Robot End Effector Grip Selection From Hand Joint Flexion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote control systems struggle to accurately reflect the movement of a human hand, particularly in gripping and manipulating objects, due to difficulties in capturing and interpreting the operator's hand movements and intentions.
Innovation Solution
A remote control system that includes an acquisition part for sensor data, an end effector capable of multiple gripping methods, a gripping method table, and a selector that determines the appropriate gripping method based on joint flexion angles and intention estimation, using models trained on human hand shapes and behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional remote control systems are used to operate robotic end effectors, then the system structure is simple, but the ability to accurately reflect human hand movements and intentions is insufficient
Solution Approach 1:
The system segments hand movement analysis into multiple independent components: joint flexion angle detection, fingertip distance measurement, and object size comparison. Each component is processed separately through dedicated algorithms, allowing complex hand gestures to be broken down into manageable analytical units that can be independently optimized and combined.
Solution Approach 2:
The system introduces an intermediary processing layer between the operator's hand movements and the robotic end effector control. This intermediary layer includes the gripping method table and selection algorithm that translate human hand gestures into standardized robotic commands, enabling accurate intention recognition without direct one-to-one mapping.
2Adaptability or versatility
If multiple gripping methods are implemented in the end effector, then the versatility of object manipulation is improved, but the complexity of control system increases
Solution Approach 1:
The system pre-establishes a gripping method table that contains multiple gripping methods and their corresponding conditions before operation begins. During actual use, the system only needs to query and select from this pre-prepared table based on detected hand gestures, eliminating the need for complex real-time decision-making algorithms and reducing computational burden.
Solution Approach 2:
The system uses parameter changes in hand posture (joint flexion angles, fingertip distances) to select different gripping methods from the table. By mapping specific parameter ranges to specific gripping methods, the system achieves versatile object manipulation through simple parameter-based selection rather than complex control logic.
3Measurement precision
If intention estimation based on fingertip distance and object size comparison is implemented, then the accuracy of operator intention recognition is improved, but the computational requirements increase
Solution Approach 1:
The system implements partial intention recognition by focusing on specific key parameters (fingertip distance and object size) rather than analyzing all possible hand movement parameters. This selective approach provides sufficient intention recognition accuracy for gripping tasks without requiring computationally exhaustive analysis of every hand gesture dimension.
Data Source
AI summary
A remote control system, in which an operator remotely operates a robot having an end effector that is capable of gripping and manipulating an object, includes an acquisition part acquiring information on a state of the operator operating the robot; an end effector capable of performing multiple types of gripping methods; a gripping method table in which the gripping methods are stored; and a gripping method selector selecting the gripping method from the gripping method table based on a joint flexion angle of the operator obtained from operator information of the acquisition part.