The field of motion prediction for automated driving has seen tremendous progress recently, bearing ever-more mighty neural network architectures. Leveraging these powerful models bears great potential for the closely related planning task. In this work, we show that state-of-the-art prediction models can be converted into goal-directed planners. To this end, we propose a novel goal-conditioning method. Our key insight is that conditioning prediction on a navigation goal at the behaviour level outperforms other widely adopted methods, with the additional benefit of increased model interpretability. Moreover, our Method can be applied at inference time only. Hence, no ground-truth navigation command is required during training. We evaluate our method on a large open-source dataset and show promising performance in a comprehensive benchmark. Code is available under https://mh0797.github.io/gc-pgp/.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    From Prediction to Planning With Goal Conditioned Lane Graph Traversals


    Contributors:


    Publication date :

    2023-09-24


    Size :

    2686546 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A visual display aid for planning rover traversals

    BERNARD, HERBERT / ELLIS, STEPHEN | AIAA | 1992


    A visual display aid for planning rover traversals

    Bernard, Herbert F. / Ellis, Stephen R. | NTRS | 1992


    Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning

    HUANG MINGLEI / ZHAN WEI / TOMIZUKA MASAYOSHI et al. | European Patent Office | 2024

    Free access

    Lunar Surface Potential Increases during Terrestrial Bow Shock Traversals

    Collier, Michael R. / Stubbs, Timothy J. / Hills, H. Kent et al. | NTRS | 2009


    MOTION GRAPH CONSTRUCTION AND LANE LEVEL ROUTE PLANNING

    LIU SHIH-YUAN | European Patent Office | 2021

    Free access