# Avoidance of an unexpected obstacle without reinforcement learning: Why not using advanced control-theoretic tools?

arXiv: https://arxiv.org/abs/2509.03721 · HTML: https://mlsanity.com/paper/2509.03721/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 14 of 14)

- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [A Tour of Reinforcement Learning: The View from Continuous Control](https://mlsanity.com/paper/1806.09460/) (2018)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [Reinforcement Learning of the Prediction Horizon in Model Predictive Control](https://mlsanity.com/paper/2102.11122/) (2021)
- [Manipulating Deformable Objects by Interleaving Prediction, Planning, and Control](https://mlsanity.com/paper/2001.09950/) (2020)
- [Model-free control](https://mlsanity.com/paper/1305.7085/) (2013)
- [Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2207.03034/) (2022)
- [Synchronization of Kuramoto oscillators via HEOL, and a discussion on AI](https://mlsanity.com/paper/2501.07948/) (2025)
- [An alternative to proportional-integral and proportional-integral-derivative regulators: Intelligent proportional-derivative regulators](https://mlsanity.com/paper/2106.12210/) (2021)
- [Flatness-based control revisited: The HEOL setting](https://mlsanity.com/paper/2408.11580/) (2024)
- [The Euler-Lagrange equation and optimal control: Preliminary results](https://mlsanity.com/paper/2410.07040/) (2024)
- [A model-free control strategy for an experimental greenhouse with an application to fault accommodation](https://mlsanity.com/paper/1411.7169/) (2014)
- [Model-Free Predictive Control: Introductory Algebraic Calculations, and a Comparison with HEOL and ANNs](https://mlsanity.com/paper/2502.00443/) (2025)
- [Guidance and Control of Unmanned Surface Vehicles via HEOL](https://mlsanity.com/paper/2505.00168/) (2025)

## Abstract (arXiv)

This communication on collision avoidance with unexpected obstacles is motivated by some critical appraisals on reinforcement learning (RL) which "requires ridiculously large numbers of trials to learn any new task" (Yann LeCun). We use the classic Dubins' car in order to replace RL with flatness-based control, combined with the HEOL feedback setting, and the latest model-free predictive control approach. The two approaches lead to convincing computer experiments where the results with the model-based one are only slightly better. They exhibit a satisfactory robustness with respect to randomly generated mismatches/disturbances, which become excellent in the model-free case. Those properties would have been perhaps difficult to obtain with today's popular machine learning techniques in AI. Finally, we should emphasize that our two methods require a low computational burden.