CN114571460A - Robot control method, device and storage medium - Google Patents
Robot control method, device and storage medium Download PDFInfo
- Publication number
- CN114571460A CN114571460A CN202210289317.6A CN202210289317A CN114571460A CN 114571460 A CN114571460 A CN 114571460A CN 202210289317 A CN202210289317 A CN 202210289317A CN 114571460 A CN114571460 A CN 114571460A
- Authority
- CN
- China
- Prior art keywords
- local
- robot
- simulation
- environment information
- pose
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000033001 locomotion Effects 0.000 claims abstract description 281
- 238000004088 simulation Methods 0.000 claims abstract description 261
- 230000036544 posture Effects 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 230000007613 environmental effect Effects 0.000 description 7
- 210000004556 brain Anatomy 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1612—Programme controls characterised by the hand, wrist, grip control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The present disclosure relates to a robot control method, apparatus, device, and storage medium, the method comprising: acquiring the pose of the robot and local real environment information within a preset range of the pose; adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot; planning a global motion path of the simulation robot based on virtual environment information in the three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in the real world where the robot is located; planning a local motion attitude of the simulation robot within a preset range of the simulation pose according to the local real environment information and the global motion path; and controlling the robot to move according to the local motion attitude.
Description
Technical Field
The present disclosure relates to the field of robotics, and in particular, to a robot control method, apparatus, and storage medium.
Background
In the process of Robot navigation and obstacle avoidance, a grid map is usually created by using single-line or multi-line laser to perform navigation and positioning, and navigation path planning and real-time obstacle avoidance are completed based on an ROS (Robot Operating System).
Because the grid map is a two-dimensional plane, the object space information in the real environment cannot be reflected, and the computational power of the ROS is limited, so that complex and multivariate data cannot be processed. Therefore, the navigation path planning result and the real-time obstacle avoidance strategy obtained in the grid map based on the ROS have poor effects in practical application.
Disclosure of Invention
An object of the present disclosure is to provide a robot control method, apparatus, device, and storage medium to solve the problems in the related art.
In order to achieve the above object, a first aspect of embodiments of the present disclosure provides a robot control method, including:
acquiring the pose of the robot and local real environment information within a preset range of the pose;
adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot;
Planning a global motion path of the simulation robot based on virtual environment information in the three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in the real world where the robot is located;
planning a local motion attitude of the simulation robot within a preset range of the simulation pose according to the local real environment information and the global motion path;
and controlling the robot to move according to the local motion attitude.
Optionally, the pose includes initial position coordinates of the robot, accordingly, the simulation pose includes simulation initial position coordinates of the simulation robot, and the planning of the global motion path of the simulation robot based on the virtual environment information in the three-dimensional simulation map model includes:
planning a plurality of initial global motion paths from the simulation initial position coordinates to simulation target position coordinates based on virtual environment information in the three-dimensional simulation map model, wherein the simulation target position coordinates are mapping results of the target position coordinates of the robot in the three-dimensional simulation map model;
And determining the global motion path from the plurality of initial global motion paths according to the test result of the movement of the simulation robot according to the plurality of initial global motion paths.
Optionally, the global motion path includes a plurality of ordered position coordinates, and the planning a local motion posture of the simulation robot within a preset range of the simulation pose according to the local real environment information and the global motion path includes:
determining a local position coordinate sequence within the preset range from the plurality of ordered position coordinates;
determining local starting point coordinates and local end point coordinates from the local position coordinate sequence;
and determining a local motion attitude of the simulation robot according to the local real environment information, the local starting point coordinate and the local ending point coordinate, wherein the local motion attitude is used for controlling the simulation robot to reach the local ending point coordinate from the local starting point coordinate.
Optionally, the determining the local motion posture of the simulation robot according to the local real environment information, the local start point coordinate and the local end point coordinate includes:
And inputting the local real environment information, the local starting point coordinates and the local end point coordinates into a trained motion decision model to obtain a local motion attitude output by the trained motion decision model.
Optionally, the determining the local motion posture of the simulation robot according to the local real environment information, the local start point coordinate and the local end point coordinate includes:
inputting the local real environment information, the local starting point coordinates and the local end point coordinates into a trained motion decision model to obtain a plurality of initial local motion postures output by the trained motion decision model;
and determining the local motion attitude from the plurality of initial local motion attitudes according to the test result of the motion of the simulation robot according to the plurality of initial local motion attitudes.
Optionally, the training process of the motion decision model includes:
acquiring a local virtual environment information sample of a simulation robot in a preset range of a simulation pose sample in a three-dimensional simulation map model sample, a local starting point coordinate sample and a local end point coordinate sample in the preset range;
Inputting the local virtual environment information sample, the local starting point coordinate sample and the local end point coordinate sample into a motion decision model to be trained to obtain a local motion attitude result output by the motion decision model to be trained;
and adjusting the training parameters of the motion decision model to be trained according to the result that the simulation robot moves in the three-dimensional simulation map model sample according to the local motion attitude result.
Optionally, the method further comprises:
and updating the virtual environment information in the three-dimensional simulation map model according to the environment information acquired by the robot in real time and/or the environment information acquired by a sensor in the environment in real time, so that the virtual environment information in the three-dimensional simulation map model is consistent with the environment information of the real world.
Optionally, the three-dimensional simulation map model is a digital twin model.
A second aspect of embodiments of the present disclosure provides a robot control device, the device including:
the acquisition module is used for acquiring the pose of the robot and the local real environment information within the preset range of the pose;
the adjusting module is used for adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot;
The first planning module is used for planning a global motion path of the simulation robot based on virtual environment information in the three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in a real world where the robot is located;
the second planning module is used for planning the local motion attitude of the simulation robot in the preset range of the simulation pose according to the local real environment information and the global motion path;
and the control module is used for controlling the robot to move according to the local motion attitude.
A third aspect of the embodiments of the present disclosure provides a robot control device including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method in the first aspect.
A fourth aspect of embodiments of the present disclosure provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
Through the technical scheme, the global motion path of the simulation robot can be planned in the three-dimensional simulation map model, and the local motion attitude of the simulation robot is planned based on the local real environment information and the global motion path acquired by the robot in the real world. Because the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world, and the simulation pose of the simulation robot is consistent with the pose of the robot in the real world. Therefore, the robot can be controlled to move in the real world according to the planned local motion posture of the simulation robot.
In the process, object space information embodied by the three-dimensional simulation map model highly simulated with the real world can be fully utilized, the three-dimensional simulation map model can be loaded to the cloud, and the global motion path and the local motion attitude of the simulation robot are planned by utilizing the powerful calculation power of the cloud. On the basis, the robot in the real world can be controlled to move according to the global motion path and the local motion attitude obtained through cloud computing. Therefore, the defect of limited computational power of ROS can be overcome, the object space information is fully utilized, and a global motion path and a local motion attitude with better practical application effect are planned.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, but do not constitute a limitation of the disclosure. In the drawings:
fig. 1 is a flowchart illustrating a robot control method according to an exemplary embodiment of the present disclosure.
Fig. 2 is a block diagram illustrating a robot control device according to an exemplary embodiment of the present disclosure.
Fig. 3 is a block diagram illustrating another robot control device according to an exemplary embodiment of the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
It should be noted that all actions of acquiring signals, information or data in the present disclosure are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
In the related art, a Robot controller (e.g., ROS, Robot Operating System) typically constructs a map for the Robot to navigate based on sensor information collected by the Robot (e.g., a grid map created based on a single-line or multi-line laser), and plans a motion path and a motion attitude of the Robot based on the constructed map and the sensor information collected in real time. And then, the robot moves according to the planned motion path and the motion attitude in real time. However, in the process of robot movement, if the planned movement path and movement posture have poor effects in practical application, failure in obstacle avoidance or damage to the robot may be caused.
For example, in a process that the robot moves according to a navigation path planning result obtained by the ROS in the grid map and the real-time obstacle avoidance strategy, the planned movement path and the obstacle avoidance strategy may have poor effects in practical application due to limitations of the grid map and the ROS, so that the robot fails in obstacle avoidance or is physically damaged.
In view of this, the present disclosure provides a robot control method, which may be applied to a robot control device, where the robot control device may include a cloud-side controller and a local controller.
The cloud controller can be a cloud brain arranged on the cloud server, the cloud brain can integrate Artificial Intelligence (AI) with Human assistance (HI), and efficient and safe cloud intelligent operation service is provided for the robot and the intelligent device. The local controller may be an ROS (ROS mounted in the Linux system) provided locally to the Robot, or may be an RCU (Robot Control Unit) provided locally to the Robot. The cloud-end controller and the local controller can both load the three-dimensional simulation map model, and can realize synchronization of the three-dimensional simulation map model through communication between the cloud-end controller and the local controller. In a possible implementation manner, synchronization of the three-dimensional simulation map model loaded by the cloud-end controller and the local controller can be realized based on a synchronization mechanism in an MMO (Massive Multiplayer Online Game) architecture.
It should be noted that the three-dimensional simulated map model may be a digital twin model. In a particular implementation, the digital twin model may be constructed as follows:
first, environmental information in the real world can be collected by tools such as unmanned aerial vehicles, robots, and handheld devices (e.g., depth cameras, laser scanners, inertometers, odometers, infrared sensors, etc.). The real-world environment Information can be embodied by sensor data such as image data, laser data, inertia data, mileage data, acceleration data, distance between objects and the like acquired by the tool and Building Information model (Building Information Modeling) data. On the basis, a preliminary map model which can be used for navigation and positioning can be constructed by the SLAM method. And then, carrying out three-dimensional modeling according to the map model to obtain a digital twin model highly simulated with the real world. Furthermore, the digital twin model may also be subjected to map editing to add semantic information (e.g., object name, object size, etc. in the environment) in the digital twin model.
The slam (simultaneous localization and mapping) method refers to a concept of synchronous positioning and mapping. In SLAM, the robot starts moving from an unknown position in an unknown environment, positions its position and attitude based on sensor data estimated and collected from the position during the movement, and builds up a map incrementally based on its position.
In the embodiment of the disclosure, after the three-dimensional simulation map model highly simulated with the real world is constructed, the three-dimensional simulation map model can be loaded locally on the cloud server and the robot respectively, and the three-dimensional simulation map model can be synchronized through communication between the cloud server and the robot. In the process, the three-dimensional simulation map models of the local and cloud servers of the robot can be updated through sensor data acquired by the robot in the real world.
Referring to fig. 1, fig. 1 is a flowchart illustrating a robot control method according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the robot control method includes the steps of:
s101, acquiring the pose of the robot and local real environment information in the preset range of the pose.
It should be noted that the pose of the robot is used to represent the position and the pose of the robot, and the robot can establish a virtual three-dimensional coordinate system in the real world and locate its position and pose through the collected sensor data during the movement process. Wherein, the position of the robot may refer to a coordinate point of the robot in a three-dimensional coordinate system. The posture of the robot can be the included angle between the robot and the X axis, the Y axis and the Z axis of the three-dimensional coordinate system respectively, and the posture of the robot can represent the front orientation of the robot.
It will be appreciated that when a robot is in a certain location, it is generally possible to collect environmental information within a certain range of that location. Wherein, the certain range of this position is changeable, can preset different scopes according to actual conditions and the performance of robot, also is the preset scope. That is, the preset range may be set according to practical situations, for example, 50m, which is not specifically limited by the present disclosure.
On the basis, the local real environment information in the preset range of the pose of the robot can be obtained. The preset range of the pose may be a circular range obtained by taking the position represented by the pose as a center of a circle and taking the preset length as a radius, a rectangular range obtained by taking the position represented by the pose as a midpoint of a rectangular diagonal and taking the preset length as a length of the rectangular diagonal with reference to the front orientation of the simulation robot, or other preset ranges set according to actual conditions, which is not specifically limited by the disclosure. The local real environment information can be embodied by sensor data acquired by the robot within a preset range.
And S102, adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot.
It is easy to understand that the three-dimensional simulation map model is provided with a simulation robot, and the initial simulation pose of the simulation robot is consistent with the initial pose of the robot. In the real world motion process of the robot, the pose of the robot can be acquired in real time, and the simulation pose in the three-dimensional simulation map model is adjusted according to the pose of the robot, so that the simulation pose of the simulation robot is consistent with the pose of the robot.
And S103, planning a global motion path of the simulation robot based on the virtual environment information in the three-dimensional simulation map model.
And the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world where the robot is located.
It should be noted that, on the basis of ensuring that the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world where the robot is located and the simulation pose of the simulation robot is consistent with the real pose of the robot, the global motion path of the simulation robot planned based on the virtual environment information in the three-dimensional simulation map model can be applied to the motion of the real-world robot. The global motion path is used for controlling the simulation robot to move from the simulation initial position coordinates to the simulation target position coordinates. The simulation initial/target position coordinates are mapping results of the preset initial/target position coordinates of the robot in the three-dimensional simulation map model. The preset initial position coordinates and the preset target position coordinates of the robot may be determined according to actual conditions, and the present disclosure is not particularly limited thereto.
And S104, planning the local motion attitude of the simulation robot in the preset range of the simulation pose according to the local real environment information and the global motion path.
It is understood that, since the virtual environment information in the three-dimensional simulation map model coincides with the environment information in the real world in which the robot is located, local virtual environment information corresponding to the local real environment information exists in the three-dimensional simulation map model. On the basis, the local motion attitude of the simulation robot in the preset range of the simulation pose can be planned according to the local real environment information and the global motion path. In the process, according to the global motion path and the local real environment information, a local motion path in a preset range where the local real environment information is located can be obtained, and the local motion path of the simulation robot in the preset range can be planned on the basis of the motion direction indicated by the local motion path.
And S105, controlling the robot to move according to the local motion attitude.
Because the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world, and the simulation pose of the simulation robot is consistent with the pose of the robot in the real world. Therefore, the robot can be controlled to move in the real world according to the planned local motion posture of the simulation robot.
By the technical scheme, the object space information embodied by the three-dimensional simulation map model highly simulated with the real world can be fully utilized, the three-dimensional simulation map model can be loaded to the cloud server, and the global motion path and the local motion attitude of the simulation robot are planned by utilizing the powerful calculation power of the cloud brain in the cloud server. On the basis, the robot in the real world can be controlled to move according to the global motion path and the local motion attitude obtained by computing the cloud brain. Therefore, the defect of limited computational power of ROS can be overcome, the object space information is fully utilized, and a global motion path and a local motion attitude with better practical application effect are planned.
Optionally, the pose includes initial position coordinates of the robot, and accordingly, the simulated pose includes simulated initial position coordinates of the simulated robot. On this basis, the step S103 may include:
planning a plurality of initial global motion paths from a simulation initial position coordinate to a simulation target position coordinate based on virtual environment information in the three-dimensional simulation map model, wherein the simulation target position coordinate is a mapping result of the target position coordinate of the robot in the three-dimensional simulation map model;
And determining a global motion path from the plurality of initial global motion paths according to the test result of the movement of the simulation robot according to the plurality of initial global motion paths.
The initial global motion path may be a motion path in which the motion duration of the simulation robot from the simulation initial position coordinate to the simulation target position coordinate is the shortest, may also be a motion path in which the motion distance is the shortest, and may also be a motion path obtained under other conditions, which is not specifically limited by the present disclosure.
In the embodiment of the disclosure, after the plurality of initial global motion paths are obtained through planning, the global motion path may be determined from the plurality of initial global motion paths according to a test result of the simulation robot moving according to the plurality of initial global motion paths. The test result may include information such as whether there is an obstacle in the way of the global motion path, obstacle information (obstacle position coordinates, size, and the like), obstacle avoidance success/failure, motion duration, and motion distance. Thus, according to the test result, the global motion path satisfying the first preset condition can be determined. The initial global motion path can also be adjusted according to the barrier information, the motion duration and other related information represented by the test result, and the test is performed again to obtain the global motion path meeting the first preset condition. The first preset condition may be a global motion path with a shortest motion duration and a success obstacle avoidance, or a global motion path with no obstacle and a shortest motion distance in the process. The present disclosure does not specifically limit this.
The method comprises the steps of testing a global motion path obtained by planning in a three-dimensional simulation map model, and determining the global motion path meeting a first preset condition according to a test result. Therefore, the global motion path obtained by planning can be ensured to be more fit with the environmental information, and the global motion path obtained by planning and the effect in practical application are improved.
Optionally, the global motion path includes a plurality of ordered position coordinates, and the step S104 may include:
determining a local position coordinate sequence within a preset range from the plurality of ordered position coordinates;
determining a local starting point coordinate and a local end point coordinate from the local position coordinate sequence;
and determining the local motion attitude of the simulation robot according to the local real environment information, the local starting point coordinates and the local end point coordinates.
The local motion attitude is used for controlling the simulation robot to reach a local end point coordinate from a local starting point coordinate.
It should be understood that the global motion path includes a plurality of ordered position coordinates, and based on the global motion path and the local real environment information, a local position coordinate sequence (i.e., a local motion path) within a preset range in which the local real environment information is located may be obtained. Since the position coordinates are ordered, the local start point coordinate (i.e., the first coordinate in the local position coordinate sequence) and the local end point coordinate (i.e., the last coordinate in the local position coordinate sequence) may be determined from the local position coordinate sequence. On the basis, the local motion attitude of the simulation robot can be determined according to the local real environment information, the local starting point coordinates and the local end point coordinates. The local motion attitude may include a linear velocity and an angular velocity of the simulation robot, among others. The linear velocity and the angular velocity are used for controlling the simulation robot to reach the local end point coordinate from the local start point coordinate.
Optionally, the determining the local motion pose of the simulated robot according to the local real environment information, the local start point coordinate and the local end point coordinate may include:
in the first mode, the local real environment information, the local starting point coordinates and the local ending point coordinates are input into the trained motion decision model, and the local motion attitude output by the trained motion decision model is obtained.
The motion decision model is used for planning the local motion attitude of the simulation robot. The training process of the motion decision model may include:
acquiring a local virtual environment information sample, a local starting point coordinate sample and a local end point coordinate sample in a preset range of a simulation pose sample of a simulation robot in a three-dimensional simulation map model sample;
inputting the local virtual environment information sample, the local starting point coordinate sample and the local end point coordinate sample into a motion decision model to be trained to obtain a local motion attitude result output by the motion decision model to be trained;
and adjusting the training parameters of the motion decision model to be trained according to the result that the simulation robot moves in the three-dimensional simulation map model sample according to the local motion attitude result.
It should be noted that the sample data input into the motion decision model to be trained may be obtained by simulating environmental information in the real world. In specific implementation, a three-dimensional simulation map model sample can be constructed according to environment information acquired in the real world. And then loading the three-dimensional simulation map model sample to a cloud server, setting a simulation robot in the cloud server, and setting an initial simulation pose of the simulation robot according to the simulation pose sample. On the basis, according to the process that the robot acquires the environment information through the sensor in the real world, the process that the simulation robot acquires the virtual environment information in the three-dimensional simulation map model sample through the simulation sensor can be simulated, so that a local virtual environment information sample in the preset range of the simulation robot, a local starting point coordinate sample and a local end point coordinate sample in the preset range can be obtained. It should be noted that, when the simulation robot starts to move, the local start point coordinate sample in the preset range of the simulation robot may be consistent with the position coordinate represented by the initial simulation pose of the simulation robot, and the local end point coordinate sample may be preset. In the motion process of the simulation robot, a local starting point coordinate sample in a preset range of the simulation robot can be determined according to the current simulation pose of the simulation robot, and a local end point coordinate sample can be preset. Alternatively, the local start point coordinate sample and the local end point coordinate sample may also be determined according to a pre-planned global motion path sample.
Then, the local virtual environment information sample, the local starting point coordinate sample and the local ending point coordinate sample can be input into the motion decision model to be trained, and a local motion attitude result output by the motion decision model to be trained is obtained. And adjusting the training parameters of the motion decision model to be trained according to the result that the simulation robot moves in the three-dimensional simulation map model sample according to the local motion attitude result. For example, under the training framework of reinforcement learning, the training parameters representing the reward value may be adjusted when the simulation robot successfully avoids the obstacle according to the planned local motion posture or safely passes through without the obstacle. And when the simulation robot fails to avoid the obstacle according to the planned local motion posture or does not safely pass through the simulation robot without the obstacle (for example, the simulation robot is damaged), adjusting training parameters representing penalty values. Therefore, after a plurality of times of iterative training, a trained motion decision model can be obtained.
Furthermore, it is understood that, in the training process, the motion decision model to be trained may output a plurality of initial local motion pose results. In a possible implementation manner, the motion decision model to be trained may output a corresponding prediction probability for whether the multiple initial local motion posture results are used for obstacle avoidance, and determine the initial local motion posture with the highest prediction probability as the local motion posture result. Accordingly, the trained motion decision model may also output a plurality of initial local motion pose results. On the basis of the above, the local motion attitude of the simulated robot can be determined according to the technical means given in the following manner II.
Inputting the local real environment information, the local starting point coordinates and the local ending point coordinates into the trained motion decision model to obtain a plurality of initial local motion postures output by the trained motion decision model;
and determining the local motion attitude from the plurality of initial local motion attitudes according to the test result of the motion of the simulation robot according to the plurality of initial local motion attitudes.
In the embodiment of the present disclosure, after obtaining a plurality of initial local motion gestures through planning, a local motion gesture may be determined from the initial local motion gestures according to a test result of the simulation robot performing motion according to the initial local motion gestures. The test result may include information about whether an obstacle exists, obstacle information (obstacle position coordinates, size, and the like), obstacle avoidance success/failure, and the like. Thus, according to the test result, the local motion attitude satisfying the second preset condition can be determined. Or adjusting the initial local motion attitude according to the obstacle information represented by the test result, the existence of the obstacle and other related information, and testing again to obtain the local motion attitude meeting the second preset condition. The second preset condition may be a local motion posture when obstacle avoidance succeeds, or a local motion posture when no obstacle exists and the obstacle passes through a preset range safely. The present disclosure does not specifically limit this.
The method comprises the steps of testing a global motion path and a local motion attitude which are planned and obtained in a three-dimensional simulation map model before controlling the robot to move according to the planned and obtained local motion attitude of the simulation robot, and determining the optimal global motion path and the optimal local motion attitude according to a test result. Therefore, trial and error cost of the robot in the real world can be reduced, the effect of the planned global motion path and local motion attitude in practical application is improved, and the obstacle avoidance capability of the robot can be further improved.
Optionally, the method provided in the embodiment of the present disclosure may further include:
and updating the virtual environment information in the three-dimensional simulation map model according to the environment information acquired by the robot in real time and/or the environment information acquired by the sensor in the environment in real time so as to make the virtual environment information in the three-dimensional simulation map model consistent with the environment information of the real world.
Because the environment in the real world may change, the virtual environment information in the three-dimensional simulation map model may be updated according to the environment information acquired by the robot in real time and/or the environment information acquired by the sensor in the environment in real time, so that the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world. The sensor in the environment may refer to a sensor preset in the real world, for example, a camera device set at a preset position in the real world, and the environmental information acquired by the sensor in the environment in real time may be, for example, pedestrian and object data acquired by the camera device.
It should be noted that the cloud-end controller may update the virtual environment information in the three-dimensional simulation map model by combining the environment information acquired by the robot in real time and/or the environment information acquired by the sensors in the environment in real time, and plan the global motion path and the local motion attitude of the simulation robot by comprehensively using these data. Compared with the method that planning is carried out only through the environmental information acquired by the robot in real time, the cloud-end controller can plan to obtain a global motion path and a local motion attitude with better practical application effect on the basis of acquiring richer environmental information.
It should be further noted that the three-dimensional simulation map model may be stored in the cloud server and the robot local according to a gridding storage manner. The gridding storage mode can generally specify the management level of the grid, and different levels correspond to different grid numbers. For example, an 18-level grid-enabled storage may include 236And the grid is stored with map resources which are in one-to-one correspondence with the objects in the real world, and the map resources which are stored in the grid and correspond to the objects in the real world at the longitude and the latitude can be obtained according to the longitude and the latitude in the real world. On the basis, in the process of updating the three-dimensional simulation map model, the map resources corresponding to the three-dimensional simulation map model can be updated according to the longitude and latitude and the range of the object in the real world.
In addition, as described above, the technical solutions provided by the embodiments of the present disclosure may be applied to a robot control apparatus, and the robot control apparatus may include a cloud-side controller and a local controller. The cloud-end controller has strong computing power and can process complex and multivariate data, so that the cloud-end controller can plan a global motion path and a local motion attitude. On the basis, the local controller can have certain computing capacity and is used for planning the local motion attitude, so that the timeliness of local motion control is improved (compared with the mode that the local controller directly sends out a control instruction to carry out local motion after receiving the control instruction of the cloud-end controller, the mode is quicker). The local controller can also be degenerated into a motion actuator, and the motion is performed by receiving a control command of the motion controller. Because the computing power of the cloud-end controller is strong, and the computing speed is far higher than that of the local robot controller, even if the global motion path and the local motion attitude are planned by the cloud-end controller, the delay caused by the planning can be ignored in most cases. That is, the planning of the global motion path and the local motion pose may be performed by both the cloud-end controller and may also be performed by the cloud-end controller and the local controller, respectively.
Through the technical scheme, the global motion path of the simulation robot can be planned in the three-dimensional simulation map model, and the local motion attitude of the simulation robot is planned based on the local real environment information and the global motion path acquired by the robot in the real world. Because the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world, and the simulation pose of the simulation robot is consistent with the pose of the robot in the real world. Therefore, the robot can be controlled to move in the real world according to the planned local motion posture of the simulation robot.
In the process, the object space information embodied by the three-dimensional simulation map model highly simulated with the real world can be fully utilized, the three-dimensional simulation map model can be loaded to the cloud, and the global motion path and the local motion attitude of the simulation robot are planned by the aid of powerful calculation of the cloud. On the basis, the robot in the real world can be controlled to move according to the global motion path and the local motion attitude obtained through cloud computing. Therefore, the defect of limited computational capability of ROS can be overcome, the object space information is fully utilized, and a global motion path and a local motion attitude with better practical application effect are planned.
Based on the same inventive concept, embodiments of the present disclosure also provide a robot control apparatus 100, and referring to fig. 2, fig. 2 is a block diagram of the robot control apparatus 100 according to an exemplary embodiment of the present disclosure. The robot control device 100 includes:
the acquisition module 101 is configured to acquire a pose of the robot and local real environment information within a preset range of the pose;
the adjusting module 102 is configured to adjust a simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot, so that the simulation pose of the simulation robot is consistent with the pose of the robot;
the first planning module 103 is used for planning a global motion path of the simulation robot based on virtual environment information in a three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in a real world where the robot is located;
the second planning module 104 is used for planning the local motion attitude of the simulation robot within the preset range of the simulation pose according to the local real environment information and the global motion path;
and the control module 105 is used for controlling the robot to move according to the local motion attitude.
By adopting the device, the global motion path of the simulation robot can be planned in the three-dimensional simulation map model, and the local motion attitude of the simulation robot is planned based on the local real environment information and the global motion path acquired by the robot in the real world. Because the virtual environment information in the three-dimensional simulation map model is consistent with the environment information in the real world, and the simulation pose of the simulation robot is consistent with the pose of the robot in the real world. Therefore, the robot can be controlled to move in the real world according to the planned local motion posture of the simulation robot.
In the process, object space information embodied by the three-dimensional simulation map model highly simulated with the real world can be fully utilized, the three-dimensional simulation map model can be loaded to the cloud, and the global motion path and the local motion attitude of the simulation robot are planned by utilizing the powerful calculation power of the cloud. On the basis, the robot in the real world can be controlled to move according to the global motion path and the local motion attitude obtained through cloud computing. Therefore, the defect of limited computational power of ROS can be overcome, the object space information is fully utilized, and a global motion path and a local motion attitude with better practical application effect are planned.
Optionally, the pose includes initial position coordinates of the robot, and accordingly, the simulation pose includes simulation initial position coordinates of the simulation robot, and the first planning module 103 is further configured to:
planning a plurality of initial global motion paths from a simulation initial position coordinate to a simulation target position coordinate based on virtual environment information in the three-dimensional simulation map model, wherein the simulation target position coordinate is a mapping result of the target position coordinate of the robot in the three-dimensional simulation map model;
and determining a global motion path from the plurality of initial global motion paths according to the test result of the movement of the simulation robot according to the plurality of initial global motion paths.
Optionally, the global motion path comprises a plurality of ordered position coordinates, and the second planning module 104 is further configured to:
determining a local position coordinate sequence within a preset range from the plurality of ordered position coordinates;
determining a local starting point coordinate and a local end point coordinate from the local position coordinate sequence;
and determining the local motion attitude of the simulation robot according to the local real environment information, the local starting point coordinate and the local end point coordinate, wherein the local motion attitude is used for controlling the simulation robot to reach the local end point coordinate from the local starting point coordinate.
Optionally, the second planning module 104 is further configured to:
and inputting the local real environment information, the local starting point coordinates and the local end point coordinates into the trained motion decision model to obtain the local motion attitude output by the trained motion decision model.
Optionally, the second planning module 104 is further configured to:
inputting the local real environment information, the local starting point coordinates and the local end point coordinates into the trained motion decision model to obtain a plurality of initial local motion postures output by the trained motion decision model;
and determining the local motion attitude from the plurality of initial local motion attitudes according to the test result of the motion of the simulation robot according to the plurality of initial local motion attitudes.
Optionally, the apparatus 100 further comprises a training module, configured to train a motion decision model, where a training process of the motion decision model includes:
acquiring a local virtual environment information sample of a simulation robot in a preset range of a simulation pose sample in a three-dimensional simulation map model sample, a local starting point coordinate sample and a local end point coordinate sample in the preset range;
inputting the local virtual environment information sample, the local starting point coordinate sample and the local end point coordinate sample into a motion decision model to be trained to obtain a local motion attitude result output by the motion decision model to be trained;
and adjusting the training parameters of the motion decision model to be trained according to the result of the movement of the simulation robot in the three-dimensional simulation map model sample according to the local motion posture result.
Optionally, the apparatus 100 further comprises an update module configured to:
and updating the virtual environment information in the three-dimensional simulation map model according to the environment information acquired by the robot in real time and/or the environment information acquired by the sensor in the environment in real time so as to enable the virtual environment information in the three-dimensional simulation map model to be consistent with the environment information of the real world.
Optionally, the three-dimensional simulated map model is a digital twin model.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Based on the same inventive concept, the disclosed embodiment further provides a robot control device 200, and referring to fig. 3, fig. 3 is a block diagram illustrating another robot control device 200 according to an exemplary embodiment of the present disclosure. The robot controller 200 may include: a processor 201 and a memory 202. The robotic control device 200 may also include one or more of a multimedia component 203, an input/output (I/O) interface 204, and a communication component 205.
The processor 201 is configured to control the overall operation of the robot control device 200, so as to complete all or part of the steps in the robot control method. The memory 202 is used to store various types of data to support operation at the robotic control device 200, which may include, for example, instructions for any application or method operating on the robotic control device 200, as well as application-related data, such as contact data, messaging, pictures, audio, video, and so forth. The Memory 202 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 203 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 202 or transmitted through the communication component 205. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 204 provides an interface between the processor 201 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 205 is used for wired or wireless communication between the robot controller 200 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 205 may thus comprise: Wi-Fi module, Bluetooth module, NFC module, etc.
In an exemplary embodiment, the robot controller 200 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described robot control method.
In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions, which when executed by a processor, implement the steps of the robot control method described above. For example, the computer readable storage medium may be the above-described memory 202 comprising program instructions executable by the processor 201 of the robot control device 200 to perform the above-described robot control method.
In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described network transmission control method when executed by the programmable apparatus.
The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details in the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the foregoing embodiments may be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the disclosure does not separately describe various possible combinations.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (11)
1. A robot control method, characterized in that the method comprises:
acquiring the pose of the robot and local real environment information within a preset range of the pose;
adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot;
Planning a global motion path of the simulation robot based on virtual environment information in the three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in the real world where the robot is located;
planning a local motion attitude of the simulation robot in a preset range of the simulation pose according to the local real environment information and the global motion path;
and controlling the robot to move according to the local motion attitude.
2. The method of claim 1, wherein the pose comprises initial position coordinates of the robot, and accordingly the simulation pose comprises simulated initial position coordinates of the simulated robot, and wherein the planning of the global motion path of the simulated robot based on the virtual environment information in the three-dimensional simulation map model comprises:
planning a plurality of initial global motion paths from the simulation initial position coordinates to simulation target position coordinates based on virtual environment information in the three-dimensional simulation map model, wherein the simulation target position coordinates are the mapping result of the target position coordinates of the robot in the three-dimensional simulation map model;
And determining the global motion path from the plurality of initial global motion paths according to the test result of the movement of the simulation robot according to the plurality of initial global motion paths.
3. The method of claim 1, wherein the global motion path comprises a plurality of ordered position coordinates, and the planning of the local motion pose of the simulated robot within the preset range of the simulation pose according to the local real environment information and the global motion path comprises:
determining a local position coordinate sequence within the preset range from the plurality of ordered position coordinates;
determining local starting point coordinates and local end point coordinates from the local position coordinate sequence;
and determining a local motion attitude of the simulation robot according to the local real environment information, the local starting point coordinate and the local end point coordinate, wherein the local motion attitude is used for controlling the simulation robot to reach the local end point coordinate from the local starting point coordinate.
4. The method of claim 3, wherein determining the local motion pose of the simulated robot based on the local real environment information, the local start point coordinates, and the local end point coordinates comprises:
And inputting the local real environment information, the local starting point coordinates and the local end point coordinates into a trained motion decision model to obtain a local motion attitude output by the trained motion decision model.
5. The method of claim 3, wherein determining the local motion pose of the simulated robot based on the local real environment information, the local start point coordinates, and the local end point coordinates comprises:
inputting the local real environment information, the local starting point coordinates and the local end point coordinates into a trained motion decision model to obtain a plurality of initial local motion postures output by the trained motion decision model;
and determining the local motion attitude from the plurality of initial local motion attitudes according to the test result of the motion of the simulation robot according to the plurality of initial local motion attitudes.
6. The method of claim 4, wherein the training process of the motion decision model comprises:
acquiring a local virtual environment information sample of a simulation robot in a preset range of a simulation pose sample in a three-dimensional simulation map model sample, a local starting point coordinate sample and a local end point coordinate sample in the preset range;
Inputting the local virtual environment information sample, the local starting point coordinate sample and the local end point coordinate sample into a motion decision model to be trained to obtain a local motion attitude result output by the motion decision model to be trained;
and adjusting the training parameters of the motion decision model to be trained according to the result of the movement of the simulation robot in the three-dimensional simulation map model sample according to the local motion posture result.
7. The method according to any one of claims 1-6, further comprising:
and updating the virtual environment information in the three-dimensional simulation map model according to the environment information acquired by the robot in real time and/or the environment information acquired by a sensor in the environment in real time, so that the virtual environment information in the three-dimensional simulation map model is consistent with the environment information of the real world.
8. The method of any one of claims 1-6, wherein the three-dimensional simulated map model is a digital twin model.
9. A robot control apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring the pose of the robot and the local real environment information within the preset range of the pose;
The adjusting module is used for adjusting the simulation pose of the simulation robot in the three-dimensional simulation map model according to the pose of the robot so as to enable the simulation pose of the simulation robot to be consistent with the pose of the robot;
the first planning module is used for planning a global motion path of the simulation robot based on virtual environment information in the three-dimensional simulation map model, wherein the virtual environment information in the three-dimensional simulation map model is consistent with environment information in a real world where the robot is located;
the second planning module is used for planning the local motion attitude of the simulation robot in the preset range of the simulation pose according to the local real environment information and the global motion path;
and the control module is used for controlling the robot to move according to the local motion attitude.
10. A robot control apparatus, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210289317.6A CN114571460A (en) | 2022-03-22 | 2022-03-22 | Robot control method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210289317.6A CN114571460A (en) | 2022-03-22 | 2022-03-22 | Robot control method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114571460A true CN114571460A (en) | 2022-06-03 |
Family
ID=81777406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210289317.6A Pending CN114571460A (en) | 2022-03-22 | 2022-03-22 | Robot control method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114571460A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116652968A (en) * | 2023-07-24 | 2023-08-29 | 贵州翰凯斯智能技术有限公司 | Multi-mechanical arm collaborative online simulation method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630146A (en) * | 2009-07-30 | 2010-01-20 | 上海交通大学 | Simulation control system for remote tele-operation of lunar rover |
| CN109814557A (en) * | 2019-01-23 | 2019-05-28 | 西北工业大学 | A kind of robot path planning method that Global motion planning device is leading |
| US20200042656A1 (en) * | 2018-07-31 | 2020-02-06 | Toyota Research Institute, Inc. | Systems and methods for persistent simulation |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN113050649A (en) * | 2021-03-24 | 2021-06-29 | 西安科技大学 | Remote control system and method for inspection robot driven by digital twin |
| CN113791616A (en) * | 2021-08-25 | 2021-12-14 | 深圳优地科技有限公司 | Path planning method, device, robot and storage medium |
| CN113885506A (en) * | 2021-10-18 | 2022-01-04 | 武汉联影智融医疗科技有限公司 | Robot obstacle avoidance method and device, electronic equipment and storage medium |
| CN114003035A (en) * | 2021-10-28 | 2022-02-01 | 山东新一代信息产业技术研究院有限公司 | Method, device, equipment and medium for autonomous navigation of robot |
| CN115857504A (en) * | 2022-12-02 | 2023-03-28 | 苏州英特雷真智能科技有限公司 | DWA-based robot local path planning method, equipment and storage medium in narrow environment |
-
2022
- 2022-03-22 CN CN202210289317.6A patent/CN114571460A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630146A (en) * | 2009-07-30 | 2010-01-20 | 上海交通大学 | Simulation control system for remote tele-operation of lunar rover |
| US20200042656A1 (en) * | 2018-07-31 | 2020-02-06 | Toyota Research Institute, Inc. | Systems and methods for persistent simulation |
| CN109814557A (en) * | 2019-01-23 | 2019-05-28 | 西北工业大学 | A kind of robot path planning method that Global motion planning device is leading |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN113050649A (en) * | 2021-03-24 | 2021-06-29 | 西安科技大学 | Remote control system and method for inspection robot driven by digital twin |
| CN113791616A (en) * | 2021-08-25 | 2021-12-14 | 深圳优地科技有限公司 | Path planning method, device, robot and storage medium |
| CN113885506A (en) * | 2021-10-18 | 2022-01-04 | 武汉联影智融医疗科技有限公司 | Robot obstacle avoidance method and device, electronic equipment and storage medium |
| CN114003035A (en) * | 2021-10-28 | 2022-02-01 | 山东新一代信息产业技术研究院有限公司 | Method, device, equipment and medium for autonomous navigation of robot |
| CN115857504A (en) * | 2022-12-02 | 2023-03-28 | 苏州英特雷真智能科技有限公司 | DWA-based robot local path planning method, equipment and storage medium in narrow environment |
Non-Patent Citations (1)
| Title |
|---|
| 周祖德等: "《数字孪生与智能制造》", 30 May 2020, 武汉理工大学出版社, pages: 178 - 182 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116652968A (en) * | 2023-07-24 | 2023-08-29 | 贵州翰凯斯智能技术有限公司 | Multi-mechanical arm collaborative online simulation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | 2D Lidar‐Based SLAM and Path Planning for Indoor Rescue Using Mobile Robots | |
| CN111442722B (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| O'Kelly et al. | F1/10: An open-source autonomous cyber-physical platform | |
| CN111968262B (en) | Semantic intelligent substation inspection operation robot navigation system and method | |
| Xie et al. | Learning with stochastic guidance for robot navigation | |
| CN110794844B (en) | Automatic driving method, device, electronic equipment and readable storage medium | |
| Denysyuk et al. | Development of mobile robot using LIDAR technology based on Arduino controller | |
| CN115222808B (en) | Positioning method and device based on unmanned aerial vehicle, storage medium and electronic equipment | |
| CN112580582B (en) | Action learning method, action learning device, action learning medium and electronic equipment | |
| CN112581535B (en) | Robot positioning method, device, storage medium and electronic equipment | |
| CN110347035A (en) | Method for autonomous tracking and device, electronic equipment, storage medium | |
| KR20240052808A (en) | Multi-robot coordination using graph neural networks | |
| CN114488848A (en) | Unmanned aerial vehicle autonomous flight system and simulation experiment platform for indoor building space | |
| CN115731531A (en) | Object trajectory prediction | |
| Ahmed Abdulsaheb et al. | Real‐Time SLAM Mobile Robot and Navigation Based on Cloud‐Based Implementation | |
| CN114571460A (en) | Robot control method, device and storage medium | |
| Xu et al. | Automated labeling for robotic autonomous navigation through multi-sensory semi-supervised learning on big data | |
| CN113848893A (en) | Robot navigation method, device, equipment and storage medium | |
| Pokhrel | Drone obstacle avoidance and navigation using artificial intelligence | |
| CN111708283B (en) | Robot simulation method, equipment and computer readable storage medium | |
| Artunedo et al. | Advanced co-simulation framework for cooperative maneuvers among vehicles | |
| Xu et al. | Avoidance of manual labeling in robotic autonomous navigation through multi-sensory semi-supervised learning | |
| Sung et al. | Graph-based motor primitive generation framework: UAV motor primitives by demonstration-based learning | |
| KR102368734B1 (en) | Drone and drone control methods | |
| Takeda et al. | Initial Localization of Mobile Robot Based on Expansion Resetting Without Manual Pose Adjustment in Robot Challenge Experiment |
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 |