Simultaneous Localization and Mapping with Dynamic Rigid Objects
This addresses the challenge of SLAM in dynamic settings for autonomous robotics, though it is incremental as it builds on classical SLAM with a new motion representation.
The paper tackles the problem of performing simultaneous localization and mapping (SLAM) in dynamic environments by integrating the motion of rigid objects without estimating their pose or geometry, resulting in consistent improvements in robot localization and mapping accuracy.
Accurate estimation of the environment structure simultaneously with the robot pose is a key capability of autonomous robotic vehicles. Classical simultaneous localization and mapping (SLAM) algorithms rely on the static world assumption to formulate the estimation problem, however, the real world has a significant amount of dynamics that can be exploited for a more accurate localization and versatile representation of the environment. In this paper we propose a technique to integrate the motion of dynamic objects into the SLAM estimation problem, without the necessity of estimating the pose or the geometry of the objects. To this end, we introduce a novel representation of the pose change of rigid bodies in motion and show the benefits of integrating such information when performing SLAM in dynamic environments. Our experiments show consistent improvement in robot localization and mapping accuracy when using a simple constant motion assumption, even for objects whose motion slightly violates this assumption.