Multi-Sensor Fusion for Motion Estimation in Visually-Degraded Environments

Mikhail Sizintsev, Abhinav Rajvanshi, Han-Pang Chiu, Kevin Kaighn, Supun Samarasekera, David P. Snyder

Abstract:

Accurate motion estimation using low-cost sensors for autonomous robots in visually-degraded environments is
critical to applications such as infrastructure inspection and indoor rescue missions. This paper analyzes the feasibility of
utilizing multiple low-cost on-board sensors for ground robots or drones navigating in visually-degraded environments. We
select four low-cost and small-size sensors for evaluation: IMU, EO stereo cameras with LED lights, active IR cameras, and
2D LiDAR. We adapt and extend state-of-the-art multi-sensor motion estimation techniques, including a factor graph framework for sensor fusion, under poor illumination conditions. We evaluate different sensor combinations using the factor
graph framework, and benchmark each combination with its accuracy for two representative datasets acquired in totally dark
environments. Our results show the potential of this sensor fusion approach towards an improved ego-motion solution in
challenging dark environments.