Papers
Topics
Authors
Recent
Search
2000 character limit reached

Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control

Published 2 Mar 2023 in cs.RO and cs.LG | (2303.01563v2)

Abstract: Model-based RL/control have gained significant traction in robotics. Yet, these approaches often remain data-inefficient and lack the explainability of hand-engineered solutions. This makes them difficult to debug/integrate in safety-critical settings. However, in many systems, prior knowledge of environment kinematics/dynamics is available. Incorporating such priors can help address the aforementioned problems by reducing problem complexity and the need for exploration, while also facilitating the expression of the decisions taken by the agent in terms of physically meaningful entities. Our aim with this paper is to illustrate and support this point of view via a case-study. We model a payload manipulation problem based on a real robotic system, and show that leveraging prior knowledge about the dynamics of the environment in an MPC framework can lead to improvements in explainability, safety and data-efficiency, leading to satisfying generalization properties with less data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258, 2021.
  2. Sparse identification of nonlinear dynamics with control (sindyc). IFAC-PapersOnLine, 49(18):710–715, 2016.
  3. Sim-to-real transfer with incremental environment complexity for reinforcement learning of depth-based robot navigation. arXiv preprint arXiv:2004.14684, 2020.
  4. Machine learning with aibo robots in the four-legged league of robocup. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 37(3):297–310, 2007.
  5. Pybullet, a python module for physics simulation for games, robotics and machine learning. http://pybullet.org, 2016–2021.
  6. Pilco: A model-based and data-efficient approach to policy search. In Proceedings of the 28th International Conference on machine learning (ICML-11), pages 465–472, 2011.
  7. Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(9):5149–5169, 2021.
  8. Explainable artificial intelligence approaches: A survey. arXiv preprint arXiv:2101.09429, 2021.
  9. Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374, 2019.
  10. Lennart Ljung. System Identification. 2017. https://doi.org/10.1002/047134608X.W1046.pub2. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/047134608X.W1046.pub2.
  11. Differentiable physics models for real-world offline model-based reinforcement learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 4163–4170. IEEE, 2021.
  12. Patrick M McGuire. Conveyors: application, selection, and integration. CRC Press, 2009.
  13. Engineering mechanics: dynamics. John Wiley & Sons, 2020.
  14. Model-based reinforcement learning: A survey. arXiv preprint arXiv:2006.16712, 2020.
  15. Linett Montaño Guzmán. Fuzzy measures and integrals. Acta Nova, 2(2):216–227, 2003.
  16. Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 7559–7566. IEEE, 2018.
  17. Lbgp: Learning based goal planning for autonomous following in front. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 3140–3146. IEEE, 2021.
  18. Sample-efficient cross-entropy method for real-time planning. In Conference on Robot Learning, pages 1049–1065. PMLR, 2021.
  19. Adaptive asynchronous control using meta-learned neural ordinary differential equations. IEEE Transactions on Robotics, 2023. 10.1109/TRO.2023.3326350.
  20. Ramp-net: A robust adaptive mpc for quadrotors via physics-informed neural network. arXiv preprint arXiv:2209.09025, 2022.
  21. Planning to explore via self-supervised world models. In International Conference on Machine Learning, pages 8583–8592. PMLR, 2020.
  22. State entropy maximization with random encoders for efficient exploration. In International Conference on Machine Learning, pages 9443–9454. PMLR, 2021.
  23. Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pages 737–744. IEEE, 2020.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up