Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers

TL;DR

This paper presents a comprehensive framework for autonomous aerial robots that combines neural network-based target detection with edge computing and a control barrier function for safe, precise physical interaction in industrial environments.

Contribution

It introduces an integrated system that enhances target detection accuracy and safety in aerial robots through neural networks, edge computing, and CBF-based control, tested in simulation and real-world scenarios.

Findings

High detection accuracy under challenging conditions

Effective real-time target pose estimation

Safe convergence to targets demonstrated in simulations

Abstract

The paper introduces a novel framework for safe and autonomous aerial physical interaction in industrial settings. It comprises two main components: a neural network-based target detection system enhanced with edge computing for reduced onboard computational load, and a control barrier function (CBF)-based controller for safe and precise maneuvering. The target detection system is trained on a dataset under challenging visual conditions and evaluated for accuracy across various unseen data with changing lighting conditions. Depth features are utilized for target pose estimation, with the entire detection framework offloaded into low-latency edge computing. The CBF-based controller enables the UAV to converge safely to the target for precise contact. Simulated evaluations of both the controller and target detection are presented, alongside an analysis of real-world detection performance.