Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation
This addresses the challenge of efficiently controlling robots for complex manipulation tasks, offering a novel approach that enhances adaptability and reduces training overhead.
The paper tackled the problem of robotic manipulation by using reinforcement learning to dynamically compose hierarchical object-centric controllers, resulting in improved sample efficiency, zero-shot generalization to novel environments, and successful simulation-to-reality transfer without fine-tuning.
Manipulation tasks can often be decomposed into multiple subtasks performed in parallel, e.g., sliding an object to a goal pose while maintaining contact with a table. Individual subtasks can be achieved by task-axis controllers defined relative to the objects being manipulated, and a set of object-centric controllers can be combined in an hierarchy. In prior works, such combinations are defined manually or learned from demonstrations. By contrast, we propose using reinforcement learning to dynamically compose hierarchical object-centric controllers for manipulation tasks. Experiments in both simulation and real world show how the proposed approach leads to improved sample efficiency, zero-shot generalization to novel test environments, and simulation-to-reality transfer without fine-tuning.