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

-- This paper presents a comprehensive sim-to-real pipeline for autonomous strawberry picking from dense clusters using a Franka Panda robot. 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. I. INTRODUCTION Despite significant advances in robotics in recent years, manipulating objects in unstructured environments remains a challenging task. With marked variability in lighting, weather and plant geometries, agricultural environments present a notable challenge for robots to operate in. Agricultural tasks such as fruit harvesting require robots to operate under these variable conditions, all of which contribute to the difficulty of achieving reliable performance in the real world.