2023/03/02 by Yuhong Deng, Deng, Yuhong, Kai Mo +5 · 3 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Human Pose and Action Recognition #Multimodal Machine Learning Applications #Robot Manipulation and Learning #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2303.01310
openalex publication_date 2023/03/02 · openalex created_date 2023/03/05 · openalex updated_date 2026/07/28
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.