3 accepted papers
A long-standing goal in robotics is a generalist policy that can be deployed zero-shot on new robot embodiments without per-embodiment adaptation. Despite large-scale multi-embodiment pre-training, existing Vision–Language–Action models (VLAs) remain tightly coupled to their training embodiments and…
Given a collaborative high-level task and a team of heterogeneous robots with behaviors to satisfy it, this work focuses on the challenge of automatically adjusting the individual robot behaviors at runtime such that the task is still satisfied. We specifically address scenarios when robots encounte
Active object localization remains a critical challenge for robots, requiring efficient exploration of partially observable environments. However, state-of-the-art robot policies either struggle to generalize beyond demonstration datasets (e.g., imitation learning methods) or fail to generate physic…