OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation
This work addresses robust robot manipulation for robotics applications, representing an incremental advance by adapting an existing control method with data-driven techniques.
The paper tackles the problem of robot manipulation by proposing OSCAR, a data-driven variant of Operational Space Control that compensates for modeling errors by inferring dynamics parameters from online trajectories, resulting in robust zero-shot performance and rapid adaptation with substantial improvements over baselines in simulated tasks.
Learning performant robot manipulation policies can be challenging due to high-dimensional continuous actions and complex physics-based dynamics. This can be alleviated through intelligent choice of action space. Operational Space Control (OSC) has been used as an effective task-space controller for manipulation. Nonetheless, its strength depends on the underlying modeling fidelity, and is prone to failure when there are modeling errors. In this work, we propose OSC for Adaptation and Robustness (OSCAR), a data-driven variant of OSC that compensates for modeling errors by inferring relevant dynamics parameters from online trajectories. OSCAR decomposes dynamics learning into task-agnostic and task-specific phases, decoupling the dynamics dependencies of the robot and the extrinsics due to its environment. This structure enables robust zero-shot performance under out-of-distribution and rapid adaptation to significant domain shifts through additional finetuning. We evaluate our method on a variety of simulated manipulation problems, and find substantial improvements over an array of controller baselines. For more results and information, please visit https://cremebrule.github.io/oscar-web/.