Hierarchical end-to-end autonomous navigation through few-shot waypoint detection
This addresses the problem of simplifying autonomous navigation for robotics by mimicking human-like landmark-based navigation, though it appears incremental as it builds on few-shot learning techniques.
The paper tackled autonomous navigation by enabling a mobile robot to navigate unknown environments using only a few sample images of landmarks and corresponding actions, reducing reliance on complex sensors and data streams. It demonstrated effectiveness with a small-scale vehicle in novel indoor tasks, achieving simplified wayfinding and easy adaptation.
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.