Data-efficient Model Learning and Prediction for Contact-rich Manipulation Tasks
This addresses data-efficient model learning for contact-rich manipulation in robotics, which is an incremental improvement over existing methods.
The paper tackles learning forward dynamics models for contact-rich manipulation tasks, focusing on discontinuous dynamics and data-efficiency, and demonstrates a clear advantage over baselines in low data regimes on tasks like a moving block and a 7-DOF robot.
In this letter, we investigate learning forward dynamics models and multi-step prediction of state variables (long-term prediction) for contact-rich manipulation. The problems are formulated in the context of model-based reinforcement learning (MBRL). We focus on two aspects-discontinuous dynamics and data-efficiency-both of which are important in the identified scope and pose significant challenges to State-of-the-Art methods. We contribute to closing this gap by proposing a method that explicitly adopts a specific hybrid structure for the model while leveraging the uncertainty representation and data-efficiency of Gaussian process. Our experiments on an illustrative moving block task and a 7-DOF robot demonstrate a clear advantage when compared to popular baselines in low data regimes.