Zoom Link: https://cmu.zoom.us/j/97161117200?pwd=QlpkS0hFOFVLRDlKVlFqby9JbWZTUT09

Title: Towards Robust Multi-Camera Visual Inertial Odometry

Abstract:
Visual inertial odometry (VIO) has become an increasingly popular method of obtaining a state estimate on board smaller robots like micro aerial vehicles (MAVs). While VIO has demonstrated impressive results in certain environments, there is still work to be done in improving the robustness of these algorithms. In this work we present a novel multi-camera VIO framework which aims to improve the robustness of a robot’s state estimate during aggressive motion and in visually challenging environments. Our system uses a fixed-lag smoother which jointly optimizes for poses and landmarks across all cameras. We propose a 1-point RANdom SAmple Consensus (RANSAC) algorithm which is able to perform outlier rejection across features from multiple stereo pairs. To handle the problem of noisy extrinsics, we account for uncertainty in the calibration of each camera and model it in both our front-end and back-end. The result is a VIO system which is able to maintain an accurate state estimate under conditions that have typically proven to be challenging for traditional state-of-the-art VIO systems. We demonstrate the benefits of our proposed multi-camera algorithm by evaluating it with both simulated and real world data. We show that our proposed algorithm is able to maintain a state estimate in scenarios where traditional VIO algorithms fail.

Committee:
Michael Kaess (advisor)
Simon Lucey
Alexander Spitzer