Image-Goal Navigation in Complex Environments via Modular Learning

TL;DR

This paper introduces a modular approach for image-goal navigation that improves success and collision rates in complex environments by decoupling navigation components and converting image goals into point-goal tasks.

Contribution

The paper proposes a novel modular framework for image-goal navigation that enhances generalization and efficiency by separating goal planning, collision avoidance, and stopping mechanisms.

Findings

Achieves at least 17% higher success rate in real environments.

Reduces collision rate by 23% compared to state-of-the-art models.

Effective in both simulation and real-world tests.

Abstract

We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning, collision avoidance, and navigation ending prediction, which enables more concentrated learning of each part. This is realized by four different modules. The first module maintains an obstacle map during robot navigation. The second predicts a long-term goal on the real-time map periodically, which can thus convert an image-goal navigation task to several point-goal navigation tasks. To achieve these point-goal navigation tasks, the third module plans collision-free command sets for navigating to these long-term goals. The final module stops the robot properly near the goal image. The four modules are designed or maintained separately, which helps cut down the search time during navigation and improves the generalization to previously unseen real scenes. We evaluate the method in both a simulator and in the real world with a mobile robot. The results in real complex environments show that our method attains at least a $17\%$ increase in navigation success rate and a $23\%$ decrease in navigation collision rate over some state-of-the-art models.