Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration
This work addresses the challenge of state representation and policy learning for soft object manipulation in robotics, which is incremental as it builds on graph-based methods and human demonstrations.
The paper tackled the problem of soft object manipulation in robotics by introducing a dynamic heterogeneous graph-based model for learning goal-oriented policies, and demonstrated its efficacy in a dough rolling task with experiments in simulation and on a real-world humanoid robot, showing superiority in achieving human-like behavior.
Soft object manipulation poses significant challenges for robots, requiring effective techniques for state representation and manipulation policy learning. State representation involves capturing the dynamic changes in the environment, while manipulation policy learning focuses on establishing the relationship between robot actions and state transformations to achieve specific goals. To address these challenges, this research paper introduces a novel approach: a dynamic heterogeneous graph-based model for learning goal-oriented soft object manipulation policies. The proposed model utilizes graphs as a unified representation for both states and policy learning. By leveraging the dynamic graph, we can extract crucial information regarding object dynamics and manipulation policies. Furthermore, the model facilitates the integration of demonstrations, enabling guided policy learning. To evaluate the efficacy of our approach, we designed a dough rolling task and conducted experiments using both a differentiable simulator and a real-world humanoid robot. Additionally, several ablation studies were performed to analyze the effect of our method, demonstrating its superiority in achieving human-like behavior.