Learning to see the wood for the trees: Deep laser localization in urban and natural environments on a CPU

Conference item

Localization in challenging, natural environments, such as forests or woodlands, is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this letter, we explore laser-based localization in both urban and natural environments, which is suitable for online applications. We propose a deep learning approach capable of learning meaningful descriptors directly from three-dimensional point clouds by comparing triplets (anchor, positive, and negative examples). The approach learns a feature space representation for a set of segmented point clouds that are matched between a current and previous observations. Our learning method is tailored toward loop closure detection resulting in a small model that can be deployed using only a CPU. The proposed learning method would allow the full pipeline to run on robots with limited computational payloads, such as drones, quadrupeds, or Unmanned Ground Vehicles (UGVs).

Authors: Fallon, M; Tinchev, G; Penate-Sanchez, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Host title: IEEE Robotics and Automation Letters
• Journal: IEEE Robotics and Automation Letters
• Volume: 4
• Issue: 2
• Pages: 1327-1334
• Publication date: 2019-01-25
• Acceptance date: 2019-01-09
• DOI: 10.1109/LRA.2019.2895264
• ISSN: 2377-3766
• Keywords: FFR