Machine learning-aided operations and communications of unmanned aerial vehicles: A contemporary survey
Over the past decade, Unmanned Aerial Vehicles (UAVs) have provided pervasive, efficient,
and cost-effective solutions for data collection and communications. Their excellent mobility …
and cost-effective solutions for data collection and communications. Their excellent mobility …
A review of UAV autonomous navigation in GPS-denied environments
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 …
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 …
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
Although many recent works have investigated generalizable NeRF-based novel view
synthesis for unseen scenes, they seldom consider the synthetic-to-real generalization …
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 …
attention from researchers. Among them, an increasing number of researchers are using …
Visuomotor reinforcement learning for multirobot cooperative navigation
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 …
observations. A fully end-to-end learning framework is presented, which leverages graph …
Grid: A platform for general robot intelligence development
Developing machine intelligence abilities in robots and autonomous systems is an
expensive and time consuming process. Existing solutions are tailored to specific …
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
Reinforcement Learning (RL) has presented an impressive performance in video games
through raw pixel imaging and continuous control tasks. However, RL performs poorly with …
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
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 …
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
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 …
effective, off-the-shelf, six-degree-of-freedom (6-DoF) ego-motion-tracking sensors for …