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

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

*Kontaktforfatter

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer 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.
OriginalsprogEngelsk
Titel2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
ForlagIEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato20 okt. 2022
DOI
StatusUdgivet - 20 okt. 2022
Begivenhed2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Kyoto, Japan
Varighed: 23 okt. 202227 okt. 2022
https://iros2022.org

Konference

Konference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Land/OmrådeJapan
ByKyoto
Periode23/10/202227/10/2022
Internetadresse

Emneord

  • Reinforcement Learning
  • Robotics
  • Grasping
  • Space Robotics
  • Deep Learning
  • Maskinlæring

Fingeraftryk

Dyk ned i forskningsemnerne om 'Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning'. Sammen danner de et unikt fingeraftryk.

Citationsformater