Advances in Deep Learning for Drones and Its Applications: 3rd Edition

Dear Colleagues,

Following the outstanding success and high visibility of the first and second editions of our Special Issue, it is with great pleasure that we announce the launch of the third edition.

Unmanned aerial vehicles (UAVs), particularly vertical takeoff and landing (VTOL) platforms, have firmly transitioned from research laboratories to indispensable tools in real-world aerial operations. Today, they are deployed extensively for infrastructure inspection, precision agriculture, and environmental monitoring. However, the next frontier in field robotics lies in heterogeneous collaboration. Integrating the high-altitude vantage points and agility of UAVs with the heavy payload capacity and endurance of unmanned ground vehicles (UGVs) unlocks unprecedented potential for complex, long-term, and multi-domain missions.

Simultaneously, the landscape of machine learning and computer vision is undergoing a massive transformation. Beyond traditional deep neural networks, we are witnessing the rapid emergence of vision–language–action (VLA) models and foundation models that bridge the gap between high-level semantic reasoning, scene understanding, and low-level robotic control. Furthermore, sophisticated advancements in reinforcement learning (RL) and imitation learning (IL) are empowering aerial and ground robots to dynamically adapt to unstructured environments and learn complex behaviors with unparalleled efficiency.

Based on these cutting-edge technological intersections, there is a rapidly growing interest in leveraging next-generation machine learning techniques to push the boundaries of robotic autonomy, perception, and multi-agent collaboration.

Within this context, we invite researchers to submit original papers to this third edition of our Special Issue, focusing on the latest advances in deep learning, computer vision, and machine learning for drones and general field robotics.

Papers are solicited on all areas directly related to these topics, including but not limited to, the following areas of interest:

• UAV and UGV Collaborations: Heterogeneous multi-agent coordination, joint perception, and task allocation;
• Vision–Language–Action (VLA) Models: Applications of foundation models and LLMs/VLMs for aerial and field robotics;
• Advanced Scene Understanding: 3D semantic mapping, spatial reasoning, and modern computer vision for robotic navigation;
• Imitation Learning (IL) and Reinforcement Learning (RL): Continuous/discrete control, sim-to-real transfer, and dynamic environment adaptation;
• Large-Scale Datasets and Benchmarks: Standardized evaluation tools for training and testing deep learning solutions in robotics;
• Deep Neural Networks (DNNs) for Perception: Object detection, instance segmentation, and semantic classification for autonomous navigation;
• State Estimation and Dynamic Identification: Utilizing recurrent networks and novel architectures for robust localization;
• Learning-based Planning and Manipulation: Decision-making, task planning, and physical interaction in cluttered environments;
• Real-Time Data Analytics: Aerial and ground robots-in-the-loop for time-critical decision-making;
• Domain-Specific Applications: Deep learning-powered robotics in precision agriculture, industrial inspection, and search-and-rescue;
• Innovative Design: Novel mechanical and electrical designs optimized for AI-driven aerial and ground vehicles.

Dr. Inkyu Sa
Dr. Marija Popovic
Dr. Ho Seok Ahn
Dr. Chanoh Park
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Drones is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• UAVs
• aerial robots
• drones
• remote sensing
• deep learning
• deep neural networks
• computer vision
• robotic perception

• Advances in Deep Learning for Drones and Its Applications: 2nd Edition in Drones (14 articles)