Feudal Networks for Visual Navigation

TL;DR

This paper introduces a hierarchical feudal learning framework for visual navigation that avoids the need for large graphs, odometry, or metric maps, achieving near state-of-the-art results with a novel memory proxy and waypoint network.

Contribution

It proposes a hierarchical feudal learning approach with a self-supervised memory proxy and a pre-trained waypoint network for improved visual navigation.

Findings

Achieves near state-of-the-art performance in image goal navigation.

Eliminates the need for graphs, odometry, and metric maps.

Uses a small set of teleoperation videos for pre-training.

Abstract

Visual navigation follows the intuition that humans can navigate without detailed maps. A common approach is interactive exploration while building a topological graph with images at nodes that can be used for planning. Recent variations learn from passive videos and can navigate using complex social and semantic cues. However, a significant number of training videos are needed, large graphs are utilized, and scenes are not unseen since odometry is utilized. We introduce a new approach to visual navigation using feudal learning, which employs a hierarchical structure consisting of a worker agent, a mid-level manager, and a high-level manager. Key to the feudal learning paradigm, agents at each level see a different aspect of the task and operate at different spatial and temporal scales. Two unique modules are developed in this framework. For the high-level manager, we learn a memory proxy map in a self supervised manner to record prior observations in a learned latent space and avoid the use of graphs and odometry. For the mid-level manager, we develop a waypoint network that outputs intermediate subgoals imitating human waypoint selection during local navigation. This waypoint network is pre-trained using a new, small set of teleoperation videos that we make publicly available, with training environments different from testing environments. The resulting feudal navigation network achieves near SOTA performance, while providing a novel no-RL, no-graph, no-odometry, no-metric map approach to the image goal navigation task.