Autonomous Driving with Interpretable Goal Recognition and Monte Carlo Tree Search
| Autor: | Brewitt, Cillian, Albrecht, Stefano V, Wilhelm, John, Gyevnar, Balint, Eiras, Francisco, Dobre, Mihai, Ramamoorthy, Ram |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Zdroj: | Brewitt, C, Albrecht, S V, Wilhelm, J, Gyevnar, B, Eiras, F, Dobre, M & Ramamoorthy, R 2020, ' Autonomous Driving with Interpretable Goal Recognition and Monte Carlo Tree Search ', Paper presented at Interaction and Decision-Making in Autonomous-Driving, 13/07/20-13/07/20 . < https://drive.google.com/file/d/1dIWMbcAN35v8mCCcccWDbbBo7pSbKGuW/view > |
| Popis: | —The ability to predict the intentions and driving trajectories of other vehicles is a key problem for autonomous driving. We propose an integrated planning and prediction system which leverages the computational benefit of using a finite space of maneuvers, and extend the approach to planning and prediction of sequences of maneuvers via 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. Our system constructs plans which are explainable by means of rationality. Evaluation in simulations of four urban driving scenarios demonstrate the system’s ability to robustly recognise the goals of other vehicles while generating near-optimal plans. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|