Skip to main content

Sim-to-Real Gap in RL: Use Case with TIAGo and Isaac Sim/Gym

  • Conference paper
  • First Online:
European Robotics Forum 2024 (ERF 2024)

Part of the book series: Springer Proceedings in Advanced Robotics ((SPAR,volume 32))

Included in the following conference series:

  • 69 Accesses

Abstract

This paper explores policy-learning approaches in the context of sim-to-real transfer for robotic manipulation using a TIAGo mobile manipulator, focusing on two state-of-art simulators, Isaac Gym and Isaac Sim, both developed by Nvidia. Control architectures are discussed, with a particular emphasis on achieving collision-less movement in both simulation and the real environment. Presented results demonstrate successful sim-to-real transfer, showcasing similar movements executed by an RL-trained model in both simulated and real setups.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://pal-robotics.com/robots/TiaGo/.

  2. 2.

    https://github.com/NVIDIA-Omniverse/IsaacGymEnvs.

  3. 3.

    https://github.com/ros-controls/ros_control.

References

  1. Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37(4–5), 421–436 (2018). https://doi.org/10.1177/0278364917710318

    Article  Google Scholar 

  2. Gu, S., et al.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2017)

    Google Scholar 

  3. Kalashnikov, D., et al.: Scalable deep reinforcement learning for vision-based robotic manipulation. In: Conference on Robot Learning. PMLR (2018)

    Google Scholar 

  4. Towers, M., et al.: Gymnasium (2023). https://zenodo.org/record/8127025

  5. Raffin, A., et al.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(1), 12348–12355 (2021)

    MATH  Google Scholar 

  6. Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE (2012)

    Google Scholar 

  7. Makoviychuk, V., et al.: Isaac gym: high performance GPU-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)

  8. NVIDIA. Isaac Sim Robotics Simulator. https://developer.nvidia.com/isaac-sim. Accessed 16 Apr 2024

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Alberto San Miguel .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Albardaner, J., Miguel, A.S., García, N., Dalmau, M. (2024). Sim-to-Real Gap in RL: Use Case with TIAGo and Isaac Sim/Gym. In: Secchi, C., Marconi, L. (eds) European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. Springer, Cham. https://doi.org/10.1007/978-3-031-76424-0_61

Download citation

Publish with us

Policies and ethics