Machine learning-aided operations and communications of unmanned aerial vehicles: A contemporary survey

H Kurunathan, H Huang, K Li, W Ni… - … Surveys & Tutorials, 2023 - ieeexplore.ieee.org
Over the past decade, Unmanned Aerial Vehicles (UAVs) have provided pervasive, efficient,
and cost-effective solutions for data collection and communications. Their excellent mobility …

A review of UAV autonomous navigation in GPS-denied environments

Y Chang, Y Cheng, U Manzoor, J Murray - Robotics and Autonomous …, 2023 - Elsevier
Unmanned aerial vehicles (UAVs) have drawn increased research interest in recent years,
leading to a vast number of applications, such as, terrain exploration, disaster assistance …

DeepSMOTE: Fusing deep learning and SMOTE for imbalanced data

D Dablain, B Krawczyk… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Despite over two decades of progress, imbalanced data is still considered a significant
challenge for contemporary machine learning models. Modern advances in deep learning …

Contranerf: Generalizable neural radiance fields for synthetic-to-real novel view synthesis via contrastive learning

H Yang, L Hong, A Li, T Hu, Z Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Although many recent works have investigated generalizable NeRF-based novel view
synthesis for unseen scenes, they seldom consider the synthetic-to-real generalization …

Vision based drone obstacle avoidance by deep reinforcement learning

Z Xue, T Gonsalves - Ai, 2021 - mdpi.com
Research on autonomous obstacle avoidance of drones has recently received widespread
attention from researchers. Among them, an increasing number of researchers are using …

Visuomotor reinforcement learning for multirobot cooperative navigation

Z Liu, Q Liu, L Tang, K Jin, H Wang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
This article investigates the multirobot cooperative navigation problem based on raw visual
observations. A fully end-to-end learning framework is presented, which leverages graph …

Grid: A platform for general robot intelligence development

S Vemprala, S Chen, A Shukla, D Narayanan… - arXiv preprint arXiv …, 2023 - arxiv.org
Developing machine intelligence abilities in robots and autonomous systems is an
expensive and time consuming process. Existing solutions are tailored to specific …

Depth-cuprl: Depth-imaged contrastive unsupervised prioritized representations in reinforcement learning for mapless navigation of unmanned aerial vehicles

JC de Jesus, VA Kich, AH Kolling… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
Reinforcement Learning (RL) has presented an impressive performance in video games
through raw pixel imaging and continuous control tasks. However, RL performs poorly with …

Sim-to-real deep reinforcement learning for safe end-to-end planning of aerial robots

HI Ugurlu, XH Pham, E Kayacan - Robotics, 2022 - mdpi.com
In this study, a novel end-to-end path planning algorithm based on deep reinforcement
learning is proposed for aerial robots deployed in dense environments. The learning agent …

A benchmark comparison of four off-the-shelf proprietary visual–inertial odometry systems

P Kim, J Kim, M Song, Y Lee, M Jung, HG Kim - Sensors, 2022 - mdpi.com
Commercial visual–inertial odometry (VIO) systems have been gaining attention as cost-
effective, off-the-shelf, six-degree-of-freedom (6-DoF) ego-motion-tracking sensors for …