Learning by Cheating : An End-to-End Zero Shot Framework for Autonomous Drone Navigation

TL;DR

This paper introduces a zero-shot learning framework for autonomous drone navigation that trains simple control policies in a basic environment and applies them to complex environments by tricking the controller into perceiving it is still in the training setting.

Contribution

It presents a novel end-to-end framework that enables transfer of control policies from simple to complex environments and offers interpretability for reinforcement learning.

Findings

Effective transfer of control policies to complex environments

Framework can be adapted for reuse in various tasks

Provides insights into reinforcement learning interpretation

Abstract

This paper proposes a novel framework for autonomous drone navigation through a cluttered environment. Control policies are learnt in a low-level environment during training and are applied to a complex environment during inference. The controller learnt in the training environment is tricked into believing that the robot is still in the training environment when it is actually navigating in a more complex environment. The framework presented in this paper can be adapted to reuse simple policies in more complex tasks. We also show that the framework can be used as an interpretation tool for reinforcement learning algorithms.