Deep Visual Teach and Repeat on Path Networks

By Tristan Swedish, Ramesh Raskar. 2018

17 citations recorded by the source corpus.

We propose an approach for solving Visual Teach and Repeat tasks for routes that consist of discrete directions along path networks using deep learning. Visual paths are specified by a single monocular image sequence and our approach does not query frames or image features during inference, but instead is composed of classifiers trained on each path. Our method is efficient for both storing or following paths and enables sharing of visual path specifications between parties without sharing visual data explicitly. We evaluate our approach in a simulated environment, and present qualitative results on real data captured with a smartphone.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Otkrist Gupta
2. Ramesh Raskar
3. Tristan Swedish
4. Abhimanyu Dubey

In Computer Vision and Pattern Recognition

1. Ramesh Raskar
2. Otkrist Gupta
3. Praneeth Vepakomma
4. Tristan Swedish
5. Abhimanyu Dubey

Citations in the corpus

• No Peek: A Survey of private distributed deep learning (2018, background): “Such representations have been shown to preserve information important for certain tasks (path following [4]), without revealing information about the underlying data (such as image features in a 3D coordinate system).”
• Learning Navigation Subroutines from Egocentric Videos (2019, unknown): “These scans have been used to study navigation tasks in [13, 39, 40], and we adapt publicly available simulation code from [13].”