DeepAI AI Chat
Log In Sign Up

Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour

by   Xihan Bian, et al.

Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26 reduction in training time, while also increasing accuracy.


page 1

page 4

page 6


Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

In this paper we consider the problem of robot navigation in simple maze...

Learning to Navigate in Complex Environments

Learning to navigate in complex environments with dynamic elements is an...

Mimicking the Behaviour of Idiotypic AIS Robot Controllers Using Probabilistic Systems

Previous work has shown that robot navigation systems that employ an arc...

The Use of Probabilistic Systems to Mimic the Behaviour of Idiotypic AIS Robot Controllers

Previous work has shown that robot navigation systems that employ an arc...

Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation

There has been an increasing interest in 3D indoor navigation, where a r...

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning

We seek to efficiently learn by leveraging shared structure between diff...

Towards the Neuromorphic Computing for Offroad Robot Environment Perception and Navigation

My research objective is to explicitly bridge the gap between high compu...