Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

TL;DR

This paper introduces a novel target-driven visual navigation system for indoor scenes that uses generative imitation learning, multi-view observations, and auxiliary tasks to improve safety, efficiency, and generalization without relying on GPS or odometry.

Contribution

It proposes a new navigation framework with a variational generative module, collision prediction, and target checking, enhancing mapless navigation performance and data efficiency.

Findings

Effective real-world navigation on a TurtleBot

Improved safety through static collision prediction

Enhanced generalization in indoor environments

Abstract

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the robot to the target without relying on odometry or GPS at runtime. The system is learned by optimizing a combinational objective encompassing three key designs. First, we propose that an agent conceives the next observation before making an action decision. This is achieved by learning a variational generative module from expert demonstrations. We then propose predicting static collision in advance, as an auxiliary task to improve safety during navigation. Moreover, to alleviate the training data imbalance problem of termination action prediction, we also introduce a target checking module to differentiate from augmenting navigation policy with a termination action. The three proposed designs all contribute to the improved training data efficiency, static collision avoidance, and navigation generalization performance, resulting in a novel target-driven mapless navigation system. Through experiments on a TurtleBot, we provide evidence that our model can be integrated into a robotic system and navigate in the real world. Videos and models can be found in the supplementary material.