Abstract This paper proposes a methodology to estimate uncertainties in automated vehicle (AV) dynamics in real time via Bayesian inference. Based on the estimated uncertainty, the method aims to track the car-following (CF) performance of the AV to support strategic actions to maintain desired performance. Our methodology consists of three sequential components: (i) the Stochastic Gradient Langevin Dynamics (SGLD) is adopted to estimate parameter uncertainty relative to vehicular dynamics in real time, (ii) dynamic monitoring of car-following stability (local and string-wise), and (iii) strategic actions for control adjustment if anomaly is detected. The proposed methodology provides means to gauge AV car-following performance in real time and preserve desired performance against real time uncertainty that are unaccounted for in the vehicle control algorithm.
Highlights Real-time car-following (CF) performance monitoring framework is developed. Probabilistic approach is adopted for uncertainty estimation in lower-level controller. Strategic adjustments are offered for performance loss in CF behavior.
A strategic approach to handle performance uncertainties in autonomous vehicle’s car-following behavior
2024-01-29
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Assembling structure of full handle and switch box for vehicle's door
Europäisches Patentamt | 2015