发表机构
The Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences; School of Intelligence Science and Technology, University of Science and Technology Beijing; Happy Elements Ltd.（北京市农林科学院智能装备研究中心; 北京科技大学智能科学与技术学院; 乐元素科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对成簇草莓采摘中果实易被遮挡的问题，提出分层强化学习框架VGPA，集成视觉引导决策机制和PAES，将任务分解为两阶段。模拟实验策略成功率96.7%，模拟到现实转移实验成功率71.7% - 88.3%，优于直接采摘，验证了方法有效性、泛化能力和实际潜力。
AI 中文摘要
在成簇草莓环境中进行选择性采摘具有挑战性，因为成熟果实常被周围未成熟果实遮挡，直接抓取不可靠。本文提出了一种分层强化学习框架VGPA，它集成了视觉引导决策机制和渐进自适应探索策略（PAES）用于基于视觉的障碍物分离和采摘。任务被分解为障碍物分离和目标抓取两个连续阶段。在高层，视觉引导机制改善选项选择并加速策略收敛；在低层，PAES在连续控制学习中提高探索效率和训练稳定性。模拟实验中，学习到的策略成功率达96.7%。在自制并行机器人上的模拟到现实转移实验表明，该方法成功率在71.7%至88.3%之间，优于直接采摘，平均采摘时间仅多1.22秒。这些结果验证了该方法在复杂成簇环境中进行机器人采摘时的有效性、泛化能力和实际潜力。
英文摘要
Selective harvesting in clustered strawberry environments is challenging because ripe fruits are often occluded by surrounding unripe fruits, making direct grasping unreliable. To address this problem, this paper proposes a hierarchical reinforcement learning framework, termed VGPA, which integrates a vision-guided decision mechanism and a Progressive Adaptive Exploration Strategy (PAES) for vision-based obstacle separation and harvesting. The task was decomposed into two sequential stages: obstacle separation and target grasping. At the high level, the vision-guided mechanism improved option selection and accelerated policy convergence. At the low level, PAES improved exploration efficiency and training stability during continuous control learning. In simulation experiments, the learned policy achieved a success rate of 96.7%. In addition, sim-to-real transfer experiments on a self-developed parallel robot showed that the proposed method achieved success rates ranging from 71.7% to 88.3%, outperforming direct picking while requiring only 1.22~s more average harvesting time. These results verified the effectiveness, generalization ability, and practical potential of the proposed method for robotic harvesting in complex clustered environments.
CommentsAccepted to IROS 2026
