Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the multi-task learning performance and can not generalize to new tasks. Thus, we adapt language instruction to specify deformable object manipulation tasks and propose a learning framework. We first design a unified Transformer-based architecture to understand multi-modal data and output picking and placing action. Besides, we have introduced the visible connectivity graph to tackle nonlinear dynamics and complex configuration of the deformable object. Both simulated and real experiments have demonstrated that the proposed method is effective and can generalize to unseen instructions and tasks. Compared with the state-of-the-art method, our method achieves higher success rates (87.2% on average) and has a 75.6% shorter inference time. We also demonstrate that our method performs well in real-world experiments.
We design a unified Transformer-based model architecture to understand the multi-modal data and output picking and placing action with task completion prediction. We introduce a visible connectivity graph to tackle deformable objects’ complex configurations and dynamics.
We evaluate the performance of our framework on a kinova robot with a standard two-finger Robotiq gripper. The experiments include 5 types of language-conditioned manipulation tasks.
@article{deng2024langdef,
title = {Learning Language-Conditioned Deformable Object Manipulation with Graph Dynamics},
author = {Yuhong Deng and Kai Mo and Chongkun Xia and Xueqian Wang},
journal = {arXiv preprint arXiv: Arxiv-2303.01310},
year = {2024},
}