Cèsar-Tondreau, BrianWarnell, GarrettStump, EthanKochersberger, Kevin B.Waytowich, Nicholas R.2021-09-022021-09-022021-06-01Cèsar-Tondreau B, Warnell G, Stump E, Kochersberger K and Waytowich NR (2021) Improving Autonomous Robotic Navigation Using Imitation Learning. Front. Robot. AI 8:627730. doi: 10.3389/frobt.2021.627730http://hdl.handle.net/10919/104917Autonomous navigation to a specified waypoint is traditionally accomplished with a layered stack of global path planning and local motion planning modules that generate feasible and obstacle-free trajectories. While these modules can be modified to meet task-specific constraints and user preferences, current modification procedures require substantial effort on the part of an expert roboticist with a great deal of technical training. In this paper, we simplify this process by inserting a Machine Learning module between the global path planning and local motion planning modules of an off-the shelf navigation stack. This model can be trained with human demonstrations of the preferred navigation behavior, using a training procedure based on Behavioral Cloning, allowing for an intuitive modification of the navigation policy by non-technical users to suit task-specific constraints. We find that our approach can successfully adapt a robot’s navigation behavior to become more like that of a demonstrator. Moreover, for a fixed amount of demonstration data, we find that the proposed technique compares favorably to recent baselines with respect to both navigation success rate and trajectory similarity to the demonstrator.10 pagesapplication/pdfenCreative Commons Attribution 4.0 Internationalautonomous navigationlearning from demonstrationimitation learninghuman in the looprobot learning and behavior adaptationArticle - Refereedhttps://doi.org/10.3389/frobt.2021.6277308