Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

Andrej Orsula*, Simon Bøgh, Miguel Olivares-Mendez, Carol Martinez

*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Extraterrestrial rovers with a general-purpose robotic arm have many potential applications in lunar and planetary exploration. Introducing autonomy into such systems is desirable for increasing the time that rovers can spend gathering scientific data and collecting samples. This work investigates the applicability of deep reinforcement learning for vision-based robotic grasping of objects on the Moon. A novel simulation environment with procedurally-generated datasets is created to train agents under challenging conditions in unstructured scenes with uneven terrain and harsh illumination. A model-free off-policy actor-critic algorithm is then employed for end-to-end learning of a policy that directly maps compact octree observations to continuous actions in Cartesian space. Experimental evaluation indicates that 3D data representations enable more effective learning of manipulation skills when compared to traditionally used image-based observations. Domain randomization improves the generalization of learned policies to novel scenes with previously unseen objects and different illumination conditions. To this end, we demonstrate zero-shot sim-to-real transfer by evaluating trained agents on a real robot in a Moon-analogue facility.
Original languageEnglish
Title of host publication2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
PublisherIEEE
Publication date20 Oct 2022
DOIs
Publication statusPublished - 20 Oct 2022
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Kyoto, Japan
Duration: 23 Oct 202227 Oct 2022
https://iros2022.org

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Country/TerritoryJapan
CityKyoto
Period23/10/202227/10/2022
Internet address

Keywords

  • Reinforcement Learning
  • Robotics
  • Grasping
  • Space Robotics
  • Deep Learning
  • Machine Learning

Fingerprint

Dive into the research topics of 'Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this