Online Visual Robot Tracking and Identification Using Deep LSTM Networks

Hafez Farazi1, Sven Behnke1

  • 1University of Bonn

Details

11:15 - 11:30 | Mon 25 Sep | Room 109 | MoAT1.4

Session: Deep Learning in Robotics and Automation I

Abstract

Collaborative robots working on a common task are necessary for many applications. One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification. We present a novel pipeline for online vision-based detection, tracking and identification of robots with a known and identical appearance. Our method runs in real-time on the limited hardware of the observer robot. Unlike previous works addressing robot tracking and identification, we use a data-driven approach based on recurrent neural networks to learn relations between sequential inputs and outputs. We formulate the data association problem as multiple classification problems. A deep LSTM network was trained on a simulated dataset and fine-tuned on small set of real data. Experiments on two challenging datasets, one synthetic and one real, which include long-term occlusions, show promising results.