用模仿学习让机械臂自动找最佳视角，避开遮挡抓取作物
Enhanced View Planning for Robotic Harvesting: Tackling Occlusions with Imitation Learning
- 通过专家示范学习相机6自由度运动策略
- 复杂遮挡下捕获成功率显著提升，实测效率更高
- 无需重编程即可适配不同作物，适合农业自动化场景
在农业自动化中，遮挡是机器人采摘的主要挑战。本文提出一种基于模仿学习的视角规划方法，通过主动调整摄像头视角，获取目标作物无遮挡图像。传统方法依赖人工设计评估指标或奖励函数，在复杂未见场景中泛化能力差。本方法采用动作分块与变压器（ACT）算法，从专家示范中学习有效的相机运动策略，实现连续六自由度（6-DoF）视角调整，使运动更平滑、精准，并有效暴露被遮挡目标。在模拟与真实世界环境中的大量实验，涵盖农业场景及配备RGB-D相机的6-DoF机械臂，验证了该方法在复杂遮挡条件下的优越成功率和效率，且能跨作物泛化，无需重新编程。本研究为遮挡问题提供了实用的‘从示范学习’（LfD）解决方案，显著提升自主采摘性能与生产效率。
原文摘要 · Abstract (English)
In agricultural automation, inherent occlusion presents a major challenge for robotic harvesting. We propose a novel imitation learning-based viewpoint planning approach to actively adjust camera viewpoint and capture unobstructed images of the target crop. Traditional viewpoint planners and existing learning-based methods, depend on manually designed evaluation metrics or reward functions, often struggle to generalize to complex, unseen scenarios. Our method employs the Action Chunking with Transformer (ACT) algorithm to learn effective camera motion policies from expert demonstrations. This enables continuous six-degree-of-freedom (6-DoF) viewpoint adjustments that are smoother, more precise and reveal occluded targets. Extensive experiments in both simulated and real-world environments, featuring agricultural scenarios and a 6-DoF robot arm equipped with an RGB-D camera, demonstrate our method's superior success rate and efficiency, especially in complex occlusion conditions, as well as its ability to generalize across different crops without reprogramming. This study advances robotic harvesting by providing a practical "learn from demonstration" (LfD) solution to occlusion challenges, ultimately enhancing autonomous harvesting performance and productivity.
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。