In Gasket Assembly, a deformable gasket must be aligned and pressed into a narrow channel. This task is common for sealing surfaces in the manufacturing of automobiles, appliances, electronics, and other products. Gasket Assembly is a long-horizon, high-precision task and the gasket must align with the channel and be fully pressed in to achieve a secure fit. To compare approaches, we present 4 methods for Gasket Assembly: one policy from deep imitation learning and three procedural algorithms. We evaluate these methods with 100 physical trials. Results suggest that the Binary+ algorithm succeeds in 10/10 on the straight channel whereas the learned policy based on 250 human teleoperated demonstrations succeeds in 8/10 trials and is significantly slower. Code, CAD models, videos, and data can be found at https://berkeleyautomation.github.io/robot-gasket/
@article{arxiv.2408.12593,
title = {Automating Deformable Gasket Assembly},
author = {Simeon Adebola and Tara Sadjadpour and Karim El-Refai and Will Panitch and Zehan Ma and Roy Lin and Tianshuang Qiu and Shreya Ganti and Charlotte Le and Jaimyn Drake and Ken Goldberg},
journal= {arXiv preprint arXiv:2408.12593},
year = {2024}
}
Comments
Content without Appendix accepted for IEEE CASE 2024