| Yang, Xintong  ORCID: https://orcid.org/0000-0002-7612-614X, Ji, Ze  ORCID: https://orcid.org/0000-0002-8968-9902, Wu, Jing  ORCID: https://orcid.org/0000-0001-5123-9861 and Lai, Yu-Kun  ORCID: https://orcid.org/0000-0002-2094-5680
      2021.
      
      An open-source multi-goal reinforcement learning environment for robotic manipulation with Pybullet.
      Presented at: 21st Towards Autonomous Robotic Systems Conference (TAROS 2021),
      Virtual,
      8-10 September 2021.
      Published in: Fox, C., Gao, J., Ghalamzan Esfahani, A., Saaj, M., Hanheide, M. and Parsons, S. eds.
      Towards Autonomous Robotic Systems. TAROS 2021.
      
      Lecture Notes in Computer Science
      
       
      
      
      Springer,
      pp. 14-24.
      10.1007/978-3-030-89177-0_2 | 
| ![7.0 TAROS2021_paper_7.pdf [thumbnail of 7.0 TAROS2021_paper_7.pdf]](https://orca.cardiff.ac.uk/style/images/fileicons/application_pdf.png) | PDF
 - Accepted Post-Print Version Download (1MB) | 
| ![7.0 taros20210308_supplementary.pdf [thumbnail of 7.0 taros20210308_supplementary.pdf]](https://orca.cardiff.ac.uk/style/images/fileicons/application_pdf.png) | PDF
 - Supplemental Material Download (3MB) | 
Abstract
This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine. By comparing the performances of the Hindsight Experience Replay-aided Deep Deterministic Policy Gradient agent on both environments, we demonstrate our successful re-implementation of the original environment. Besides, we provide users with new APIs to access a joint control mode, image observations and goals with customisable camera and a built-in on-hand camera. We further design a set of multi-step, multi-goal, long-horizon and sparse reward robotic manipulation tasks, aiming to inspire new goal-conditioned reinforcement learning algorithms for such challenges. We use a simple, human-prior-based curriculum learning method to benchmark the multi-step manipulation tasks. Discussions about future research opportunities regarding this kind of tasks are also provided.
| Item Type: | Conference or Workshop Item (Paper) | 
|---|---|
| Date Type: | Published Online | 
| Status: | Published | 
| Schools: | Schools > Engineering | 
| Publisher: | Springer | 
| ISBN: | 9783030891763 | 
| Date of First Compliant Deposit: | 20 July 2021 | 
| Date of Acceptance: | 11 February 2021 | 
| Last Modified: | 14 May 2025 14:49 | 
| URI: | https://orca.cardiff.ac.uk/id/eprint/142729 | 
Citation Data
Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
|  | Edit Item | 

 
							

 Dimensions
 Dimensions Dimensions
 Dimensions