Map-Based Temporally Consistent Geolocalization through Learning Motion Trajectories

TL;DR

This paper introduces a trajectory learning method using recurrent neural networks for temporally consistent geolocalization on topological maps, leveraging motion trajectories and sequence prediction without requiring initial position.

Contribution

It presents a novel approach that learns motion trajectories with RNNs for self-localization, eliminating the need for initial position and using simple sensors on topological maps.

Findings

Effective trajectory learning with RNNs demonstrated on KITTI dataset

Achieved temporally consistent geolocalization with proposed strategies

Robustness to noisy input and no initial position required

Abstract

In this paper, we propose a novel trajectory learning method that exploits motion trajectories on topological map using recurrent neural network for temporally consistent geolocalization of object. Inspired by human's ability to both be aware of distance and direction of self-motion in navigation, our trajectory learning method learns a pattern representation of trajectories encoded as a sequence of distances and turning angles to assist self-localization. We pose the learning process as a conditional sequence prediction problem in which each output locates the object on a traversable path in a map. Considering the prediction sequence ought to be topologically connected in the graph-structured map, we adopt two different hypotheses generation and elimination strategies to eliminate disconnected sequence prediction. We demonstrate our approach on the KITTI stereo visual odometry dataset which is a city-scale environment and can generate trajectory with metric information. The key benefits of our approach to geolocalization are that 1) we take advantage of powerful sequence modeling ability of recurrent neural network and its robustness to noisy input, 2) only require a map in the form of a graph and simply use an affordable sensor that generates motion trajectory and 3) do not need initial position. The experiments show that the motion trajectories can be learned by training an recurrent neural network, and temporally consistent geolocation can be predicted with both of the proposed strategies.