Zero-Shot Sim-to-Real Reinforcement Learning for Fruit Harvesting

2025/05/13 by Williams, Emlyn, Polydoros, Athanasios
#FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2505.08458

Abstract

This paper presents a comprehensive sim-to-real pipeline for autonomous strawberry picking from dense clusters using a Franka Panda robot. Our approach leverages a custom Mujoco simulation environment that integrates domain randomization techniques. In this environment, a deep reinforcement learning agent is trained using the dormant ratio minimization algorithm. The proposed pipeline bridges low-level control with high-level perception and decision making, demonstrating promising performance in both simulation and in a real laboratory environment, laying the groundwork for successful transfer to real-world autonomous fruit harvesting.

Related

• Reinforcement Learning for the Full Strawberry Harvesting Process: Obstacle Separation, Detachment, and Placement
• Viewpoint Optimization for Autonomous Strawberry Harvesting with Deep Reinforcement Learning
• Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulation
• Single-Shot 6DoF Pose and 3D Size Estimation for Robotic Strawberry Harvesting
• Learning to Pick: A Visuomotor Policy for Clustered Strawberry Picking