Interpretable Goal-based Prediction and Planning for Autonomous Driving

Stefano V Albrecht; Cillian Brewitt; John Wilhelm; Balint Gyevnar; Francisco Eiras; Mihai Dobre; Subramanian Ramamoorthy

doi:10.1109/ICRA48506.2021.9560849

Interpretable Goal-based Prediction and Planning for Autonomous Driving

Stefano V Albrecht, Cillian Brewitt, John Wilhelm, Balint Gyevnar, Francisco Eiras, Mihai Dobre, Subramanian Ramamoorthy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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 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.

Original language	English
Title of host publication	2021 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	Institute of Electrical and Electronics Engineers
Pages	1043-1049
Number of pages	7
ISBN (Electronic)	978-1-7281-9077-8
ISBN (Print)	978-1-7281-9078-5
DOIs	https://doi.org/10.1109/ICRA48506.2021.9560849
Publication status	Published - 18 Oct 2021
Event	2021 IEEE International Conference on Robotics and Automation - Xi'an, China Duration: 30 May 2021 → 5 Jun 2021

Publication series

Name
ISSN (Print)	1050-4729
ISSN (Electronic)	2577-087X

Conference

Conference	2021 IEEE International Conference on Robotics and Automation
Abbreviated title	ICRA 2021
Country/Territory	China
City	Xi'an
Period	30/05/21 → 5/06/21

Access to Document

10.1109/ICRA48506.2021.9560849Licence: All Rights Reserved

Interpretable Goal-base_ALBRECHT_DOA28022021_AFVAccepted author manuscript, 1.27 MBLicence: All Rights Reserved

https://ieeexplore.ieee.org/document/9560849Licence: All Rights Reserved

Cite this

@inproceedings{c3d424bd5e304028b91bf0ddd613c245,

title = "Interpretable Goal-based Prediction and Planning for Autonomous Driving",

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 rationality principles. Evaluation in simulations of urban driving scenarios demonstrate the system{\textquoteright}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{\textquoteright}s decisions.",

author = "Albrecht, {Stefano V} and Cillian Brewitt and John Wilhelm and Balint Gyevnar and Francisco Eiras and Mihai Dobre and Subramanian Ramamoorthy",

year = "2021",

month = oct,

day = "18",

doi = "10.1109/ICRA48506.2021.9560849",

language = "English",

isbn = "978-1-7281-9078-5",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "1043--1049",

booktitle = "2021 IEEE International Conference on Robotics and Automation (ICRA)",

address = "United States",

note = "2021 IEEE International Conference on Robotics and Automation, ICRA 2021 ; Conference date: 30-05-2021 Through 05-06-2021",

}

Albrecht, SV, Brewitt, C, Wilhelm, J, Gyevnar, B, Eiras, F, Dobre, M & Ramamoorthy, S 2021, Interpretable Goal-based Prediction and Planning for Autonomous Driving. in 2021 IEEE International Conference on Robotics and Automation (ICRA). Institute of Electrical and Electronics Engineers, pp. 1043-1049, 2021 IEEE International Conference on Robotics and Automation, Xi'an, China, 30/05/21. https://doi.org/10.1109/ICRA48506.2021.9560849

TY - GEN

T1 - Interpretable Goal-based Prediction and Planning for Autonomous Driving

AU - Albrecht, Stefano V

AU - Brewitt, Cillian

AU - Wilhelm, John

AU - Gyevnar, Balint

AU - Eiras, Francisco

AU - Dobre, Mihai

AU - Ramamoorthy, Subramanian

PY - 2021/10/18

Y1 - 2021/10/18

N2 - 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 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.

AB - 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 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.

U2 - 10.1109/ICRA48506.2021.9560849

DO - 10.1109/ICRA48506.2021.9560849

M3 - Conference contribution

SN - 978-1-7281-9078-5

SP - 1043

EP - 1049

BT - 2021 IEEE International Conference on Robotics and Automation (ICRA)

PB - Institute of Electrical and Electronics Engineers

T2 - 2021 IEEE International Conference on Robotics and Automation

Y2 - 30 May 2021 through 5 June 2021

ER -

Interpretable Goal-based Prediction and Planning for Autonomous Driving

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this