Research Publications
Integrating planning and interpretable goal recognition for autonomous driving
S.V. Albrecht, C. Brewitt, J. Wilhelm, F. Eiras, M. Dobre, S. Ramamoorthy
arxiv.org/abs/2002.02277
Abstract
We propose an integrated prediction and planning system for autonomous driving which uses rational inverse planning to recognise the goals of other vehicles. Goal recognition informs a Monte Carlo Tree Search (MCTS) algorithm to plan optimal maneuvers for the ego vehicle. Inverse planning and MCTS utilise a shared set of defined maneuvers and macro actions to construct plans which are explainable by means of \emph{rationality} principles. Evaluation in simulations of urban driving scenarios demonstrate the system's ability to robustly recognise the goals of other vehicles, enabling our vehicle to exploit non-trivial opportunities to significantly reduce driving times. In each scenario, we extract intuitive explanations for the predictions which justify the system's decisions.
Download the full paper