Robust Vision-based Obstacle Avoidance for Micro Aerial Vehicles in Dynamic Environments

TL;DR

This paper introduces a vision-based collision avoidance system for micro aerial vehicles that uses depth images and a chance-constrained model predictive controller to navigate safely among moving obstacles in dynamic environments.

Contribution

It presents a novel on-board obstacle detection, tracking, and avoidance method combining depth imaging with a chance-constrained MPC for MAVs in dynamic settings.

Findings

Effective online collision avoidance demonstrated in various environments.

The approach accounts for MAV and obstacle sensing uncertainties.

Robust avoidance achieved with real-time implementation on a quadrotor.

Abstract

In this paper, we present an on-board vision-based approach for avoidance of moving obstacles in dynamic environments. Our approach relies on an efficient obstacle detection and tracking algorithm based on depth image pairs, which provides the estimated position, velocity and size of the obstacles. Robust collision avoidance is achieved by formulating a chance-constrained model predictive controller (CC-MPC) to ensure that the collision probability between the micro aerial vehicle (MAV) and each moving obstacle is below a specified threshold. The method takes into account MAV dynamics, state estimation and obstacle sensing uncertainties. The proposed approach is implemented on a quadrotor equipped with a stereo camera and is tested in a variety of environments, showing effective on-line collision avoidance of moving obstacles.