arXiv Robotics — research abstracts· Octi Zhang, Iretiayo Akinola, Rosario Scalise, Mateo Guaman Castro, Patrick Yin, Tobias Widmer, Miles Macklin, Chris Amevor, Dylan Turpin, Dirk Van Gelder, Jan Carius, Ankur Handa, Gavriel State, Yunrong Guo, Yashraj Narang·· 16 hours agoEditorial score65
AlphaNIST: Emergent Assembly Skills from Binary Task Rewards
AlphaNIST: Emergent Assembly Skills from Binary Task Rewards
Summary
AlphaNIST explores whether sparse binary task rewards can enable robots to learn complex assembly tasks without explicit guidance. The method trains a single policy across all 20 assembly tasks on the NIST Assembly Task Board #1, achieving 98.2% success without demonstrations, progress shaping, or per-task tuning. The learned policies exhibit planning-like behaviors such as reorienting parts and managing multiple assembly sequences.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
Source：arXiv Robotics — research abstracts · arxiv.org