Object-Centric Task and Motion Planning in Dynamic Environments
This addresses the problem of slow re-planning for robots in dynamic environments, offering a more robust solution for real-world manipulation tasks, though it appears incremental as it builds on existing TAMP frameworks.
The paper tackles the problem of Task and Motion Planning (TAMP) failing in dynamic environments by proposing an algorithm that optimizes over Cartesian frames relative to target objects, enabling plans to remain valid during object motion and be executed by reactive controllers. It demonstrates this approach on a torque-controlled robot in pick-and-place tasks, showing adaptation to changes, inaccurate perception, and imprecise control in simulation and real-world settings.
We address the problem of applying Task and Motion Planning (TAMP) in real world environments. TAMP combines symbolic and geometric reasoning to produce sequential manipulation plans, typically specified as joint-space trajectories, which are valid only as long as the environment is static and perception and control are highly accurate. In case of any changes in the environment, slow re-planning is required. We propose a TAMP algorithm that optimizes over Cartesian frames defined relative to target objects. The resulting plan then remains valid even if the objects are moving and can be executed by reactive controllers that adapt to these changes in real time. We apply our TAMP framework to a torque-controlled robot in a pick and place setting and demonstrate its ability to adapt to changing environments, inaccurate perception, and imprecise control, both in simulation and the real world.