AquaBot让水下机器人自主操作更高效，自学习能力比人类快41%。
Self-Improving Autonomous Underwater Manipulation
- 用人类示范数据训练基础策略，再通过自优化提升性能。
- 真实场景实验中，自主操作速度比人类快41%。
- 适合水下搜救、垃圾分拣等复杂任务，开源软硬件。
水下机器人操作因复杂的流体动力学和非结构化环境而面临巨大挑战，现有系统大多依赖人工遥控。本文提出AquaBot，一个完全自主的操作系统，结合人类示范的行为克隆与自我学习优化，实现超越人类操作的表现。通过大量真实世界实验，验证了AquaBot在物体抓取、垃圾分拣、救援回收等多种任务中的通用性。实验表明，其自优化策略在速度上比人类操作员提升41%。AquaBot代表了向自主且自改进的水下操作系统的迈进。我们已开源其软硬件实现细节。
原文摘要 · Abstract (English)
Underwater robotic manipulation faces significant challenges due to complex fluid dynamics and unstructured environments, causing most manipulation systems to rely heavily on human teleoperation. In this paper, we introduce AquaBot, a fully autonomous manipulation system that combines behavior cloning from human demonstrations with self-learning optimization to improve beyond human teleoperation performance. With extensive real-world experiments, we demonstrate AquaBot's versatility across diverse manipulation tasks, including object grasping, trash sorting, and rescue retrieval. Our real-world experiments show that AquaBot's self-optimized policy outperforms a human operator by 41% in speed. AquaBot represents a promising step towards autonomous and self-improving underwater manipulation systems. We open-source both hardware and software implementation details.
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。