Mutually Orthogonal Metric, ECMR’2021

Our work “Be your own Benchmark: No-Reference Trajectory Metric on Registered Point Clouds” lead by Anastasiia Kornilova has been recently accepted for the ECMR 2021 conference.

This works tries to answer the question: How to asses the quality of a trajectory without proper ground truth? We have proposed a method based on the Mutually Orthogonal Metric (MOM), a no-reference metric that estimates the quality of the map from registered point clouds via the trajectory poses.

This work has been accepted for the European Conference on Mobile Robotics (ECMR) 2021.