Robot Gripper Force Control Using Tactile Damage Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems struggle to grip various fragile objects without specialized soft grippers, and often cause damage due to varying softness characteristics of target objects.
Innovation Solution
A control device connected to a robot with an end effector, tactile sensors, and a prediction model that acquires contact forces and predicts when a specific effect occurs on the target object, allowing for controlled gripping without damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If specialized soft grippers are used to grip fragile objects, then gripping capability is improved, but device complexity increases
Solution Approach 1:
The patent applies universality by using a standard rigid gripper structure that can handle multiple types of objects (fragile, soft, hard) through software-based control rather than requiring specialized grippers for each object type. The prediction model enables the same hardware to adapt to different object characteristics dynamically.
Solution Approach 2:
The patent replaces the mechanical complexity of specialized soft grippers with a computational system consisting of tactile sensors, prediction models, and control algorithms. The prediction model uses machine learning to anticipate damage risks, substituting mechanical adaptation with intelligent control.
2Reliability
If gripping force is increased to secure fragile objects, then gripping reliability is improved, but object damage increases
Solution Approach 1:
The prediction model performs preliminary assessment of damage risk before actual damage occurs. By predicting the time when damage will occur based on current gripping force and object characteristics, the system can proactively adjust gripping force to prevent damage while maintaining secure grip.
Solution Approach 2:
The system continuously monitors tactile sensor data and feeds this information back to the prediction model, which adjusts the gripping force in real-time. This closed-loop feedback ensures the gripping force remains within safe limits while maintaining reliable grip on fragile objects.
3Device complexity
If standard rigid grippers are used to grip fragile objects, then device complexity is reduced, but gripping reliability deteriorates
Solution Approach 1:
The system dynamically adjusts gripping force based on real-time prediction of damage risk. Rather than using a fixed gripping force, the control unit continuously modifies the force applied by the rigid gripper according to the prediction model's assessment, enabling reliable grip on fragile objects with standard hardware.
Solution Approach 2:
The system changes the gripping force parameter dynamically based on prediction results. By adjusting this critical parameter in real-time according to the predicted damage time and object characteristics, the rigid gripper achieves reliable gripping of fragile objects without requiring structural modifications.
Data Source
AI summary
The present disclosure provides a control device connected to a robot including an end effector acting on a target object, a drive source for driving the end effector or a robot body, and a tactile sensor provided to the end effector, and that controls the drive source to perform an action on the target object.