Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Event-Triggered Safe Bayesian Optimization on Quadcopters (2312.08058v1)

Published 13 Dec 2023 in eess.SY and cs.SY

Abstract: Bayesian optimization (BO) has proven to be a powerful tool for automatically tuning control parameters without requiring knowledge of the underlying system dynamics. Safe BO methods, in addition, guarantee safety during the optimization process, assuming that the underlying objective function does not change. However, in real-world scenarios, time-variations frequently occur, for example, due to wear in the system or changes in operation. Utilizing standard safe BO strategies that do not address time-variations can result in failure as previous safe decisions may become unsafe over time, which we demonstrate herein. To address this, we introduce a new algorithm, Event-Triggered SafeOpt (ETSO), which adapts to changes online solely relying on the observed costs. At its core, ETSO uses an event trigger to detect significant deviations between observations and the current surrogate of the objective function. When such change is detected, the algorithm reverts to a safe backup controller, and exploration is restarted. In this way, safety is recovered and maintained across changes. We evaluate ETSO on quadcopter controller tuning, both in simulation and hardware experiments. ETSO outperforms state-of-the-art safe BO, achieving superior control performance over time while maintaining safety.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Fast feedback control over multi-hop wireless networks with mode changes and stability guarantees. ACM Transactions on Cyber-Physical Systems, 4(2):1–32, 2019.
  2. Gosafe: Globally optimal safe robot learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 4452–4458. IEEE, 2021.
  3. Safe controller optimization for quadrotors with Gaussian processes. In 2016 IEEE International Conference on Robotics and Automation (ICRA), pages 491–496. IEEE, 2016.
  4. Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics. Machine Learning, pages 1–35, 2021.
  5. Time-varying Gaussian process bandit optimization. In Artificial Intelligence and Statistics, pages 314–323. PMLR, 2016.
  6. On controller tuning with time-varying Bayesian optimization. In 2022 IEEE 61st Conference on Decision and Control (CDC), pages 4046–4052. IEEE, 2022.
  7. Event-triggered time-varying Bayesian optimization. arXiv preprint arXiv:2208.10790, 2023.
  8. Bayesian optimization for learning gaits under uncertainty: An experimental comparison on a dynamic bipedal walker. Annals of Mathematics and Artificial Intelligence, 76:5–23, 2016.
  9. Safe contextual Bayesian optimization integrated in industrial control for self-learning machines. Journal of Intelligent Manufacturing, pages 1–19, 2023.
  10. Weighted Gaussian process bandits for non-stationary environments. In International Conference on Artificial Intelligence and Statistics, pages 6909–6932. PMLR, 2022.
  11. Safe contextual bayesian optimization for sustainable room temperature PID control tuning. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pages 5850–5856. International Joint Conferences on Artificial Intelligence, 2019.
  12. Roman Garnett. Bayesian Optimization. Cambridge University Press, 2023.
  13. Stability of switched systems with average dwell-time. In Proceedings of the 38th IEEE Conference on Decision and Control, pages 2655–2660 vol.3, 1999.
  14. High dimensional Bayesian optimisation and bandits via additive models. In International Conference on Machine Learning, pages 295–304. PMLR, 2015.
  15. Controller tuning by Bayesian optimization an application to a heat pump. In 2019 18th European Control Conference (ECC), pages 1467–1472, 2019.
  16. Contextual Gaussian process bandit optimization. Advances in Neural Information Processing Systems, 24, 2011.
  17. Safe and efficient model-free adaptive control via Bayesian optimization. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 9782–9788, 2021.
  18. Teppo Luukkonen. Modelling and control of quadcopter. Independent research project in applied mathematics, Espoo, 22(22), 2011.
  19. Automatic LQR tuning based on Gaussian process global optimization. In 2016 IEEE International Conference on Robotics and Automation (ICRA), pages 270–277. IEEE, 2016.
  20. Minimum snap trajectory generation and control for quadrotors. In 2011 IEEE International Conference on Robotics and Automation, pages 2520–2525. IEEE, 2011.
  21. Data-efficient autotuning with Bayesian optimization: An industrial control study. IEEE Transactions on Control Systems and Technology, 2018.
  22. Learning to fly—a gym environment with pybullet physics for reinforcement learning of multi-agent quadcopter control. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
  23. Crazyswarm: A large nano-quadcopter swarm. In IEEE International Conference on Robotics and Automation (ICRA), pages 3299–3304. IEEE, 2017.
  24. Event-triggered learning. Automatica, 117:109009, 2020.
  25. Gaussian process optimization in the bandit setting: no regret and experimental design. In Proceedings of the 27th International Conference on International Conference on Machine Learning, pages 1015–1022, 2010.
  26. Autonomous vehicle control through the dynamics and controller learning. IEEE Transactions on Vehicular Technology, 67(7):5650–5657, 2018.
  27. Safe exploration for optimization with Gaussian processes. In International conference on machine learning, pages 997–1005. PMLR, 2015.
  28. Stagewise safe Bayesian optimization with Gaussian processes. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pages 4781–4789. PMLR, 10–15 Jul 2018.
  29. Gosafeopt: Scalable safe exploration for global optimization of dynamical systems. Artificial Intelligence, 320:103922, 2023.
  30. Safe exploration for interactive machine learning. Advances in Neural Information Processing Systems, 32, 2019.
  31. Feedback linearization based on Gaussian processes with event-triggered online learning. IEEE Transactions on Automatic Control, 65(10):4154–4169, 2019.
  32. Gaussian processes for machine learning, volume 3. MIT press Cambridge, MA, 2006.
  33. Violation-aware contextual Bayesian optimization for controller performance optimization with unmodeled constraints. arXiv preprint arXiv:2301.12099, 2023.
  34. No-regret algorithms for time-varying Bayesian optimization. In 2021 55th Annual Conference on Information Sciences and Systems (CISS), pages 1–6. IEEE, 2021.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now