Obstacle Avoidance Using a Monocular Camera

TL;DR

This paper presents a monocular camera-based obstacle avoidance system for small UAVs, combining neural networks and path planning to enable safe navigation in cluttered environments.

Contribution

It introduces a hybrid neural network approach integrated with a path planner for obstacle avoidance using only a monocular camera.

Findings

Achieves low collision rates in simulated obstacle courses.

Maintains relevant flight speeds during navigation.

Demonstrates effective depth estimation from monocular images.

Abstract

A collision avoidance system based on simple digital cameras would help enable the safe integration of small UAVs into crowded, low-altitude environments. In this work, we present an obstacle avoidance system for small UAVs that uses a monocular camera with a hybrid neural network and path planner controller. The system is comprised of a vision network for estimating depth from camera images, a high-level control network, a collision prediction network, and a contingency policy. This system is evaluated on a simulated UAV navigating an obstacle course in a constrained flight pattern. Results show the proposed system achieves low collision rates while maintaining operationally relevant flight speeds.