Range-Visual-Inertial Odometry: Scale Observability Without Excitation
This solves the scale drift issue for robotics applications like aerial vehicles, enabling efficient constant-velocity operations without terrain limitations, though it builds incrementally on prior work like NASA's Ingenuity approach.
The paper tackles the problem of scale unobservability in monocular visual-inertial odometry (VIO) during constant-velocity motion by incorporating a 1D laser range finder with a novel facet constraint model, enabling scale observability without accelerometer excitation and demonstrating robustness in real flight data over arbitrary terrain.
Traveling at constant velocity is the most efficient trajectory for most robotics applications. Unfortunately without accelerometer excitation, monocular Visual-Inertial Odometry (VIO) cannot observe scale and suffers severe error drift. This was the main motivation for incorporating a 1D laser range finder in the navigation system for NASA's Ingenuity Mars Helicopter. However, Ingenuity's simplified approach was limited to flat terrains. The current paper introduces a novel range measurement update model based on using facet constraints. The resulting range-VIO approach is no longer limited to flat scenes, but extends to any arbitrary structure for generic robotic applications. An important theoretical result shows that scale is no longer in the right nullspace of the observability matrix for zero or constant acceleration motion. In practical terms, this means that scale becomes observable under constant-velocity motion, which enables simple and robust autonomous operations over arbitrary terrain. Due to the small range finder footprint, range-VIO retains the minimal size, weight, and power attributes of VIO, with similar runtime. The benefits are evaluated on real flight data representative of common aerial robotics scenarios. Robustness is demonstrated using indoor stress data and fullstate ground truth. We release our software framework, called xVIO, as open source.