Experiential Mapping and Localization - Honda Research Institute USA

Experiential Mapping and Localization

Experiential Mapping and Localization

An accurate mapping and localization system acts as a memory module which greatly simplifies the tasks of perception and planning by putting ego car in a context. While classical SLAM (Simultaneous Localization and Mapping) solves this problem to some extent, it leaves many unrealistic assumptions for autonomous driving, e.g. static environment, similar visual appearances between sessions, etc. We aim to address these challenges by the “experiential mapping” concept, where we draw intuition from human driving experience. The result is a more robust mapping and localization system which evolves over time and focuses on important information.

Related Publications

    Mahmut Demir, Kikuo Fujimura
    Robust Localization with Low-Mounted Multiple LiDARs in Urban Environments
    IEEE International Conference on Intelligent Transportation (ITSC) 2019
    October, 2019 -

    In this paper, we propose a robust, real-time and scalable localization framework for multi-LiDAR equipped vehicles in challenging urban environments. Our test vehicle uses multiple LiDARs with low mounting positions which makes the localization task very challenging in dense traffic scenarios due to the reduced field-of-view of LiDARs and additional uncertainty introduced by the dynamic vehicles. In order to increase the robustness and provide consistently smooth localization output, LiDAR localization is fused with the dead reckoning using the probabilistic scan matching confidence estimation method. We conducted experiments in different urban settings and results confirmed that our framework can operate reliably with low-position multi-LiDAR suite under various traffic scenarios.

Related Research Areas