A Vision-Based Collision Sensing Method for Stable Circular Object Grasping with A Soft Gripper System
🤖 AI Summary
Flexible grippers often suffer from unstable grasping of cylindrical objects under external collisions. To address this, this paper proposes a real-time collision perception and response method leveraging an “eye-in-hand” wide-angle vision system. By analyzing high-frame-rate image sequences to track fingertip–object relative motion trajectories, we construct a lightweight optical flow feature model enabling millisecond-level identification of collision direction and intensity. An adaptive obstacle-avoidance motion planning strategy dynamically modulates grasping force and end-effector pose upon collision detection. The system integrates a soft gripper, collaborative robotic arm, and embedded vision module—requiring no additional sensors. Experimental results demonstrate an average response latency of <35 ms, 96.2% accuracy in collision direction classification, and significantly improved grasping success rate and system robustness under multi-angle and multi-intensity collision scenarios.
Application Category
📝 Abstract
External collisions to robot actuators typically pose risks to grasping circular objects. This work presents a vision-based sensing module capable of detecting collisions to maintain stable grasping with a soft gripper system. The system employs an eye-in-palm camera with a broad field of view to simultaneously monitor the motion of fingers and the grasped object. Furthermore, we have developed a collision-rich grasping strategy to ensure the stability and security of the entire dynamic grasping process. A physical soft gripper was manufactured and affixed to a collaborative robotic arm to evaluate the performance of the collision detection mechanism. An experiment regarding testing the response time of the mechanism confirmed the system has the capability to react to the collision instantaneously. A dodging test was conducted to demonstrate the gripper can detect the direction and scale of external collisions precisely.
Problem
Research questions and friction points this paper is trying to address.
Detect collisions for stable grasping of circular objects
Monitor finger and object motion with vision system
Ensure dynamic grasping stability with collision-rich strategy
Innovation
Methods, ideas, or system contributions that make the work stand out.
Vision-based collision sensing module
Eye-in-palm camera monitoring
Collision-rich grasping strategy
🔎 Similar Papers
No similar papers found.
