Hierarchical end-to-end autonomous navigation through few-shot waypoint detection

TL;DR

This paper introduces a hierarchical end-to-end meta-learning approach that allows a robot to navigate new environments using only a few images of landmarks, mimicking human navigation simplicity.

Contribution

It presents a novel few-shot waypoint detection method using metric-based learning, enabling autonomous navigation with minimal environmental data.

Findings

Effective in novel indoor environments

Requires only a few landmark images for navigation

Outperforms traditional navigation methods

Abstract

Human navigation is facilitated through the association of actions with landmarks, tapping into our ability to recognize salient features in our environment. Consequently, navigational instructions for humans can be extremely concise, such as short verbal descriptions, indicating a small memory requirement and no reliance on complex and overly accurate navigation tools. Conversely, current autonomous navigation schemes rely on accurate positioning devices and algorithms as well as extensive streams of sensory data collected from the environment. Inspired by this human capability and motivated by the associated technological gap, in this work we propose a hierarchical end-to-end meta-learning scheme that enables a mobile robot to navigate in a previously unknown environment upon presentation of only a few sample images of a set of landmarks along with their corresponding high-level navigation actions. This dramatically simplifies the wayfinding process and enables easy adoption to new environments. For few-shot waypoint detection, we implement a metric-based few-shot learning technique through distribution embedding. Waypoint detection triggers the multi-task low-level maneuver controller module to execute the corresponding high-level navigation action. We demonstrate the effectiveness of the scheme using a small-scale autonomous vehicle on novel indoor navigation tasks in several previously unseen environments.