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

arXiv: https://arxiv.org/abs/2410.15802 · HTML: https://mlsanity.com/paper/2410.15802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 41 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 7 of 7)

- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Deep Learning vs. Traditional Computer Vision](https://mlsanity.com/paper/1910.13796/) (2019)
- [Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles](https://mlsanity.com/paper/2205.14942/) (2022)
- [Dense 3D Reconstruction for Visual Tunnel Inspection using Unmanned Aerial Vehicle](https://mlsanity.com/paper/1911.03603/) (2019)
- [A Subterranean Virtual Cave World for Gazebo based on the DARPA SubT Challenge](https://mlsanity.com/paper/2004.08452/) (2020)
- [A Resilient Framework for 5G-Edge-Connected UAVs based on Switching Edge-MPC and Onboard-PID Control](https://mlsanity.com/paper/2310.15849/) (2023)
- [Adaptive Control of Euler-Lagrange Systems under Time-varying State Constraints without a Priori Bounded Uncertainty](https://mlsanity.com/paper/2311.00067/) (2023)

## Abstract (arXiv)

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.