用强化学习增强数据集，让机器人抓取成功率提升至80%。
DiffusionRL: Efficient Training of Diffusion Policies for Robotic Grasping Using RL-Adapted Large-Scale Datasets
- 用强化学习优化大规模抓取数据集，提升训练质量。
- 五指机械手抓取任务成功率达80%。
- 无需人工采集数据，适合快速部署于真实场景。
扩散模型在图像、视频和音频生成中已取得成功。近期研究显示其在序列决策与灵巧操作中也具潜力，因其能建模复杂动作分布。然而，数据局限性和场景特异性适应仍是挑战。本文提出一种优化方法，利用强化学习增强的大规模预建数据集训练扩散策略。端到端流程包括：基于RL增强的DexGraspNet数据集、针对五指机械手灵巧操作任务的轻量级扩散策略训练，以及用于验证的姿态采样算法。该流程在三个DexGraspNet物体上实现了80%的成功率。通过消除手动数据采集，本方法降低了机器人领域应用扩散模型的门槛，提升了泛化性与鲁棒性，适用于真实世界应用。
原文摘要 · Abstract (English)
Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action distributions. However, challenges persist due to the data limitations and scenario-specific adaptation needs. In this paper, we address these challenges by proposing an optimized approach to training diffusion policies using large, pre-built datasets that are enhanced using Reinforcement Learning (RL). Our end-to-end pipeline leverages RL-based enhancement of the DexGraspNet dataset, lightweight diffusion policy training on a dexterous manipulation task for a five-fingered robotic hand, and a pose sampling algorithm for validation. The pipeline achieved a high success rate of 80% for three DexGraspNet objects. By eliminating manual data collection, our approach lowers barriers to adopting diffusion models in robotics, enhancing generalization and robustness for real-world applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。