AI-Enhanced Perception and Multi-Sensor Fusion for Unmanned Systems

Dear Colleagues,

Unmanned systems—including aerial, ground, and underwater vehicles—are becoming increasingly integral to modern societies. AI-enhanced perception and multi-sensor data fusion, which enables these systems to share and integrate sensor data, overcome occlusion challenges, and achieve more accurate and robust environmental awareness—will play a key role in this evolution. These capabilities are essential for safe and efficient operations in complex transportation, industrial, and environmental monitoring environments. This is particularly relevant in the context of low-altitude economy, where intelligent perception technologies are essential for enabling safe and efficient drone operations in complex urban environments. By fusing multi-source, heterogeneous data from sensors such as radar, cameras, LiDAR, and inertial measurement units, AI-driven perception enhances the capabilities of unmanned system operating in diverse domains.

This Special Issue aims to explore the modeling, development and application of AI-enhanced perception and multi-sensor data fusion for unmanned systems, with emphasis on how these technologies enhance system performance across multiple domains. A particularly compelling case is the integration application of aerial and ground unmanned vehicles: the efficiency of complex missions can be greatly improved by leveraging the complementary strengths of UAVs (wide field of view, rapid deployment) and UGVs (extended endurance, precise manipulation capabilities). However, contributions are not limited to this scenario—we also welcome studies addressing underwater vehicles and other unmanned platforms. Beyond platform-level integration, we also place strong emphasis on swarm intelligence and multi-agent collaboration, both of which are essential for translating enhanced perception into coordinated action in dynamic environments.

We welcome contributions from researchers across disciplines—including robotics, computer vision, artificial intelligence, and sensor fusion—who are working at the intersection of perception, learning, and control for unmanned systems. Submissions should demonstrate a clear connection to unmanned-system-based data collection, deployment, or system-centric analysis—with methodologies, validations, and insights grounded in specific unmanned system scenarios. We particularly encourage studies that address the technical challenges of multi-sensor fusion, data sharing, and AI-driven collaborative decision-making in heterogeneous unmanned systems. In particular, we are interested in contributions that bridge perception and decision-making at both the single-agent and multi-agent levels, including distributed perception architectures, consensus-based data fusion, and human-on-the-loop supervision in heterogeneous unmanned teams.

Topics include, but are not limited to, the following:

• Development of new sensors and innovative data fusion algorithms for unmanned systems;
• Remote sensing and data fusion for cooperative multi-platform systems;
• Localization and high-definition map for unmanned systems;
• Deep-reinforcement learning for multi-agent cooperative perception systems;
• AI-empowered collaborative perception for unmanned systems;
• Modeling, simulation, and dynamic analysis of collaboration system for unmanned systems;
• Decision-making in heterogeneous unmanned teams operating in complex environments;
• Parameter identification and state estimation of unmanned systems;
• Methods for predicting trajectories of unmanned systems in collaborative scenarios;
• Design of new sensors and novel estimation and data fusion algorithms for unmanned systems;
• Spiking Neural Network and neuromorphic computing in the context of unmanned systems.
• Swarm intelligence, multi-agent perception, and distributed coordination for unmanned systems.

Dr. Jinsheng Xiao
Dr. Yunhua Chen
Dr. Jian Zhou
Dr. Sheng Bao
Dr. Hailong Shi
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.

• AI-enhanced perception
• unmanned systems
• collaborative perception
• sensor fusion
• multi-agent perception
• intelligent sensing
• situational awareness
• multi-agent collaboration
• swarm intelligence