SnapNav: Learning Mapless Visual Navigation with Sparse Directional Guidance and Visual Reference
Linhai Xie,Andrew Markham,Niki Trigoni,Linhai Xie,Andrew Markham,Niki Trigoni
Learning-based visual navigation still remains a challenging problem in robotics, with two overarching issues: how to transfer the learnt policy to unseen scenarios, and how to deploy the system on real robots. In this paper, we propose a deep neural network based visual navigation system, SnapNav. Unlike map-based navigation or Visual-Teach-and-Repeat (VT&R), SnapNav only receives a few snapshots...
