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. 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.

 @inproceedings{williams2025zero,
  title = {Zero-Shot Sim-to-Real Reinforcement Learning for Fruit Harvesting},
  author = {Williams, Emlyn and Polydoros, Athanasios},
  booktitle = {2025 IEEE 21th International Conference on Automation Science and Engineering (CASE)},
  year = {2025},
  organization = {IEEE},
  public = {yes},
  pdflink1 = {https://arxiv.org/abs/2505.08458}
}