# Symbolic Perception Risk in Autonomous Driving

arXiv: https://arxiv.org/abs/2303.09416 · HTML: https://mlsanity.com/paper/2303.09416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics](https://mlsanity.com/paper/1710.11040/) (2017)
- [Robust Guarantees for Perception-Based Control](https://mlsanity.com/paper/1907.03680/) (2019)
- [Traffic Sign Classification Using Deep Inception Based Convolutional Networks](https://mlsanity.com/paper/1511.02992/) (2015)
- [Risk-Aware Motion Planning in Partially Known Environments](https://mlsanity.com/paper/2109.11287/) (2021)
- [Cautious Planning with Incremental Symbolic Perception: Designing Verified Reactive Driving Maneuvers](https://mlsanity.com/paper/2209.09818/) (2022)
- [Robust Learning of Recurrent Neural Networks in Presence of Exogenous Noise](https://mlsanity.com/paper/2105.00996/) (2021)
- [Risk of Cascading Failures in Time-Delayed Vehicle Platooning](https://mlsanity.com/paper/2109.01963/) (2021)
- [Robustness Analysis of Classification Using Recurrent Neural Networks with Perturbed Sequential Input](https://mlsanity.com/paper/2203.05403/) (2022)
- [Exceedance Probabilities for the Dirichlet Distribution](https://mlsanity.com/paper/1611.01439/) (2016)
- [CVaR-based Safety Analysis in the Infinite Time Horizon Setting](https://mlsanity.com/paper/2108.06776/) (2021)

## Abstract (arXiv)

We develop a novel framework to assess the risk of misperception in a traffic sign classification task in the presence of exogenous noise. We consider the problem in an autonomous driving setting, where visual input quality gradually improves due to improved resolution, and less noise since the distance to traffic signs decreases. Using the estimated perception statistics obtained using the standard classification algorithms, we aim to quantify the risk of misperception to mitigate the effects of imperfect visual observation. By exploring perception outputs, their expected high-level actions, and potential costs, we show the closed-form representation of the conditional value-at-risk (CVaR) of misperception. Several case studies support the effectiveness of our proposed methodology.