6 papers
Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness
Ziou Hu, Xiangtong Yao, Yuan Meng +2
Diffusion policies excel at visuomotor control but often fail catastrophically under severe out-of-distribution (OOD) disturbances, such as unexpected object displacements or visua…
Growing with Your Embodied Agent: A Human-in-the-Loop Lifelong Code Generation Framework for Long-Horizon Manipulation Skills
Yuan Meng, Zhenguo Sun, Max Fest +3
Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing…
Inference-stage Adaptation-projection Strategy Adapts Diffusion Policy to Cross-manipulators Scenarios
Xiangtong Yao, Yirui Zhou, Yuan Meng +7
Diffusion policies are powerful visuomotor models for robotic manipulation, yet they often fail to generalize to manipulators or end-effectors unseen during training and struggle t…
Pretrained Bayesian Non-parametric Knowledge Prior in Robotic Long-Horizon Reinforcement Learning
Yuan Meng, Xiangtong Yao, Kejia Chen +4
Reinforcement learning (RL) methods typically learn new tasks from scratch, often disregarding prior knowledge that could accelerate the learning process. While some methods incorp…
Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation
Yuan Meng, Xiangtong Yao, Haihui Ye +6
Embodied long-horizon manipulation requires robotic systems to process multimodal inputs-such as vision and natural language-and translate them into executable actions. However, ex…
Pick-and-place Manipulation Across Grippers Without Retraining: A Learning-optimization Diffusion Policy Approach
Xiangtong Yao, Yirui Zhou, Yuan Meng +7
Current robotic pick-and-place policies typically require consistent gripper configurations across training and inference. This constraint imposes high retraining or fine-tuning co…