Online Self-supervised Scene Segmentation for Micro Aerial Vehicles
This addresses the problem of autonomous flight in complex environments for MAVs, offering an incremental improvement by integrating existing approaches.
The paper tackles robust scene understanding for Micro Aerial Vehicles by proposing a self-supervised online learning framework that combines geometry and data-driven methods, demonstrating efficacy through experiments on benchmarks and real-world tests.
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.