Robot Arm Grasping Control with Obstacle-Aware Region Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robot grasp control methods fail when obstacles are present in the designated grasp region, leading to user inconvenience and instability in grasping objects.
Innovation Solution
A control method for robots that divides an object into target and feasible grasp regions, senses orientations of the object and obstacle, and generates a grasp route using stored grasp policies to adaptively adjust joint units and hands for stable grasping, even when obstacles are present.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a designated region of an object is set as a grasp region, then the robot can perform grasping operations, but if any obstacle is present in the grasp region, grasping of the object fails
Solution Approach 1:
The object is divided into multiple grasp regions (target grasp region and alternative grasp regions), allowing the robot to segment the grasping task and switch between different regions based on obstacle presence, thereby maintaining grasping success while adapting to environmental constraints
Solution Approach 2:
The grasp region selection is made dynamic based on real-time obstacle detection and joint unit constraints. The system dynamically switches between target and alternative grasp regions, and between different robot arms, to adapt to changing environmental conditions and maintain reliable grasping
2Manufacturing precision
If the robot attempts to grasp the target region despite obstacles, then it maintains grasping precision, but the grasping operation becomes unstable
Solution Approach 1:
The system uses feedback from obstacle sensing and joint constraint evaluation to determine whether to proceed with target region grasping or switch to alternative regions. This feedback mechanism ensures that grasping precision is maintained only when stability conditions are satisfied, preventing unstable grasping operations
3Reliability
If the user sets a part of the object to be grasped to avoid obstacles, then grasping can be performed, but user inconvenience increases
Solution Approach 1:
The robot autonomously evaluates grasp feasibility by sensing obstacles and joint constraints, and automatically selects appropriate grasp regions and robot arms without requiring user intervention. This self-service capability maintains grasping feasibility while eliminating the inconvenience of manual region setting
Data Source
AI summary
A robot and a control method thereof. The robot has plural robot arms, each having at least one joint unit and a hand, and the control method includes dividing an object into target and feasible grasp regions and storing grasp policies respectively corresponding to the grasp regions, sensing respective orientations of the object, the at least one joint unit, and an obstacle, judging whether or not grasping of the target grasp region is feasible after sensing the orientations, generating a grasp route using the grasp policy for the target grasp region, upon judging that grasping of the target grasp region is feasible, and generating a grasp route using the grasp policy for one of the feasible grasp regions, upon judging that grasping of the target grasp region is not feasible, and controlling the at least one joint unit and the hand to trace the generated grasp route.