arXiv Analytics

Sign in

arXiv:1909.09295 [cs.RO]AbstractReferencesReviewsResources

Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation

David Watkins-Valls, Jingxi Xu, Nicholas Waytowich, Peter Allen

Published 2019-09-20Version 1

We present a robot navigation system that uses an imitation learning framework to successfully navigate in complex environments. Our framework takes a pre-built 3D scan of a real environment and trains an agent from pre-generated expert trajectories to navigate to any position given a panoramic view of the goal and the current visual input without relying on map, compass, odometry, GPS or relative position of the target at runtime. Our end-to-end trained agent uses RGB and depth (RGBD) information and can handle large environments (up to $1031m^2$) across multiple rooms (up to $40$) and generalizes to unseen targets. We show that when compared to several baselines using deep reinforcement learning and RGBD SLAM, our method (1) requires fewer training examples and less training time, (2) reaches the goal location with higher accuracy, (3) produces better solutions with shorter paths for long-range navigation tasks, and (4) generalizes to unseen environments given an RGBD map of the environment.

Related articles: Most relevant | Search more
arXiv:1909.11337 [cs.RO] (Published 2019-09-25)
OCTNet: Trajectory Generation in New Environments from Past Experiences
arXiv:1806.02501 [cs.RO] (Published 2018-06-07)
Simplifying Reward Design through Divide-and-Conquer
arXiv:2002.05700 [cs.RO] (Published 2020-02-13)
BADGR: An Autonomous Self-Supervised Learning-Based Navigation System