arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.09243cs.ROcs.AIcs.LG
收藏

DiffClone:基于扩散驱动策略学习的机器人行为克隆增强

DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning

IIT Kharagpur(印度理工学院卡哈拉格普尔分校);University of Waterloo(滑铁卢大学)

Sabariswaran Mani, Sreyas Venkataraman, Abhranil Chandra, Adyan Rizvi, Yash Sirvi, Soumojit Bhattacharya, Aritra Hazra

AI总结:

针对机器人学习计算密集和硬件依赖问题,提出 DiffClone 离线算法,利用条件扩散增强行为克隆,在 TOTO 基准和真实机器人上验证,MOCO 微调的 ResNet50 表现最佳。

摘要:

机器人学习任务极其计算密集且依赖于特定硬件。因此,利用多样化的离线演示数据集来训练机器人操作智能体,是应对这些挑战的极具吸引力的途径。Train-Offline-Test-Online (TOTO) 基准提供了一个精心整理的开放源码离线训练数据集,主要由专家数据组成,并包含常见离线强化学习和行为克隆智能体的基准分数。在本文中,我们介绍了 DiffClone,一种通过基于扩散的策略学习增强的行为克隆智能体的离线算法,并在测试时在真实在线物理机器人上评估了我们方法的有效性。这也是我们向 NeurIPS 2023 组织的 Train-Offline-Test-Online (TOTO) 基准挑战赛的官方提交。我们同时实验了预训练的视觉表示和智能体策略。在我们的实验中,我们发现与其他微调表示相比,MOCO 微调的 ResNet50 表现最佳。目标状态条件化和到转移的映射导致成功率和平均奖励的微小增加。至于智能体策略,我们开发了 DiffClone,一种使用条件扩散改进的行为克隆智能体。

英文摘要:

Robot learning tasks are extremely compute-intensive and hardware-specific. Thus the avenues of tackling these challenges, using a diverse dataset of offline demonstrations that can be used to train robot manipulation agents, is very appealing. The Train-Offline-Test-Online (TOTO) Benchmark provides a well-curated open-source dataset for offline training comprised mostly of expert data and also benchmark scores of the common offline-RL and behaviour cloning agents. In this paper, we introduce DiffClone, an offline algorithm of enhanced behaviour cloning agent with diffusion-based policy learning, and measured the efficacy of our method on real online physical robots at test time. This is also our official submission to the Train-Offline-Test-Online (TOTO) Benchmark Challenge organized at NeurIPS 2023. We experimented with both pre-trained visual representation and agent policies. In our experiments, we find that MOCO finetuned ResNet50 performs the best in comparison to other finetuned representations. Goal state conditioning and mapping to transitions resulted in a minute increase in the success rate and mean-reward. As for the agent policy, we developed DiffClone, a behaviour cloning agent improved using conditional diffusion.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑