What's the effect of DR on results in simulation and on the real robot?Īs this is mostly an experimental paper, it will be valuable if the authors publish the code and the experimental setup enabling to reproduce their results. As learning in simulation is claimed as a contribution, I was expecting to see an ablation study for domain randomization (DR). Experimental validation is mostly convincing. Taskfabric to zaawansowany menader zada zaprojektowany zarówno z myl o uytkowniku domowym jak i profesjonalistach. The paper is clearly written and provides many details. Virtual Conference Presentation Paper Reviews Review 2 Code, data, videos, and supplementary material are available at. RGBD data yields an 80% improvement in fabric folding success rate over pure RGB data. Furthermore, we find that leveraging depth significantly improves performance. We experimentally evaluate VSF on multi-step fabric smoothing and folding tasks against 5 baseline methods in simulation and on the da Vinci Research Kit (dVRK) surgical robot without any demonstrations at train or test time. We introduce VisuoSpatial Foresight (VSF), which builds on prior work by learning visual dynamics on domain randomized RGB images and depth maps simultaneously and completely in simulation. We extend the Visual Foresight framework to learn fabric dynamics that can be efficiently reused to accomplish different fabric manipulation tasks with a single goal-conditioned policy. Existing fabric manipulation techniques, however, are designed for specific tasks, making it difficult to generalize across different but related tasks. Robotic fabric manipulation has applications in home robotics, textiles, senior care and surgery. Ryan Hoque, Daniel Seita, Ashwin Balakrishna, Adi Ganapathi, Ajay Tanwani, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg To accomplish this task, fabric material properties must be determined and related to the performance of the handling system using selected fabrics at. VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |