NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors
This addresses the problem of limited generalizability in robot manipulation for household and factory tasks, though it appears incremental as it builds on existing NOD and TAMP paradigms.
The paper tackles the challenge of solving complex long-horizon manipulation tasks in diverse settings by combining Neural Object Descriptors (NODs) with Task and Motion Planning (TAMP), resulting in a framework that outperforms prior methods on new tasks and handles real-world applications like tool-use and insertion.
Solving complex manipulation tasks in household and factory settings remains challenging due to long-horizon reasoning, fine-grained interactions, and broad object and scene diversity. Learning skills from demonstrations can be an effective strategy, but such methods often have limited generalizability beyond training data and struggle to solve long-horizon tasks. To overcome this, we propose to synergistically combine two paradigms: Neural Object Descriptors (NODs) that produce generalizable object-centric features and Task and Motion Planning (TAMP) frameworks that chain short-horizon skills to solve multi-step tasks. We introduce NOD-TAMP, a TAMP-based framework that extracts short manipulation trajectories from a handful of human demonstrations, adapts these trajectories using NOD features, and composes them to solve broad long-horizon, contact-rich tasks. NOD-TAMP solves existing manipulation benchmarks with a handful of demonstrations and significantly outperforms prior NOD-based approaches on new tabletop manipulation tasks that require diverse generalization. Finally, we deploy NOD-TAMP on a number of real-world tasks, including tool-use and high-precision insertion. For more details, please visit https://nodtamp.github.io/.