MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization
arXiv:2607.26315
MoMo is a two-stage imitation‑learning system that uses spatiotemporal action tokenization and a behavior‑cloning transformer to let robots vary their manipulation style (steady, dynamic, etc.) via a continuous motion‑mode condition, enabling reuse of motion modes across different tasks.
Abstract
To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interaction setting. We ask whether this execution-level variation can be learned as a reusable behavioral factor shared across tasks. We present \textbf{MoMo}, a two-stage imitation-learning framework consisting of a spatiotemporal action tokenizer and a behavior-cloning transformer that takes task and a continuous motion-mode condition as inputs. Across six real-robot manipulation tasks, varying this condition produces steady, dynamic, and intermediate behaviors that human raters can distinguish and that differ in joint speed, acceleration, and end-effector approach pitch. On tasks demonstrated in only one mode, MoMo transfers the unseen requested mode while largely preserving task success. Together, these results provide evidence of compositional generalization to unseen task--mode combinations and show that motion mode can be reused across tasks to control how a manipulation skill is performed.