Learning to Navigate by Growing Deep Networks

12/14/2017
by   Thushan Ganegedara, et al.
0

Adaptability is central to autonomy. Intuitively, for high-dimensional learning problems such as navigating based on vision, internal models with higher complexity allow to accurately encode the information available. However, most learning methods rely on models with a fixed structure and complexity. In this paper, we present a self-supervised framework for robots to learn to navigate, without any prior knowledge of the environment, by incrementally building the structure of a deep network as new data becomes available. Our framework captures images from a monocular camera and self labels the images to continuously train and predict actions from a computationally efficient adaptive deep architecture based on Autoencoders (AE), in a self-supervised fashion. The deep architecture, named Reinforced Adaptive Denoising Autoencoders (RA-DAE), uses reinforcement learning to dynamically change the network structure by adding or removing neurons. Experiments were conducted in simulation and real-world indoor and outdoor environments to assess the potential of self-supervised navigation. RA-DAE demonstrates better performance than equivalent non-adaptive deep learning alternatives and can continue to expand its knowledge, trading-off past and present information.

READ FULL TEXT

page 6

page 9

research
04/05/2023

Self-Supervised Siamese Autoencoders

Fully supervised models often require large amounts of labeled training ...
research
05/13/2020

Self-Supervised Deep Visual Odometry with Online Adaptation

Self-supervised VO methods have shown great success in jointly estimatin...
research
09/29/2017

Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

Enabling robots to autonomously navigate complex environments is essenti...
research
05/26/2021

Self-supervised Monocular Multi-robot Relative Localization with Efficient Deep Neural Networks

Relative localization is an important ability for multiple robots to per...
research
05/15/2022

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

In this paper, we present a self-supervised learning framework for conti...
research
08/24/2022

SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge

Unsupervised lifelong learning refers to the ability to learn over time ...
research
06/11/2021

A Novel Approach to Lifelong Learning: The Plastic Support Structure

We propose a novel approach to lifelong learning, introducing a compact ...

Please sign up or login with your details

Forgot password? Click here to reset