Incremental Few-Shot Adaptation for Non-Prehensile Object Manipulation using Parallelizable Physics Simulators
This work addresses the challenge of few-shot adaptation for robots in open-world environments, offering an incremental improvement for domain-specific applications like object manipulation.
The paper tackles the problem of enabling robots to adapt quickly to new objects in non-prehensile manipulation tasks by incrementally updating a physics-based dynamics model using a few interaction examples, achieving improved performance in pushing experiments in both simulation and real-world settings.
Few-shot adaptation is an important capability for intelligent robots that perform tasks in open-world settings such as everyday environments or flexible production. In this paper, we propose a novel approach for non-prehensile manipulation which incrementally adapts a physics-based dynamics model for model-predictive control (MPC). The model prediction is aligned with a few examples of robot-object interactions collected with the MPC. This is achieved by using a parallelizable rigid-body physics simulation as dynamic world model and sampling-based optimization of the model parameters. In turn, the optimized dynamics model can be used for MPC using efficient sampling-based optimization. We evaluate our few-shot adaptation approach in object pushing experiments in simulation and with a real robot.