Robot adapts movement plans based on its physical state during tasks
Body-Grounded Replanning for Physically Adaptive Manipulation
Robotics
Summary
Manipulating objects is tricky for robots because they not only need to think about the outside world but also about their own body. Sometimes a movement plan looks good but actually puts too much strain on the robot's joints or is hard to perform. The authors designed a method where the robot can notice changes in its body, like joint stress or limited motion, and then change its strategy while still aiming for the same goal. They tested this idea on robots reaching and handling objects, showing it helps keep success high while using less effort.
What this means in practice
- •For robotics engineers: Enable robots to adapt high-level manipulation strategies in real time based on their own physical condition to improve task success and efficiency.
- •For manufacturing automation teams: Use robots that dynamically adjust their motion plans to reduce joint strain and handle asymmetric mobility constraints during assembly and material handling.
Authors
Namiko Saito, Hiroshi Kera
Abstract
Manipulation requires not only reasoning about the external environment, but also about the robot's physical condition. A strategy may remain geometrically feasible while becoming physically unsuitable due to increased joint load or limited mobility, yet internal physical state is typically used only for low-level control. We propose body-grounded high-level replanning, which uses internal physical state to adapt manipulation strategies during execution. Body-state events trigger strategy replanning, and an LLM interprets the underlying joint-level state, recent execution statistics, and execution history to select a context-dependent alternative, while leaving the task objective and low-level controller unchanged. We evaluate the framework on a reaching task under controlled load and asymmetric mobility constraints in simulation and on a real robot. Our experiments show that body-grounded replanning maintains high task success while reducing physical effort and enabling more efficient strategy adaptation. Additional contact-rich manipulation experiments demonstrate the applicability of the same replanning interface beyond reaching. These results show that internal physical state can inform not only low-level control, but also high-level decisions about how a manipulation task should be performed.