# Synthesizing Adversarial Visual Scenarios for Model-Based Robotic Control

arXiv: https://arxiv.org/abs/2204.06173 · HTML: https://mlsanity.com/paper/2204.06173/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2022.

## Built on by (most cited first, 4 of 4)

- [Time Weaver: A Conditional Time Series Generation Model](https://mlsanity.com/paper/2403.02682/) (2024)
- [Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation](https://mlsanity.com/paper/2307.07907/) (2023)
- [Robust Forecasting for Robotic Control: A Game-Theoretic Approach](https://mlsanity.com/paper/2209.10802/) (2022)
- [Beyond the Patch: Exploring Vulnerabilities of Visuomotor Policies via Viewpoint-Consistent 3D Adversarial Object](https://mlsanity.com/paper/2603.04913/) (2026)

## Abstract (arXiv)

Today's robots often interface with data-driven perception and planning models with classical model-predictive controllers (MPC). Often, such learned perception/planning models produce erroneous waypoint predictions on out-of-distribution (OoD) or even adversarial visual inputs, which increase control costs. However, today's methods to train robust perception models are largely task-agnostic - they augment a dataset using random image transformations or adversarial examples targeted at the vision model in isolation. As such, they often introduce pixel perturbations that are ultimately benign for control. In contrast to prior work that synthesizes adversarial examples for single-step vision tasks, our key contribution is to synthesize adversarial scenarios tailored to multi-step, model-based control. To do so, we use differentiable MPC methods to calculate the sensitivity of a model-based controller to errors in state estimation. We show that re-training vision models on these adversarial datasets improves control performance on OoD test scenarios by up to 36.2% compared to standard task-agnostic data augmentation. We demonstrate our method on examples of robotic navigation, manipulation in RoboSuite, and control of an autonomous air vehicle.