Receding Horizon Navigation and Target Tracking for Aerial Detection of Transient Radioactivity

TL;DR

This paper introduces a receding horizon control method enabling quadrotor MAVs to autonomously navigate and intercept moving targets in cluttered, unknown environments using onboard sensors and neural networks, without prior environment knowledge.

Contribution

It proposes a novel real-time motion planning and control strategy combining sensor data and neural networks for reactive target interception by MAVs.

Findings

Successfully intercepts moving targets up to 5 m/s

Operates effectively in cluttered indoor and outdoor environments

Demonstrates real-time performance with onboard computation

Abstract

The paper presents a receding horizon planning and control strategy for quadrotor-type \ac{mav}s to navigate reactively and intercept a moving target in a cluttered unknown and dynamic environment. Leveraging a lightweight short-range sensor that generates a point-cloud within a relatively narrow and short \ac{fov}, and an \acs{ssd}-MobileNet based Deep neural network running on board the \ac{mav}, the proposed motion planning and control strategy produces safe and dynamically feasible \ac{mav} trajectories within the sensor \acs{fov}, which the vehicle uses to autonomously navigate, pursue, and intercept its moving target. This task is completed without reliance on a global planner or prior information about the environment or the moving target. The effectiveness of the reported planner is demonstrated numerically and experimentally in cluttered indoor and outdoor environments featuring maximum speeds of up to 4.5-5~m/s.