CN-122008237-A - Robot teaching method based on sphere bounding box and related equipment

CN122008237ACN 122008237 ACN122008237 ACN 122008237ACN-122008237-A

Abstract

The invention discloses a robot teaching method based on a sphere bounding box and related equipment. The robot teaching method comprises the steps of obtaining a chemical experiment virtual scene corresponding to a real operation environment, collecting motion data of teaching input equipment, driving a virtual robot in the chemical experiment virtual scene to conduct chemical action exercise based on the motion data, updating space occupation information in real time in the motion process of the virtual robot, obtaining collision detection results among all sphere bounding boxes according to the updated space occupation information, and generating control instructions for sending to the real robot according to the collision detection results. The invention abandons the traditional full-grid collision detection, adopts a simplified sphere bounding box model mode to carry out collision detection, realizes low-delay real-time anti-collision early warning, and ensures the stability and safety of the chemical experiment operation process.

Inventors

ZHAI CONG
Ye sichao
SONG KANGKANG
XIAO JIANGJIAN
HUANG KAIXIN

Assignees

中国科学院宁波材料技术与工程研究所

Dates

Publication Date: 20260512
Application Date: 20260331

Claims (10)

1. The robot teaching method based on the sphere bounding box is characterized by comprising the following steps of: The method comprises the steps of obtaining a chemical experiment virtual scene corresponding to a real working environment, wherein the chemical experiment virtual scene comprises space occupation information of a virtual robot model, a chemical experiment equipment model and a sphere bounding box, and the space occupation information is used for indicating a motion part of the virtual robot model and a space occupation range of experimental equipment in the chemical experiment equipment model in the chemical experiment virtual scene; Acquiring motion data of a teaching input device, and driving a virtual robot in the chemical experiment virtual scene to perform chemical action exercise based on the motion data; The method comprises the steps of carrying out real-time updating on space occupation information in the motion process of a virtual robot, obtaining collision detection results among all sphere bounding boxes according to the updated space occupation information, and generating control instructions for sending to a real robot according to the collision detection results.
2. The robot teaching method according to claim 1, wherein the sphere bounding box comprises a dynamic sphere bounding box and a static environment sphere bounding box, the dynamic sphere bounding box is a dynamic virtual sphere which peripherally wraps one or more target positions of a tail end clamping jaw of a virtual robot model, the static environment sphere bounding box is a static virtual sphere which peripherally wraps test equipment, and the dynamic virtual sphere and the static virtual sphere are larger than the actual geometric outline of corresponding objects.
3. The robot teaching method according to claim 2, wherein the acquiring the collision detection result between the sphere bounding boxes according to the updated space occupation information comprises: Acquiring distance data between sphere centers of any two sphere bounding boxes according to the updated space occupation information, and considering a collision detection result between the two sphere bounding boxes as triggering early warning when the distance data is smaller than a corresponding warning threshold value; The method further comprises the steps of switching the visual state of the virtual small ball with the collision detection result in the virtual scene triggering early warning, and/or generating warning information and sending the warning information to warning equipment.
4. The robot teaching method according to claim 3, wherein when the collision detection result is a trigger pre-warning, the generating a control command for transmitting to the real robot according to the collision detection result includes generating a forced blocking command and transmitting to the real robot.
5. The robot teaching method according to claim 3, wherein when the collision detection result is not a trigger pre-warning, the generating a control instruction for transmission to the real robot according to the collision detection result comprises: And planning a smooth track between the current angle and the target angle of the terminal clamping jaw corresponding to the real robot by utilizing a polynomial interpolation algorithm according to the discrete joint angle data of the terminal clamping jaw corresponding to the collision detection result, generating a control instruction and sending the control instruction to the real robot.
6. The robot teaching method according to claim 1, characterized in that the method further comprises: When the virtual robot moves to a position where the vision is blocked by an environmental object in a chemical experiment virtual scene, the environmental object is used as an obstacle, and the transparent state of the obstacle is adjusted, so that the tail end clamping jaw of the virtual robot and the experimental equipment acted by the tail end clamping jaw are visible.
7. An electronic device comprising one or more processors and a memory, one or more programs stored in the memory and configured to perform the method of any of claims 1-6 by the one or more processors.
8. A robot teaching system, characterized in that it comprises the electronic device of claim 7.
9. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by at least one processor, implements the steps of the method of any of claims 1-6.
10. A computer program product, characterized in that it comprises a computer program which, when executed by at least one processor, implements the steps of the method according to any of claims 1-6.

Description

Robot teaching method based on sphere bounding box and related equipment Technical Field The invention belongs to the technical field of robot control and man-machine interaction, and particularly relates to a robot teaching method based on a sphere bounding box and related equipment. Background With the development of laboratory automation, double-arm cooperative robots are increasingly being used in chemical experiments to perform complex tasks such as hazardous liquid dumping, multi-tube mixing, and the like. However, chemical experimental scenarios are specialized in that the environment is filled with fragile glassware (e.g., beakers, measuring cylinders) and corrosive/flammable liquids, and have extremely high demands on the smoothness and safety of operation. The physical engines used in related art teleoperation or teaching techniques mostly employ full Mesh (Mesh) for collision detection, such as PhysX, bullet. This approach is typically binarized, i.e. the collision is fed back only when the object models actually overlap, and the operator cannot be informed about the impending collision before it occurs, resulting in the operator not getting up to react. Meanwhile, high-fidelity Mesh collision detection consumes huge computing resources. In the case of high dynamic motion of both arms, complex grid operation can pull down the simulation frame rate, resulting in increased communication delay between the virtual and real terminals. This delay is manifested as motion stuck or overshoot jitter on the real robot arm, which can easily lead to chemical liquid spills or glassware breakage. That is, related teleoperation or teaching techniques lack active early warning mechanisms, and complex grid operations cause calculation delays to cause real mechanical arm jitter, which affect the stability and safety of operation. Accordingly, there is a need to provide a robot teaching method based on a sphere bounding box and related apparatus. Disclosure of Invention The invention mainly aims to provide a robot teaching method based on a sphere bounding box and related equipment, so as to overcome the defects of the prior art. In order to achieve the above object, the present invention adopts the following technical scheme: The embodiment of the invention provides a robot teaching method based on a sphere bounding box, which comprises the following steps: The method comprises the steps of obtaining a chemical experiment virtual scene corresponding to a real working environment, wherein the chemical experiment virtual scene comprises space occupation information of a virtual robot model, a chemical experiment equipment model and a sphere bounding box, and the space occupation information is used for indicating a motion part of the virtual robot model and a space occupation range of experimental equipment in the chemical experiment equipment model in the chemical experiment virtual scene; Acquiring motion data of a teaching input device, and driving a virtual robot in the chemical experiment virtual scene to perform chemical action exercise based on the motion data; The method comprises the steps of carrying out real-time updating on space occupation information in the motion process of a virtual robot, obtaining collision detection results among all sphere bounding boxes according to the updated space occupation information, and generating control instructions for sending to a real robot according to the collision detection results. In a preferred embodiment, the sphere bounding box comprises a dynamic sphere bounding box and a static environment sphere bounding box, wherein the dynamic sphere bounding box is a dynamic virtual small sphere which peripherally wraps one or more target positions of the tail end clamping jaw of the virtual robot model, the static environment sphere bounding box is a static virtual small sphere which peripherally wraps test equipment, and the dynamic virtual small sphere and the static virtual small sphere are larger than the actual geometric outline of corresponding objects. In a preferred embodiment, the obtaining the collision detection result between the sphere bounding boxes according to the updated space occupation information includes: Acquiring distance data between sphere centers of any two sphere bounding boxes according to the updated space occupation information, and considering a collision detection result between the two sphere bounding boxes as triggering early warning when the distance data is smaller than a corresponding warning threshold value; The method further comprises the steps of switching the visual state of the virtual small ball with the collision detection result in the virtual scene triggering early warning, and/or generating warning information and sending the warning information to warning equipment. In a preferred embodiment, when the collision detection result is triggering pre-warning, the control instruction for sending to the real robot is generated