InsertionNet -- A Scalable Solution for Insertion
Oren Spector, Dotan Di Castro

TL;DR
This paper introduces InsertionNet, a scalable and robust learning-based method that combines visual and force data to perform multiple insertion tasks efficiently, even with variations and complex assembly scenarios.
Contribution
The paper presents a novel regression-based approach that integrates visual and force inputs, enabling scalable and robust insertion policies for diverse assembly tasks.
Findings
Successfully scaled to 16 insertion tasks in under 10 minutes
Policies are robust to socket and peg variations
Effective in complex multi-insertion assembly scenarios
Abstract
Complicated assembly processes can be described as a sequence of two main activities: grasping and insertion. While general grasping solutions are common in industry, insertion is still only applicable to small subsets of problems, mainly ones involving simple shapes in fixed locations and in which the variations are not taken into consideration. Recently, RL approaches with prior knowledge (e.g., LfD or residual policy) have been adopted. However, these approaches might be problematic in contact-rich tasks since interaction might endanger the robot and its equipment. In this paper, we tackled this challenge by formulating the problem as a regression problem. By combining visual and force inputs, we demonstrate that our method can scale to 16 different insertion tasks in less than 10 minutes. The resulting policies are robust to changes in the socket position, orientation or peg color,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning · Reinforcement Learning in Robotics · Hand Gesture Recognition Systems
