Dynamic Parameter Update for Robot Navigation Systems through Unsupervised Environmental Situational Analysis

A robot’s local navigation is often done through forward simulation of robot velocities and measuring the possible trajectories against safety, distance to the final goal and the generated path of a global path planner. Then, the computed velocities vector for the winning trajectory is executed on the robot. This process is done continuously through the whole navigation process and requires an extensive amount of processing. This only allows for a very limited sampling space. In this paper, we propose a novel approach to automatically detect the type of surrounding environment based on navigation complexity using unsupervised clustering, and limit the local controller’s sampling space. The experimental results in 3D simulation and using a real mobile robot show that we can increase the navigation performance by at least thirty percent while reducing the number of failures due to collision or lack of sampling