Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining safety with respect to the overall closed-loop system. For this reason, it is useful to distill high-level safety requirements into component-level requirements on the perception system. In this work, we focus on efficiently determining sets of safe perception system performance characteristics given a black-box simulator of the fully-integrated, closed-loop system. We combine the advantages of common black-box estimation techniques such as Gaussian processes and threshold bandits to develop a new estimation method, which we call smoothing bandits. We demonstrate our method on a vision-based aircraft collision avoidance problem and show improvements in terms of both accuracy and efficiency over the Gaussian process and threshold bandit baselines.
Efficient Determination of Safety Requirements for Perception Systems
2023-10-01
1764737 byte
Conference paper
Electronic Resource
English
On Perception Safety Requirements and Multi Sensor Systems for Automated Driving Systems
British Library Conference Proceedings | 2020
|On Perception Safety Requirements and Multi Sensor Systems for Automated Driving Systems
SAE Technical Papers | 2020
|On Perception Safety Requirements and Multi Sensor Systems for Automated Driving Systems
British Library Conference Proceedings | 2020
|British Library Conference Proceedings | 2006
|Environmental perception for future integrated safety systems
Automotive engineering | 2009
|