Projects per year
Testing black-box perceptual-control systems in simulation faces two difficulties. Firstly, perceptual inputs in simulation lack the fidelity of real-world sensor inputs. Secondly, for a reasonably accurate perception system, encountering a rare failure trajectory may require running infeasibly many simulations. This paper combines perception error models -- surrogates for a sensor-based detection system -- with state-dependent adaptive importance sampling. This allows us to efficiently assess the rare failure probabilities for real-world perceptual control systems within simulation. Our experiments with an autonomous braking system equipped with an RGB obstacle-detector show that our method can calculate accurate failure probabilities with an inexpensive number of simulations. Further, we show how choice of safety metric can influence the process of learning proposal distributions capable of reliably sampling high-probability failures.
|Title of host publication||Proceedings of ICRA 2023 : IEEE International Conference on Robotics and Automation|
|Number of pages||7|
|Publication status||Accepted/In press - 17 Jan 2023|
|Event||2023 IEEE International Conference on Robotics and Automation - London, United Kingdom|
Duration: 29 May 2023 → 2 Jun 2023
|Conference||2023 IEEE International Conference on Robotics and Automation|
|Abbreviated title||ICRA 2023|
|Period||29/05/23 → 2/06/23|
FingerprintDive into the research topics of 'Testing Rare Downstream Safety Violations via Upstream Adaptive Sampling of Perception Error Models'. Together they form a unique fingerprint.
- 1 Active
UKRI Trustworthy Autonomous Systems Node in Governance and Regulation
Ramamoorthy, R., Belle, V., Bundy, A., Jackson, P., Lascarides, A. & Rajan, A.
1/11/20 → 30/04/24