Flow Synthesis Based Visual Servoing Frameworks for Monocular Obstacle Avoidance Amidst High-Rises

TL;DR

This paper introduces a flow synthesis visual servoing framework for MAVs that enables long-range obstacle avoidance among skyscrapers by synthesizing flows to guide safe navigation in complex urban environments.

Contribution

The paper presents a novel flow synthesis approach for visual servoing that effectively guides MAVs around high-rise obstacles, improving long-range obstacle avoidance capabilities.

Findings

Successfully navigates high-rise environments in simulation and real scenes

Outperforms optical flow and depth-based methods in obstacle avoidance

Uses a multi-step CEM control for flow convergence and safe maneuvering

Abstract

We propose a novel flow synthesis based visual servoing framework enabling long-range obstacle avoidance for Micro Air Vehicles (MAV) flying amongst tall skyscrapers. Recent deep learning based frameworks use optical flow to do high-precision visual servoing. In this paper, we explore the question: can we design a surrogate flow for these high-precision visual-servoing methods, which leads to obstacle avoidance? We revisit the concept of saliency for identifying high-rise structures in/close to the line of attack amongst other competing skyscrapers and buildings as a collision obstacle. A synthesised flow is used to displace the salient object segmentation mask. This flow is so computed that the visual servoing controller maneuvers the MAV safely around the obstacle. In this approach, we use a multi-step Cross-Entropy Method (CEM) based servo control to achieve flow convergence, resulting in obstacle avoidance. We use this novel pipeline to successfully and persistently maneuver high-rises and reach the goal in simulated and photo-realistic real-world scenes. We conduct extensive experimentation and compare our approach with optical flow and short-range depth-based obstacle avoidance methods to demonstrate the proposed framework's merit. Additional Visualisation can be found at https://sites.google.com/view/monocular-obstacle/home