# Approximate Robust Control of Uncertain Dynamical Systems

arXiv: https://arxiv.org/abs/1903.00220 · HTML: https://mlsanity.com/paper/1903.00220/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 9 of 9)

- [Social Coordination and Altruism in Autonomous Driving](https://mlsanity.com/paper/2107.00200/) (2021)
- [Learning Safety Constraints from Demonstrations with Unknown Rewards](https://mlsanity.com/paper/2305.16147/) (2023)
- [Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic](https://mlsanity.com/paper/2202.00881/) (2022)
- [Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic](https://mlsanity.com/paper/2107.05664/) (2021)
- [Prediction-aware and Reinforcement Learning based Altruistic Cooperative Driving](https://mlsanity.com/paper/2211.10585/) (2022)
- [Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge](https://mlsanity.com/paper/2103.10245/) (2021)
- [Towards Learning Generalizable Driving Policies from Restricted Latent Representations](https://mlsanity.com/paper/2111.03688/) (2021)
- [Learning-based social coordination to improve safety and robustness of cooperative autonomous vehicles in mixed traffic](https://mlsanity.com/paper/2211.11963/) (2022)
- [When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability](https://mlsanity.com/paper/2605.26155/) (2026)

## Abstract (arXiv)

This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a principled approach to safety that aims to maximize the worst-case performance of a system. However, the resulting optimization problem is generally intractable for non-linear systems with continuous states. To overcome this issue, we introduce two tractable methods that are based either on sampling or on a conservative approximation of the robust objective. The proposed approaches are applied to the problem of autonomous driving.