Search papers, labs, and topics across Lattice.
FAR-Dex addresses the challenge of limited data and high-dimensional action spaces in dexterous manipulation by combining few-shot data augmentation in IsaacLab with an adaptive residual policy refinement module. The data augmentation generates diverse, physically plausible trajectories from limited demonstrations, while the residual module refines policies by combining trajectory segments and observation features. Experiments show FAR-Dex improves data quality by 13.4% and task success rates by 7% in simulation, and achieves over 80% success in real-world tasks, demonstrating strong positional generalization.
Overcoming the data scarcity bottleneck in robotic arm-hand coordination, FAR-Dex achieves over 80% real-world success in fine-grained dexterous manipulation tasks.
Achieving human-like dexterous manipulation through the collaboration of multi-fingered hands with robotic arms remains a longstanding challenge in robotics, primarily due to the scarcity of high-quality demonstrations and the complexity of high-dimensional action spaces. To address these challenges, we propose FAR-Dex, a hierarchical framework that integrates few-shot data augmentation with adaptive residual refinement to enable robust and precise arm-hand coordination in dexterous tasks. First, FAR-DexGen leverages the IsaacLab simulator to generate diverse and physically constrained trajectories from a few demonstrations, providing a data foundation for policy training. Second, FAR-DexRes introduces an adaptive residual module that refines policies by combining multi-step trajectory segments with observation features, thereby enhancing accuracy and robustness in manipulation scenarios. Experiments in both simulation and real-world demonstrate that FAR-Dex improves data quality by 13.4% and task success rates by 7% over state-of-the-art methods. It further achieves over 80% success in real-world tasks, enabling fine-grained dexterous manipulation with strong positional generalization.
