step of identifying the obstacle in the environmental image and determining the positioning sensing module for positioning the obstacle is executed, the method further includes:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle; and if so, executing the steps of identifying the obstacles in the environment image and determining a positioning sensing module for positioning the obstacles.
One or more embodiments of the present specification further provide a robot obstacle avoidance processing apparatus, including:
the environment image acquisition module is configured to acquire an environment image acquired by the image sensing module;
an obstacle identification module configured to identify an obstacle in the environment image and determine a positioning sensing module that positions the obstacle;
the obstacle judging module is configured to judge whether the obstacle is in a target obstacle area or not based on the positioning characteristic information acquired by the positioning sensing module;
if so, operating an obstacle avoidance processing module; and the obstacle avoidance processing module is configured to perform obstacle avoidance processing based on the position information determined by the positioning characteristic information.
One or more embodiments of the present specification further provide a robot including:
the system comprises a processor, an image sensing module and a positioning sensing module;
wherein the image sensing module is configured to acquire an environmental image;
the processor is configured to acquire an environment image acquired by the image sensing module, identify an obstacle in the environment image, judge whether the obstacle is in a target obstacle area based on positioning feature information acquired by the positioning sensing module, and if so, perform obstacle avoidance processing based on position information determined by the positioning feature information;
the location sensing module is determined by the processor and is configured to locate the obstacle.
Optionally, the identifying an obstacle in the environment image includes:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
Optionally, if the type of the obstacle is a fixed obstacle, determining the image sensing module as the positioning sensing module; the image sensing module includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, if the type of the obstacle is a moving obstacle, determining the depth image sensor and the image sensing module as the positioning sensing module;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, the processor determines the location sensing module by performing the following operations:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not; if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle;
if not, determining the image sensing module as a positioning sensing module for positioning the obstacle; wherein the image sensing module comprises: monocular camera.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area; if yes, executing the next step.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, the processor determines the location sensing module by performing the following operations:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance as the positioning sensing module according to the corresponding relation between the distance and the positioning sensing module established in advance.
Optionally, the processor is further configured to:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance; if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
Optionally, the obstacle avoidance processing performed on the position information determined based on the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
Optionally, the planning a driving route based on the position information includes:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
Optionally, the processor is further configured to:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle; if yes, the next step.
One or more embodiments of the present specification also provide a storage medium storing computer-executable instructions that, when executed, implement the following:
acquiring an environment image acquired by an image sensing module;
identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles;
judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module;
and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
Drawings
In order to more clearly illustrate one or more embodiments or technical solutions in the prior art in the present specification, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise;
fig. 1 is a processing flow diagram of a robot obstacle avoidance processing method according to one or more embodiments of the present disclosure;
fig. 2 is a processing flow diagram of a robot obstacle avoidance processing method applied to a warehousing scene according to one or more embodiments of the present disclosure;
fig. 3 is a schematic diagram of a robot obstacle avoidance processing apparatus according to one or more embodiments of the present disclosure;
fig. 4 is a schematic structural diagram of a robot according to one or more embodiments of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.
The embodiment of the robot obstacle avoidance processing method provided by the specification comprises the following steps:
referring to fig. 1, a processing flow chart of a robot obstacle avoidance processing method provided by the present embodiment is shown, and referring to fig. 2, a processing flow chart of a robot obstacle avoidance processing method applied to a warehousing scene provided by the present embodiment is shown.
Referring to fig. 1, the robot obstacle avoidance processing method provided in this embodiment specifically includes the following steps S102 to S108.
And S102, acquiring an environment image acquired by the image sensing module.
The robot obstacle avoidance processing method provided by the specification includes the steps that an environment image of a working environment where a robot is located is collected through an image sensing module, a positioning sensing module for positioning an obstacle is determined according to the type of the obstacle, the height of the obstacle or the distance between the obstacle and the robot under the condition that the obstacle included in the environment image is identified, so that different positioning sensing modules are adopted for more accurate positioning according to different obstacle situations, after the obstacle is positioned, whether the obstacle is located in a target obstacle area influencing the work of the robot is further judged, if the obstacle is located in the target obstacle area, obstacle avoidance processing is conducted on the robot according to the position information of the obstacle, and the work of the robot is guaranteed to be conducted smoothly.
The image sensor in this embodiment refers to an image sensor configured for the robot itself, such as a monocular camera configured for the robot. The image of the working environment of the robot acquired by the image sensor is the environment image, and the purpose of acquiring the environment image is to detect an obstacle in the running process of the robot, so the environment image acquired by the image sensor is the environment image of the working environment area in front of the running route of the robot.
In addition, the image sensor can also be a movable camera which is arranged in the working environment of the robot and works in cooperation with the robot, or a plurality of fixed cameras which are arranged at different positions in the working environment of the robot and are mutually matched.
In practical application, in order to improve timeliness and accuracy of a robot for detecting an obstacle, the adopted method is often to improve the acquisition frequency of an image sensor configured for the robot, and the robot is prevented from colliding with the obstacle in a working environment through higher-frequency image acquisition and obstacle detection positioning, but the high-frequency image acquisition and obstacle detection positioning identification can bring processing pressure to the robot; if yes, executing the following step S104; if not, the fact that no obstacle exists in the environment image acquired by the image sensor configured in the robot currently, namely the robot is in the current working environment without the obstacle affecting the driving of the robot, is indicated, and the obstacle is not processed.
And step S104, identifying obstacles in the environment image, and determining a positioning sensing module for positioning the obstacles.
On the basis of the environment image acquired by the image acquisition module, the obstacle in the environment image is identified. Or recognizing the obstacle when it is detected that the obstacle is included in the environment image. Specifically, in the identification process, the environment image is input into an image identification model, the image identification model carries out feature segmentation and feature identification on the environment image, and the obstacle type of an obstacle contained in the environment image is output.
For example, in order to improve the recognition efficiency and the recognition accuracy, an image recognition model adopting a YOLO algorithm is trained, and the image recognition model is used for recognizing obstacles in the acquired environment image. In the process of identifying an obstacle in an environment image, the image identification model often needs to perform feature segmentation before identification, that is: segmenting obstacle features from the complex image features of the environment image, and identifying obstacles by using the obstacle features obtained by feature segmentation; in consideration of efficiency improvement, a module for performing feature segmentation on the environment image can be added to the image recognition model, and the obstacle features output by the module are used as input for subsequent obstacle recognition, so that the environment image is input into the image recognition model to perform feature segmentation and obstacle recognition, and the types of obstacles obtained through recognition, such as human legs (order pickers), robots, charging piles, shelves, walls and the like, are output.
The positioning sensing module in this embodiment refers to a sensor used for positioning in a sensor configured in a robot. For example, the robot is provided with a monocular camera, a depth camera and an infrared sensor, and if the robot is positioned according to an environment image acquired by the monocular camera in the positioning process, the monocular camera is determined as a positioning sensing module; similarly, if positioning is performed according to the depth image acquired by the depth camera or the position data acquired by the infrared sensor in the positioning process, the depth camera or the infrared sensor is determined as the positioning sensing module.
In practical applications, various types of obstacles may exist in a robot work environment, such as a picker, other robots, and other moving obstacles, and fixed obstacles such as a shelf and a wall also exist, and based on different characteristics of different types of obstacles, in an optional implementation provided by this embodiment, the corresponding positioning sensing module is determined according to the type of the obstacle, that is, the obstacle is positioned by selecting a corresponding positioning manner according to the type of the obstacle, so as to improve the accuracy of positioning the obstacle.
Specifically, if the type of the obstacle output by the image recognition model is a fixed obstacle, the image sensing module is determined as a positioning sensing module for positioning the obstacle. For example, for fixed obstacles such as a shelf, a wall, and the like, a monocular camera which previously collects an environmental image is still used as a positioning sensing module for positioning the obstacle, that is, the obstacle is positioned according to the environmental image collected by the monocular camera.
And if the type of the obstacle is a moving obstacle, determining the depth image sensor and the image sensing module as a positioning sensing module for positioning the obstacle. For example, for a picking man or other robots, the obstacle is positioned by matching a depth camera and a monocular camera configured by the robots, that is, the obstacle is positioned by combining a depth image acquired by the depth camera and an environment image acquired by the monocular camera.
In specific implementation, considering that the heights of obstacles in many scenes have certain influence on the identification and positioning of the obstacles, for example, the heights of sorting robots in storage scenes are relatively low, and accordingly, the visual field ranges of image sensors arranged on the sorting robots may also be relatively low, for this reason, in an optional implementation manner provided in this embodiment, corresponding positioning sensing modules are determined according to the heights of the obstacles, so that different positioning manners are adopted for the obstacles with different heights, so as to improve the accuracy of positioning the obstacles, and the following is specifically implemented:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not;
if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle;
if not, the image sensing module is determined as a positioning sensing module for positioning the obstacle.
For example, in an environment image of a working environment collected by a sorting robot in a warehousing scene, if the height ratio of an image feature of a certain obstacle (a shelf) in the environment image exceeds 1/2, it indicates that the height of the obstacle, namely the shelf in front of the warehousing robot, is higher, and in this case, the obstacle, namely the shelf, is more accurately positioned by adopting a radio detection and ranging sensor (radar), an ultrasonic sensor or an infrared sensor; if the height ratio of a certain obstacle (other sorting robots) is lower than 1/2, the height of the obstacle of the sorting robot in front of the warehousing robot is low, and the robot is still used for positioning.
In addition, in a specific implementation, considering that distances between an obstacle and a robot in many scenes may also have a certain influence on the identification and positioning of the obstacle, in an optional implementation manner provided in this embodiment, a corresponding positioning manner is selected according to the distance between the obstacle, so as to improve the accuracy of positioning the obstacle, specifically, an initial distance corresponding to the obstacle is calculated according to the environment image, and then a first positioning sensing module corresponding to the initial distance is determined according to a pre-established correspondence relationship between the distance and the positioning sensing module, and is used as a positioning sensing module for positioning the obstacle.
For example, when the distance between the obstacle and the robot is greater than 6m, the corresponding positioning sensing module is a radio detection and ranging sensor (radar), an ultrasonic sensor or an infrared sensor and other long-distance detection sensors; when the distance between the obstacle and the robot is smaller than or equal to 6m, the corresponding positioning sensing module is a depth camera, under the condition, the obstacle can be positioned according to the depth image acquired by the depth camera, and the obstacle with higher precision can be positioned by combining the depth image and the environment image acquired by the monocular camera.
It should be noted that, at different stages of obstacle avoidance processing on the same obstacle, the accuracy of positioning the obstacle by using different positioning sensing modules may be higher, and in order to further enhance the positioning accuracy of the robot in the working and driving process, the embodiment further provides switching operation of the positioning sensing modules, specifically, a second distance corresponding to the obstacle is calculated based on the positioning feature information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance, and on this basis, it is determined whether the second positioning sensing module corresponding to the second distance in the corresponding relationship between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance; if yes, no treatment is needed; if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
And step S106, judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module.
On the basis that the positioning sensing module is determined in the step S104, it is determined whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the determined positioning sensing module; if yes, executing step S108, and performing obstacle avoidance processing based on the position information determined by the positioning feature information; if not, the obstacle is not in the target obstacle area of the robot, and the robot is not processed.
It should be noted that the positioning feature information acquired by the positioning sensing module may be the positioning feature information acquired by the determined positioning sensor after the positioning sensor is determined, for example, if the determined positioning sensing module is a depth camera, the positioning feature information acquired by the positioning sensing module is a depth image acquired by the depth camera; for example, if the determined positioning sensing module is a monocular camera, the positioning characteristic information acquired by the positioning sensing module is an environment image acquired by the monocular camera, and the environment image may be an environment image acquired before the monocular camera is determined as the positioning sensing module, or an environment image acquired again after the monocular camera is determined as the positioning sensing module.
The target obstacle area in this embodiment refers to a specific area in front of the robot in the space dimension, for example, a rectangular area with a width of 0.7m and a length of 1.2m in front of the robot is designated as the target obstacle area. In addition, the target obstacle area may also be a specific area in the image dimension. For example, a rectangular area or a fan-shaped area in an environment image acquired by a monocular camera is designated as a target obstacle area, or a rectangular area or a fan-shaped area in a depth image acquired by a depth camera is designated as a target obstacle area.
Corresponding to the implementation mode of determining the positioning sensing module according to the type of the obstacle, if the type of the obstacle output by the image recognition model is a fixed obstacle, after determining the image sensing module as the positioning sensing module for positioning the obstacle, judging whether the obstacle is in a target obstacle area by adopting the following mode:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area;
if yes, executing the following step S108, and carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information;
if not, the obstacle is not in the target obstacle area of the robot, and the robot is not processed.
Similarly, if the type of the obstacle output by the image recognition model is a moving obstacle, after the image sensing module is determined as a positioning sensing module for positioning the obstacle, whether the obstacle is in the target obstacle area is determined in the following way:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
then judging whether the image coordinate position is in the target image area;
if yes, executing the following step S108, and carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information;
if not, the obstacle is not in the target obstacle area of the robot, and the robot is not processed.
In addition, corresponding to the implementation manner of determining the corresponding positioning sensing module according to the height of the obstacle, if the determined positioning sensing module is a radio sensor, the following manner is adopted to judge whether the obstacle is in the target obstacle area:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area;
if yes, executing the following step S108, and carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information;
if not, the obstacle is not in the target obstacle area of the robot, and the robot is not processed.
Similarly, if the determined positioning sensing module is an image sensor, the following method is adopted to determine whether the obstacle is in the target obstacle area:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area;
if yes, executing the following step S108, and carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information;
if not, the obstacle is not in the target obstacle area of the robot, and the robot is not processed.
And S108, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
The precondition for implementing this step is that the determination result of determining whether the obstacle is in the target obstacle area in step S106 is yes, specifically, in the process of performing obstacle avoidance processing based on the position information determined by the positioning feature information, a driving instruction for deceleration driving is first generated and executed, then a driving route is planned based on the position information, and the original driving route is updated based on the driving route.
In practical applications, various complex situations often exist in the working scene of the robot, for example, a warehousing scene, the volume of goods placed on the sorting robot may be larger than that of the sorting robot, and although the sorting robots do not collide with obstacles, the goods placed on the sorting robot may collide with the obstacles or collide with the obstacles. For such a situation, in the process of planning a driving route, according to the environment image, the maximum obstacle contour of the obstacle is determined, and the driving route is planned based on the maximum obstacle contour and the position information, so that the driving width of the driving route is larger than the maximum obstacle contour value, thereby reducing the probability of collision with the obstacle in the driving process of the robot, and improving the capability of the robot in dealing with complex scenes.
The following takes an application of the robot obstacle avoidance processing method provided in this embodiment in a warehousing scene as an example, and further describes the robot obstacle avoidance processing method provided in this embodiment, referring to fig. 2, the robot obstacle avoidance processing method applied in the warehousing scene specifically includes steps S202 to S226.
And step S202, acquiring an environment image acquired by a monocular camera configured by the sorting robot.
Besides, the monocular camera can also be a movable camera which is arranged in the working environment where the sorting robot is located and works in cooperation with the sorting robot, or a plurality of fixed cameras which are arranged in different positions in the working environment of the sorting robot and are matched with each other.
Step S204, detecting the characteristics of the target object contained in the environment image.
Step S206 detects whether the target object feature is an obstacle.
If the detection result of the target object feature indicates that the target object feature is an obstacle, the following step S208 is executed; otherwise, it indicates that no obstacle exists in the environment image acquired by the monocular camera configured for the current sorting robot, that is, the current working environment of the sorting robot has no obstacle affecting the running of the sorting robot, and the sorting robot is not processed.
Step S208 is to perform feature segmentation and feature recognition on the environment image input image recognition model, and output the obstacle type of the obstacle included in the environment image.
And step S210, if the type of the obstacle is a fixed obstacle, determining the monocular camera as a positioning sensing module for positioning the obstacle.
In step S212, a spatial coordinate position corresponding to the obstacle is determined based on the environment image.
Step S214, judging whether the space coordinate position is in the space obstacle area; if yes, go to step S224; if not, the processing is not required.
And S216, if the type of the obstacle is a moving obstacle, determining the depth camera and the monocular camera as positioning sensing modules for positioning the obstacle.
And step S218, determining the image coordinate position of the obstacle in the fused image based on the environment image and the depth image acquired by the depth camera. The fusion image is obtained by fusing the environment image and the depth image.
Step S220 is to determine a target image region corresponding to the preset reference image region in the fused image.
Step S222, judging whether the image coordinate position is in the target image area; if yes, go to step S224; if not, the processing is not required.
In step S224, a travel command for deceleration travel is generated and executed.
In step S226, a driving route is planned based on the position information and a route update is performed for the sorting robot.
The robot obstacle avoidance processing device provided by the specification comprises the following embodiments:
in the above embodiment, a robot obstacle avoidance processing method is provided, and correspondingly, a robot obstacle avoidance processing device is also provided, which is described below with reference to the accompanying drawings.
Referring to fig. 3, a schematic diagram of a robot obstacle avoidance processing device according to the present embodiment is shown.
Since the device embodiments correspond to the method embodiments, the description is relatively simple, and the relevant portions may refer to the corresponding description of the method embodiments provided above. The device embodiments described below are merely illustrative.
The embodiment provides an obstacle avoidance processing device for a robot, which comprises:
an environment image acquisition module 302 configured to acquire an environment image acquired by the image sensing module;
an obstacle identification module 304 configured to identify an obstacle in the environment image and determine a location sensing module that locates the obstacle;
an obstacle judging module 306 configured to judge whether the obstacle is in a target obstacle area based on the positioning feature information acquired by the positioning sensing module;
if yes, operating an obstacle avoidance processing module 308; the obstacle avoidance processing module 308 is configured to perform obstacle avoidance processing based on the position information determined by the positioning feature information.
Optionally, the obstacle identifying module 304 includes:
and the recognition submodule is configured to input the environment image into an image recognition model, perform feature segmentation and feature recognition on the environment image by the image recognition model, and output the obstacle type of the obstacle contained in the environment image.
Optionally, the obstacle identifying module 304 includes:
a first determination submodule configured to determine the image sensing module as a positioning sensing module that positions the obstacle, in a case where the obstacle type is a fixed obstacle; the image sensing module includes: a monocular camera;
correspondingly, the obstacle determining module 306 is specifically configured to determine, based on the environment image, an image coordinate position corresponding to the obstacle, and determine a target image area corresponding to a preset reference image area in the environment image; judging whether the image coordinate position is in the target image area; if yes, the obstacle avoidance processing module 308 is operated.
Optionally, the obstacle identifying module 304 includes:
a second determination submodule configured to determine the depth image sensor and the image sensing module as a positioning sensing module that positions the obstacle, in a case where the obstacle type is a moving obstacle;
correspondingly, the obstacle determination module 306 is specifically configured to determine, based on the environment image and the depth image acquired by the depth image sensor, a corresponding image coordinate position of the obstacle in the depth image; determining a target image area corresponding to a preset reference image area in the depth image; judging whether the image coordinate position is in the target image area; if yes, the obstacle avoidance processing module 308 is operated.
Optionally, the obstacle identifying module 304 includes:
a feature ratio determination submodule configured to determine a feature ratio of the obstacle from the environment image;
a feature ratio judgment submodule configured to judge whether a feature ratio of the obstacle is greater than a preset feature ratio threshold; if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle; if not, determining the image sensing module as a positioning sensing module for positioning the obstacle; wherein the image sensing module comprises: monocular camera.
Optionally, the obstacle determining module 306 is specifically configured to determine a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor; judging whether the physical coordinate position is in a preset physical barrier area; if yes, the obstacle avoidance processing module 308 is operated.
Optionally, the obstacle determining module 306 is specifically configured to determine, based on the environment image, an image coordinate position corresponding to the obstacle, and determine a target image area corresponding to a preset reference image area in the environment image; judging whether the image coordinate position is in the target image area; if yes, the obstacle avoidance processing module 308 is operated.
Optionally, the obstacle identifying module 304 includes:
an initial distance calculation submodule configured to calculate an initial distance corresponding to the obstacle from the environment image;
and the first positioning sensing module determining submodule is configured to determine the first positioning sensing module corresponding to the initial distance according to the corresponding relation between the distance and the positioning sensing module, and the first positioning sensing module determining submodule is used as a positioning sensing module for positioning the obstacle.
Optionally, the obstacle avoidance processing apparatus for a robot further includes:
the second distance determining module is configured to calculate a second distance corresponding to the obstacle based on the positioning feature information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
the second distance judging module is configured to judge whether the second distance is consistent with the second positioning sensing module corresponding to the initial distance in the corresponding relation between the distance and the positioning sensing module; if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
Optionally, the obstacle avoidance processing module 308 includes:
a travel instruction execution submodule configured to generate and execute a travel instruction for deceleration travel;
and the driving route planning submodule is configured to plan a driving route based on the position information and update the original driving route based on the driving route.
Optionally, the driving route planning sub-module includes:
a maximum obstacle contour determination unit configured to determine a maximum obstacle contour of the obstacle from the environment image;
a driving route planning unit configured to plan a driving route based on the maximum obstacle profile and the position information such that a driving width of the driving route is greater than the maximum obstacle profile value.
Optionally, the obstacle avoidance processing apparatus for a robot further includes:
a target object feature detection module configured to detect a target object feature contained in the environment image;
an obstacle detection module configured to detect whether the target object feature is an obstacle; if so, the obstacle identification module 304 is operated.
The embodiment of the robot provided by the specification is as follows:
on the basis of the same technical concept, one or more embodiments of the present specification further provide a robot for executing the above-mentioned obstacle avoidance processing method, and fig. 4 is a schematic structural diagram of the robot provided in one or more embodiments of the present specification.
The embodiment provides a robot, includes:
a processor 401, an image sensing module 402 and a positioning sensing module 403;
wherein the image sensing module 402 is configured to acquire an environmental image;
the processor 401 is configured to acquire an environment image acquired by the image sensing module 402, identify an obstacle in the environment image, determine whether the obstacle is located in a target obstacle area based on positioning feature information acquired by the positioning sensing module 403, and if so, perform obstacle avoidance processing based on position information determined by the positioning feature information;
the location sensing module 403 is determined by the processor 401 and is configured to locate the obstacle.
Optionally, the identifying an obstacle in the environment image includes:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
Optionally, if the type of the obstacle is a fixed obstacle, determining the image sensing module 402 as the positioning sensing module 403; the image sensing module 402 includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information acquired by the positioning sensing module 403 includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, if the type of the obstacle is a moving obstacle, determining the depth image sensor and the image sensing module 402 as the positioning sensing module 403;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information acquired by the positioning sensing module 403 includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, the processor determines the positioning sensing module 403 by performing the following operations:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not; if yes, determining that the radio sensor is the positioning sensing module 403; if not, determining the image sensing module 402 as the positioning sensing module 403; wherein the image sensing module 402 comprises: monocular camera.
Optionally, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information acquired by the positioning sensing module 403 includes:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area; if yes, executing the next step.
Optionally, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information acquired by the positioning sensing module 403 includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
Optionally, the processor determines the positioning sensing module 403 by performing the following operations:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance according to a pre-established corresponding relationship between the distance and the positioning sensing module, as the positioning sensing module 403.
Optionally, the processor 401 is further configured to:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance;
if not, the positioning sensing module 403 is switched from the first positioning sensing module to the second positioning sensing module.
Optionally, the obstacle avoidance processing performed on the position information determined based on the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
Optionally, the planning a driving route based on the position information includes:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
Optionally, the processor is further configured to:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle; if yes, the next step.
An embodiment of a storage medium provided in this specification is as follows:
on the basis of the same technical concept, one or more embodiments of the present specification further provide a storage medium corresponding to the above-described robot obstacle avoidance processing method.
The storage medium provided in this embodiment is used to store computer-executable instructions, and when executed, the computer-executable instructions implement the following processes:
acquiring an environment image acquired by an image sensing module;
identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles;
judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module;
and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
Optionally, the identifying an obstacle in the environment image includes:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
Optionally, the determining a location sensing module for locating the obstacle includes:
if the type of the obstacle is a fixed obstacle, determining the image sensing module as a positioning sensing module for positioning the obstacle; the image sensing module includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; and if so, executing the obstacle avoidance processing flow based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
if the type of the obstacle is a moving obstacle, determining a depth image sensor and the image sensing module as a positioning sensing module for positioning the obstacle;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area; and if so, executing the obstacle avoidance processing flow based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not; if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle; if not, determining the image sensing module as a positioning sensing module for positioning the obstacle; wherein the image sensing module comprises: monocular camera.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area; and if so, executing the obstacle avoidance processing flow based on the position information determined by the positioning feature information.
Optionally, the determining, based on the positioning feature information acquired by the positioning sensing module, whether the obstacle is located in a target obstacle area includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; and if so, executing the obstacle avoidance processing flow based on the position information determined by the positioning feature information.
Optionally, the determining a location sensing module for locating the obstacle includes:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance according to the corresponding relation between the distance and the positioning sensing module, which is established in advance, as a positioning sensing module for positioning the obstacle.
Optionally, the computer executable instructions, when executed, further implement the following process:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance; if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
Optionally, the obstacle avoidance processing performed on the position information determined based on the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
Optionally, the planning a driving route based on the position information includes:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
Optionally, the computer executable instructions, when executed, further implement the following process:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle; and if so, executing the process of identifying the obstacle in the environment image and determining a positioning sensing module process for positioning the obstacle.
It should be noted that the embodiment of the storage medium in this specification and the embodiment of the robot obstacle avoidance processing method in this specification are based on the same inventive concept, and therefore, specific implementation of this embodiment may refer to implementation of the foregoing corresponding method, and repeated details are not described again.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
In the 30 s of the 20 th century, improvements in a technology could clearly be distinguished between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in multiple software and/or hardware when implementing the embodiments of the present description.
One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of this document and is not intended to limit this document. Various modifications and changes may occur to those skilled in the art from this document. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.

Claims (26)

1. A robot obstacle avoidance processing method is characterized by comprising the following steps:
acquiring an environment image acquired by an image sensing module;
identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles;
judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module;
and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
2. The robot obstacle avoidance processing method according to claim 1, wherein the identifying an obstacle in the environment image includes:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
3. The robot obstacle avoidance processing method according to claim 2, wherein the determining of the positioning sensing module for positioning the obstacle includes:
if the type of the obstacle is a fixed obstacle, determining the image sensing module as a positioning sensing module for positioning the obstacle; the image sensing module includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area;
and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
4. The robot obstacle avoidance processing method according to claim 2, wherein the determining of the positioning sensing module for positioning the obstacle includes:
if the type of the obstacle is a moving obstacle, determining a depth image sensor and the image sensing module as a positioning sensing module for positioning the obstacle;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area;
and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
5. The robot obstacle avoidance processing method according to claim 1, wherein the determining of the positioning sensing module for positioning the obstacle includes:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not;
if so, determining that the radio sensor is a positioning sensing module for positioning the obstacle;
if not, determining the image sensing module as a positioning sensing module for positioning the obstacle;
wherein the image sensing module comprises: monocular camera.
6. The robot obstacle avoidance processing method according to claim 5, wherein the determining whether the obstacle is in a target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area;
and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
7. The robot obstacle avoidance processing method according to claim 5, wherein the determining whether the obstacle is in a target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area;
and if so, executing the step of obstacle avoidance processing based on the position information determined by the positioning feature information.
8. The robot obstacle avoidance processing method according to claim 1, wherein the determining of the positioning sensing module for positioning the obstacle includes:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance according to the corresponding relation between the distance and the positioning sensing module, which is established in advance, as a positioning sensing module for positioning the obstacle.
9. The robot obstacle avoidance processing method according to claim 8, further comprising:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance;
if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
10. The robot obstacle avoidance processing method according to claim 1, wherein the performing obstacle avoidance processing based on the position information determined by the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
11. The robot obstacle avoidance processing method according to claim 10, wherein the planning of the travel route based on the position information includes:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
12. The robot obstacle avoidance processing method according to claim 1, wherein after the step of acquiring the environment image collected by the image sensing module is executed, and before the step of identifying the obstacle in the environment image and determining the positioning sensing module for positioning the obstacle is executed, the method further comprises:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle;
and if so, executing the steps of identifying the obstacles in the environment image and determining a positioning sensing module for positioning the obstacles.
13. The utility model provides a barrier processing apparatus is kept away to robot which characterized in that includes:
the environment image acquisition module is configured to acquire an environment image acquired by the image sensing module;
an obstacle identification module configured to identify an obstacle in the environment image and determine a positioning sensing module that positions the obstacle;
the obstacle judging module is configured to judge whether the obstacle is in a target obstacle area or not based on the positioning characteristic information acquired by the positioning sensing module;
if so, operating an obstacle avoidance processing module; and the obstacle avoidance processing module is configured to perform obstacle avoidance processing based on the position information determined by the positioning characteristic information.
14. A robot, comprising:
the system comprises a processor, an image sensing module and a positioning sensing module;
wherein the image sensing module is configured to acquire an environmental image;
the processor is configured to acquire an environment image acquired by the image sensing module, identify an obstacle in the environment image, judge whether the obstacle is in a target obstacle area based on positioning feature information acquired by the positioning sensing module, and if so, perform obstacle avoidance processing based on position information determined by the positioning feature information;
the location sensing module is determined by the processor and is configured to locate the obstacle.
15. The robot of claim 14, wherein said identifying an obstacle in the environmental image comprises:
inputting the environment image into an image recognition model, performing feature segmentation and feature recognition on the environment image by the image recognition model, and outputting the obstacle type of an obstacle contained in the environment image.
16. The robot of claim 15, wherein if the obstacle type is a fixed obstacle, the image sensing module is determined as the positioning sensing module; the image sensing module includes: a monocular camera;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
17. The robot of claim 15, wherein if the obstacle type is a moving obstacle, a depth image sensor and the image sensing module are determined as the positioning sensing module;
correspondingly, the determining whether the obstacle is located in the target obstacle area based on the positioning feature information collected by the positioning sensing module includes:
determining the corresponding image coordinate position of the obstacle in the depth image based on the environment image and the depth image acquired by the depth image sensor;
determining a target image area corresponding to a preset reference image area in the depth image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
18. The robot of claim 14, wherein the processor determines the position sensing module by:
determining the feature proportion of the obstacle according to the environment image;
judging whether the feature ratio of the barrier is larger than a preset feature ratio threshold value or not;
if yes, determining that the radio sensor is the positioning sensing module;
if not, determining the image sensing module as the positioning sensing module;
wherein the image sensing module comprises: monocular camera.
19. The robot of claim 18, wherein said determining whether the obstacle is within a target obstacle area based on the positioning characteristic information collected by the positioning sensing module comprises:
determining a physical coordinate position corresponding to the position data based on the position data of the obstacle acquired by the radio sensor;
judging whether the physical coordinate position is in a preset physical barrier area; if yes, executing the next step.
20. The robot of claim 18, wherein said determining whether the obstacle is within a target obstacle area based on the positioning characteristic information collected by the positioning sensing module comprises:
determining an image coordinate position corresponding to the obstacle based on the environment image, and determining a target image area corresponding to a preset reference image area in the environment image;
judging whether the image coordinate position is in the target image area; if yes, executing the next step.
21. The robot of claim 14, wherein the processor determines the position sensing module by:
calculating an initial distance corresponding to the obstacle according to the environment image;
and determining a first positioning sensing module corresponding to the initial distance as the positioning sensing module according to the corresponding relation between the distance and the positioning sensing module established in advance.
22. The robot of claim 21, wherein the processor is further configured to:
calculating a second distance corresponding to the obstacle based on the positioning characteristic information of the obstacle, which is acquired by the positioning sensing module corresponding to the distance;
judging whether a second positioning sensing module corresponding to the second distance in the corresponding relation between the distance and the positioning sensing module is consistent with the positioning sensing module corresponding to the initial distance;
if not, the positioning sensing module is switched from the first positioning sensing module to the second positioning sensing module.
23. The robot of claim 14, wherein the performing obstacle avoidance processing based on the position information determined by the positioning feature information includes:
generating and executing a driving instruction for deceleration driving;
and planning a driving route based on the position information, and updating the original driving route based on the driving route.
24. The robot of claim 23, wherein said planning a driving route based on said location information comprises:
determining the maximum obstacle outline of the obstacle according to the environment image;
planning a driving route based on the maximum obstacle profile and the position information so that the driving width of the driving route is larger than the maximum obstacle profile value.
25. The robot of claim 14, wherein the processor is further configured to:
detecting a target object feature contained in the environment image;
detecting whether the target object feature is an obstacle; if yes, the next step.
26. A storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed, implement the following:
acquiring an environment image acquired by an image sensing module;
identifying obstacles in the environment image and determining a positioning sensing module for positioning the obstacles;
judging whether the barrier is in a target barrier area or not based on the positioning characteristic information acquired by the positioning sensing module;
and if so, carrying out obstacle avoidance processing based on the position information determined by the positioning characteristic information.
CN202010843699.3A 2020-08-20 2020-08-20 Robot obstacle avoidance processing method and device and robot Pending CN112068553A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010843699.3A CN112068553A (en) 2020-08-20 2020-08-20 Robot obstacle avoidance processing method and device and robot
JP2020193589A JP6884312B1 (en) 2020-08-20 2020-11-20 Robot obstacle avoidance processing method, device, robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010843699.3A CN112068553A (en) 2020-08-20 2020-08-20 Robot obstacle avoidance processing method and device and robot

Publications (1)

Publication Number Publication Date
CN112068553A true CN112068553A (en) 2020-12-11

Family

ID=73662546

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010843699.3A Pending CN112068553A (en) 2020-08-20 2020-08-20 Robot obstacle avoidance processing method and device and robot

Country Status (2)

Country Link
JP (1) JP6884312B1 (en)
CN (1) CN112068553A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113655793A (en) * 2021-08-12 2021-11-16 上海三一重机股份有限公司 Obstacle avoidance control method and device based on fusion strategy and engineering machinery
CN113741472A (en) * 2021-09-10 2021-12-03 上海伯镭智能科技有限公司 Obstacle avoidance method and device based on multi-image acquisition
WO2023216555A1 (en) * 2022-05-10 2023-11-16 丰疆智能(深圳)有限公司 Obstacle avoidance method and apparatus based on binocular vision, and robot and medium

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113467468B (en) * 2021-07-23 2024-03-29 合肥工业大学 Intelligent robot obstacle avoidance system and method based on embedded robot
CN113848895B (en) * 2021-09-16 2023-06-06 北京空间飞行器总体设计部 Long-distance safe movement and efficient detection method and device for fire surface inspection device
CN114879701A (en) * 2022-06-23 2022-08-09 池州市安安新材科技有限公司 Robot track obstacle avoidance method and system
CN115147738B (en) * 2022-06-24 2023-01-13 中国人民公安大学 Positioning method, device, equipment and storage medium
CN115019216B (en) * 2022-08-09 2022-10-21 江西师范大学 Real-time ground object detection and positioning counting method, system and computer
CN116203970A (en) * 2023-04-27 2023-06-02 泰坦(天津)能源技术有限公司 Intelligent obstacle avoidance method and system for inspection robot

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109116841A (en) * 2018-07-23 2019-01-01 昆明理工大学 A kind of path planning smooth optimization method based on ant group algorithm
CN110442120A (en) * 2018-05-02 2019-11-12 深圳市优必选科技有限公司 Method, robot and the terminal device that control robot moves under different scenes
CN110502019A (en) * 2019-09-06 2019-11-26 北京云迹科技有限公司 A kind of barrier-avoiding method and device of Indoor Robot
CN110609546A (en) * 2019-08-15 2019-12-24 浙江国自机器人技术有限公司 Protection method, system, computer device and readable storage medium for picking device
US20200089247A1 (en) * 2018-09-14 2020-03-19 Florian Shkurti Iterative generation of adversarial scenarios

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5722127B2 (en) * 2011-06-07 2015-05-20 株式会社小松製作所 Work vehicle perimeter monitoring device
WO2016009585A1 (en) * 2014-07-18 2016-01-21 パナソニックＩｐマネジメント株式会社 Autonomous mobile object and method of controlling same
JP2017220057A (en) * 2016-06-08 2017-12-14 株式会社リコー Obstacle avoidance device, obstacle avoidance system and program
JP2020017206A (en) * 2018-07-27 2020-01-30 ソニー株式会社 Information processing apparatus, action determination method, and program
JP7044694B2 (en) * 2018-12-27 2022-03-30 ヤンマーパワーテクノロジー株式会社 Obstacle detection system for work vehicles

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110442120A (en) * 2018-05-02 2019-11-12 深圳市优必选科技有限公司 Method, robot and the terminal device that control robot moves under different scenes
CN109116841A (en) * 2018-07-23 2019-01-01 昆明理工大学 A kind of path planning smooth optimization method based on ant group algorithm
US20200089247A1 (en) * 2018-09-14 2020-03-19 Florian Shkurti Iterative generation of adversarial scenarios
CN110609546A (en) * 2019-08-15 2019-12-24 浙江国自机器人技术有限公司 Protection method, system, computer device and readable storage medium for picking device
CN110502019A (en) * 2019-09-06 2019-11-26 北京云迹科技有限公司 A kind of barrier-avoiding method and device of Indoor Robot

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113655793A (en) * 2021-08-12 2021-11-16 上海三一重机股份有限公司 Obstacle avoidance control method and device based on fusion strategy and engineering machinery
CN113741472A (en) * 2021-09-10 2021-12-03 上海伯镭智能科技有限公司 Obstacle avoidance method and device based on multi-image acquisition
CN113741472B (en) * 2021-09-10 2024-03-08 上海伯镭智能科技有限公司 Obstacle avoidance method and device based on multi-image acquisition
WO2023216555A1 (en) * 2022-05-10 2023-11-16 丰疆智能(深圳)有限公司 Obstacle avoidance method and apparatus based on binocular vision, and robot and medium

Also Published As

Publication number Publication date
JP2022035927A (en) 2022-03-04
JP6884312B1 (en) 2021-06-09

Similar Documents

Publication Publication Date Title
CN112068553A (en) Robot obstacle avoidance processing method and device and robot
US20210154835A1 (en) Robot path planning method and apparatus and robot using the same
US20230100814A1 (en) Obstacle trajectory prediction method and apparatus
US11537138B2 (en) Adaptive region division method and system
CN108320296B (en) Method, device and equipment for detecting and tracking target object in video
US11334086B2 (en) Autonomous robots and methods of operating the same
CN115600157B (en) Data processing method and device, storage medium and electronic equipment
CN112561859B (en) Monocular vision-based steel belt drilling and anchor net identification method and device for anchoring and protecting
CN116740361B (en) Point cloud segmentation method and device, storage medium and electronic equipment
CN111288971A (en) Visual positioning method and device
CN114077252B (en) Robot collision obstacle distinguishing device and method
CN114740842A (en) Multi-sensor fusion robot obstacle avoidance method, equipment and medium
US20220314980A1 (en) Obstacle tracking method, storage medium and unmanned driving device
US20220319189A1 (en) Obstacle tracking method, storage medium, and electronic device
US20220309707A1 (en) Pose determining
CN113642616B (en) Training sample generation method and device based on environment data
CN114623824A (en) Method and device for determining barrier speed
CN114332201A (en) Model training and target detection method and device
CN111598092A (en) Method for determining target area in image, method and device for identifying target
CN112338910A (en) Space map determination method, robot, storage medium and system
CN112329547A (en) Data processing method and device
Cheng et al. Dynamic path planning in human-shared environments for low-resource mobile agents
CN114047763B (en) System, method and device for distinguishing collision barriers by unmanned vehicles and electronic equipment
CN115880685B (en) Three-dimensional target detection method and system based on volntet model
Sumbal et al. Environment Detection and Path Planning using the e-puck Robot

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination