Showing 2024Show all
2 papers · 1 filter
cs.RO2024
Learn2Decompose: Learning Problem Decomposition for Efficient Sequential Multi-object Manipulation Planning
Yan Zhang, Teng Xue, Amirreza Razmjoo +1
We present an efficient task and motion replanning approach for sequential multi-object manipulation in dynamic environments. Conventional Task And Motion Planning (TAMP) solvers e…
cs.RO2024
Logic Learning from Demonstrations for Multi-step Manipulation Tasks in Dynamic Environments
Yan Zhang, Teng Xue, Amirreza Razmjoo +1
Learning from Demonstration (LfD) stands as an efficient framework for imparting human-like skills to robots. Nevertheless, designing an LfD framework capable of seamlessly imitati…