Online Self-supervised Scene Segmentation for Micro Aerial Vehicles

TL;DR

This paper introduces an online self-supervised learning framework for scene segmentation in lightweight Micro Aerial Vehicles, enabling robust, long-range perception without extensive manual annotations, suitable for high-speed autonomous flight.

Contribution

The paper proposes a novel adaptive scene segmentation system that combines geometry and data-driven methods with self-supervised online learning for MAVs.

Findings

Effective scene segmentation demonstrated on benchmark datasets.

System enables long-range perception in real-world MAV flights.

Reduces reliance on manual annotations for training.

Abstract

Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles (MAVs). As these robots aspire for high-speed autonomous flights in complex dynamic environments, robust scene understanding at long-range becomes critical. The problem is heavily characterized by either the limitations imposed by sensor capabilities for geometry-based methods, or the need for large-amounts of manually annotated training data required by data-driven methods. This motivates the need to build systems that have the capability to alleviate these problems by exploiting the complimentary strengths of both geometry and data-driven methods. In this paper, we take a step in this direction and propose a generic framework for adaptive scene segmentation using self-supervised online learning. We present this in the context of vision-based autonomous MAV flight, and demonstrate the efficacy of our proposed system through extensive experiments on benchmark datasets and real-world field tests.