Reinforcement Learning for the Full Strawberry Harvesting Process: Obstacle Separation, Detachment, and Placement
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Severe occlusions and deformable plant structures introduce complex contact dynamics that challenge robotic strawberry harvesting. A policy-driven reinforcement learning (RL) framework with heuristic phase coordination was developed, in which obstacle separation, fruit detachment, and placement were formulated as a sequential decision-making task. A shared interaction-aware policy generated Cartesian motions across all task phases, while lightweight heuristic logic coordinated task progression and gripper events. A shared structured observation space was used to represent target, obstacle, end-effector, and task-context information. A hierarchical architecture combined the high-level policy with low-level Cartesian impedance control for compliant interaction. To support zero-shot sim-to-real transfer, feasibility-first observation alignment and domain randomization were adopted. The policy achieved success rates of 89.7% in simulation and 82.0% in real-world experiments. As the occlusion level increased from 1 to 5, the average execution time increased from 12.99 s to 21.73 s, reflecting greater interaction complexity. These results demonstrated effective transfer of interaction-aware harvesting behaviors to a structurally different robotic platform.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 20 references that are in the map. First posted on arXiv 16 Jul 2026.
Builds on
13 of 20 references.
Closest ancestors · 2
Same direction, newest first
- 2024Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL26 Oct
- 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning29 Jan
Other references · 11
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
- 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
- 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 131
- 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 121
- 2023DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimizationcited by 47
- 2023Deep Reinforcement Learning for Robotic Pushing and Picking in Cluttered Environmentcited by 13
- 2023Push Past Green: Learning to Look Behind Plant Foliage by Moving Itcited by 3
- 2024Design and Control of a Novel Six-Degree-of-Freedom Hybrid Robotic Armcited by 3
- 2025Zero-Shot Sim-to-Real Reinforcement Learning for Fruit Harvestingcited by 1
- 2025Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Vision-Based Obstacle Separation for Strawberry Harvesting in Clusters Using Hierarchical Reinforcement Learning ↗
- 2026Robotic Strawberry Harvesting with Robust Vision and Deep Reinforcement Learning based Sim-to-Real Control ↗
- 2026HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion ↗
- 2024Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments ↗
- 2025Enhanced View Planning for Robotic Harvesting: Tackling Occlusions with Imitation Learning
- 2026Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
- 2026From Vision to Harvest: Benchmarking Vision-Language Models for Multi-Arm Robotic Fruit Harvesting
- 2026HarvestFlex: Strawberry Harvesting via Vision-Language-Action Policy Adaptation in the Wild