An Effective Multi-Cue Positioning System for Agricultural Robotics
share
The self-localization capability is a crucial component for Unmanned Ground Vehicles (UGV) in farming applications. Approaches based solely on visual information or on low-cost GPS are easily prone to fail in such scenarios. In this paper, we present a robust and accurate 3D global pose estimation framework, designed to take full advantage of heterogeneous sensory data. By modeling the pose estimation problem as a pose graph optimization, our approach simultaneously mitigates the cumulative drift introduced by motion estimation systems (wheel odometry, visual odometry, ...), and the noise introduced by the raw GPS readings. Along with a suitable motion model, our system also integrates two additional types of constraints: (i) a Digital Elevation Model (DEM) and (ii) a Markov Random Field (MRF) assumption. We demonstrate how using these additional cues substantially reduces the error along the altitude axis, and this benefit spreads to the other components of the state. We report exhaustive experiments combining several sensor setups, showing improvements from 37 GPS. We also show that our approach provides accurate results even if the GPS temporarily change positioning mode. We released our C++ open-source implementation and two challenging datasets with their relative ground truth.
READ FULL TEXT