CN-122008258-A - Safety action execution method of robot with body and robot system with body

CN122008258ACN 122008258 ACN122008258 ACN 122008258ACN-122008258-A

Abstract

The present application relates to a method for executing a safety motion of a robot with a body and a robot system with a body. The method comprises the steps of receiving a task instruction, executing a task indicated by the task instruction, recording event information of a collision event if the collision event is detected through a collision switch of the robot body in the process of executing the task, arranging a plurality of event information according to time sequence to form an event information sequence, wherein the event information comprises a collision position and corresponding collision time, generating collision density information corresponding to a grid map of the robot body according to a first subsequence in a first sliding time window in the event information sequence, wherein the collision density information comprises collision density corresponding to each grid in the grid map, and executing a safety action when the collision density information represents that a first safety action executing condition is met. By adopting the method, the safety can be improved.

Inventors

Request for anonymity
Request for anonymity
LI ZHICHEN
PAN YANG
LI JIANGANG

Assignees

卧安科技(深圳)有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (11)

1. A method of performing a safety action for an autonomous robot, the method comprising: receiving a task instruction and executing a task indicated by the task instruction; in the process of executing the task, if a collision event is detected through a collision switch of the robot with body, recording event information of the collision event, wherein a plurality of event information are arranged according to a time sequence to form an event information sequence, and the event information comprises a collision position and corresponding collision time; Generating collision density information corresponding to a grid map of the robot with body according to a first subsequence in a first sliding time window in the event information sequence, wherein the collision density information comprises collision density corresponding to each grid in the grid map; and executing the safety action under the condition that the collision density information representation meets the first safety action execution condition.
2. The method of claim 1, wherein generating collision density information corresponding to the grid map of the autonomous robot from a first sub-sequence within a first sliding time window in the sequence of event information comprises: Determining a first sub-sequence within the first sliding time window from the sequence of event information; Determining, for each grid in the grid map, a collision density corresponding to the grid based on the collision position in the first sub-sequence and the grid position of the grid; And obtaining collision density information corresponding to the grid map according to the collision density corresponding to each grid in the grid map.
3. The method of claim 1, wherein performing a safety action if the collision density information characterizes a first safety action performance condition is met, comprising: Determining a reference collision density under the first sliding time window according to the collision density contained in the collision density information; and executing the safety action when the reference collision density reaches a collision density threshold value.
4. A method according to claim 3, wherein said determining a reference collision density under said first sliding time window from the collision density contained in said collision density information comprises: Determining a maximum collision density from a plurality of target collision densities contained in the collision density information, taking the maximum collision density as the reference collision density; The plurality of target collision densities are all collision densities in the collision density information, or the plurality of target collision densities are collision densities respectively corresponding to a plurality of grids in a target area contained in the grid map.
5. A method according to any one of claims 1 to 4, wherein after receiving a task instruction, the method further comprises: Determining a second sub-sequence in a second sliding time window from the event information sequence, wherein the second time length of the second sliding time window is longer than the first time length of the first sliding time window; And executing the safety action under the condition that the second sub-sequence characterization meets the second safety action execution condition.
6. The method of claim 5, wherein performing a security action if the second subsequence characterization satisfies a second security action execution condition comprises: Determining corresponding collision times and at least one collision time interval in the second sliding time window according to the second subsequence, wherein the collision time interval is a time interval between two adjacent collision events; and triggering the safety action if the collision times are greater than a time threshold or any collision time interval is smaller than a preset interval threshold.
7. The method of any of claims 1 to 4, wherein the executing the task indicated by the task instruction comprises: performing task planning to generate an action sequence based on the task instruction and the current first scene information; And executing corresponding actions according to the sequence of actions to execute the task indicated by the task instruction.
8. The method of claim 7, wherein prior to performing the corresponding actions in the order of the sequence of actions to perform the task indicated by the task instruction, the method further comprises: Determining a collision limit type of each action in the action sequence, wherein the collision limit type comprises a limited collision type or a forbidden collision type, the limited collision type represents that the collision density is not allowed to reach a collision density threshold value in the execution process of the action, and the forbidden collision type represents that collision events are forbidden in the execution process of the action; The generating collision density information corresponding to the grid map of the robot according to the first subsequence in the first sliding time window in the event information sequence includes: for a current action performed, determining a first sub-sequence generated during the execution of the current action and within a first sliding time window from the event information sequence in the case that a collision limit type of the current action is a limited collision type; and generating collision density information corresponding to the grid map of the robot body based on the first subsequence.
9. The method of claim 8, wherein in the process of performing the corresponding actions in the order of the sequence of actions to perform the task indicated by the task instruction, the method further comprises: If a collision event is detected through a collision switch of the robot with body, and the collision limit type of the action executed when the collision event occurs is a forbidden collision type, immediately executing a safety action.
10. The method according to any one of claims 1 to 4, wherein after said performing a security action, the method further comprises: And acquiring current second scene information, and generating a risk record according to the recorded event information and the second scene information, wherein the risk record is used for assisting the robot with the body to carry out task planning.
11. A self-contained robotic system comprising a terminal for sending task instructions to the self-contained robot and a self-contained robot for performing the method of any one of claims 1 to 10.

Description

Safety action execution method of robot with body and robot system with body Technical Field The present application relates to the technical field of a robot, and in particular, to a method for performing a safety motion of a robot and a robot system. Background With the development of artificial intelligence and robotics, the self-contained robot is gradually becoming incorporated into the home environment. For example, in a home environment, the robot body may perform a corresponding task according to an instruction of a user. In the prior art, a force sensor installed at a joint of the robot body is generally used to detect a contact force between the robot body and an external environment, so as to judge a collision event and control contact behavior. The force sensor can provide continuous measurement information of contact force and moment, and is helpful for the robot to recognize micro contact, judge contact strength and safe man-machine interaction. However, the force sensor has high cost and complex structure, and has high requirements on the installation position, the calibration precision and the system bandwidth, so that many self-contained robots with limited cost or limited structure are difficult to configure. Disclosure of Invention In view of the above, it is desirable to provide a safety operation execution method for an autonomous robot and an autonomous robot system that can improve safety. The application provides a safety action execution method of a robot with a body, which comprises the steps of receiving a task instruction, executing a task indicated by the task instruction, recording event information of a collision event if the collision event is detected through a collision switch of the robot with the body in the process of executing the task, arranging a plurality of event information according to time sequence to form an event information sequence, wherein the event information comprises a collision position and corresponding collision time, generating collision density information corresponding to a grid map of the robot with the body according to a first subsequence in a first sliding time window in the event information sequence, wherein the collision density information comprises collision density corresponding to each grid in the grid map, and executing a safety action when the collision density information represents that a first safety action execution condition is met. In some embodiments, the generating collision density information corresponding to the grid map of the robot with body according to the first subsequence in the first sliding time window in the event information sequence includes determining the first subsequence in the first sliding time window from the event information sequence, determining, for each grid in the grid map, collision density corresponding to the grid based on the collision position in the first subsequence and the grid position of the grid, and obtaining collision density information corresponding to the grid map according to the collision density respectively corresponding to each grid in the grid map. In some embodiments, the performing a safety action when the collision density information characterizes that a first safety action performance condition is met includes determining a reference collision density under the first sliding time window according to the collision density contained in the collision density information, and performing the safety action when the reference collision density reaches a collision density threshold. In some embodiments, the determining the reference collision density under the first sliding time window according to the collision density contained in the collision density information includes determining a maximum collision density from a plurality of target collision densities contained in the collision density information, and taking the maximum collision density as the reference collision density, wherein the plurality of target collision densities are all collision densities in the collision density information or are collision densities respectively corresponding to a plurality of grids in a target area contained in the grid map. In some embodiments, after receiving the task instruction, the method further includes determining a second sub-sequence within a second sliding time window from the sequence of event information, the second time duration of the second sliding time window being greater than the first time duration of the first sliding time window, and executing the security action if the second sub-sequence characterizes a second security action execution condition. In some embodiments, the executing the safety action when the second sub-sequence representation meets the second safety action execution condition includes determining, according to the second sub-sequence, a corresponding collision number and at least one collision time interval in the second sliding time window, where the