Gesture Control of Micro-drone: A Lightweight-Net with Domain Randomization and Trajectory Generators

TL;DR

This paper introduces a lightweight deep neural network with domain randomization and trajectory generation for gesture-based micro-drone control, achieving efficient computation and promising navigation performance with low-resource hardware.

Contribution

The study presents a novel, computationally-efficient CNN with attention and trajectory modules for gesture-controlled micro-drones, improving performance while reducing resource consumption.

Findings

18% computational resource savings during training

Successful micro-drone navigation using the proposed model

Outperforms conventional vision-based techniques

Abstract

Micro-drones can be integrated into various industrial applications but are constrained by their computing power and expert pilots, a secondary challenge. This study presents a computationally-efficient deep convolutional neural network that utilizes Gabor filters and spatial separable convolutions with low computational complexities. An attention module is integrated with the model to complement the performance. Further, perception-based action space and trajectory generators are integrated with the model's predictions for intuitive navigation. The computationally-efficient model aids a human operator in controlling a micro-drone via gestures. Nearly 18% of computational resources are conserved using the NVIDIA GPU profiler during training. Using a low-cost DJI Tello drone for experiment verification, the computationally-efficient model shows promising results compared to a state-of-the-art and conventional computer vision-based technique.