Safe driving requires autonomous vehicles to anticipate potential hidden traffic participants and other unseen objects, such as a cyclist hidden behind a large vehicle, or an object on the road hidden behind a building. Existing methods are usually unable to consider all possible shapes and orientations of such obstacles. They also typically do not reason about observations of hidden obstacles over time, leading to conservative anticipations. We overcome these limitations by (1) modeling possible hidden obstacles as a set of states of a point mass model and (2) sequential reasoning based on reachability analysis and previous observations. Based on (1), our method is safer, since we anticipate obstacles of arbitrary unknown shapes and orientations. In addition, (2) increases the available drivable space when planning trajectories for autonomous vehicles. In our experiments, we demonstrate that our method, at no expense of safety, gives rise to significant reductions in time to traverse various intersection scenarios from the CommonRoad Benchmark Suite. ; Published in 2022 IEEE Intelligent Vehicles Symposium (IV), Aachen, 04-09 June 2022, see https://ieeexplore.ieee.org/document/9827171 QC 20220208


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Foresee the Unseen : Sequential Reasoning about Hidden Obstacles for Safe Driving


    Beteiligte:

    Medientyp :

    Paper


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Foresee the Unseen: Sequential Reasoning about Hidden Obstacles for Safe Driving

    Sanchez, Jose Manuel Gaspar / Nyberg, Truls / Pek, Christian et al. | IEEE | 2022


    Foresee trat an die Oeffentlichkeit

    Foresee,Bad Homburg,DE | Kraftfahrwesen | 1996


    Foresee: Blick in die Zukunft

    Online Contents | 1996


    Foresee wider use of exhaust jet cooling

    McRoberts, L. | Engineering Index Backfile | 1947


    The ‘FORESEE’ Prototype, Fully Active, Steered Two Axle Railway Vehicle

    Iwnicki, Simon / Jonsson, Per-Anders / Gustafsson, Jorgen et al. | TIBKAT | 2020