Check out our work on agentic planning for mobile- and loco-manipulation at CoRL next week! We combine agents’ flexibility and common-sense reasoning with robot planners’ time and token efficiency, enabling safe, correct zero-shot execution on new tasks over long horizons.
Coding agents that call robot tools directly mostly work on fully observable tabletops. Can an agent solve long-horizon mobile manipulation under partial observability, with the target inside a fridge or blocked by other objects, zero-shot and without rehearsal in simulation?
We
