Guest Editors
Prof. Dr. Hwangnam Kim
Email: hnkim@korea.ac.kr
Affiliation: School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea
Homepage:
Research Interests: Unmanned aerial vehicles, Counter-drone systems, Multi-agent system, Blockchain platforms, Reinforcement learning, Resource-constrained learning, Autonomous swarms, Cyber-physical systems, and mobile computing
Prof. Dr. Jin Tae Kwak
Email: jkwak@korea.ac.kr
Affiliation: School of Electrical Engineering, Korea University, Seoul 02841, Korea
Homepage:
Research Interests: Data mining, Artificial intelligence, Machine learning, and deep learning, Multimodal medical imaging, Computer-aided diagnosis
Assist. Prof. Hae Beom Lee
Email: haebeomlee@korea.ac.kr
Affiliation: School of Electrical Engineering, Korea University, Seoul 02841, Korea
Homepage:
Research Interests: Inter-task generalization such as meta-learning, transfer Learning, multi-task Learning, and continual Learning, Practical machine learning such as AutoML, hyperparameter optimization, and bi-level optimization, Large language model reasoning, System 2 deep learning, Probabilistic inferences such as Bayesian deep learning and Generative Flow Networks
Summary
The growing complexity of real-world applications for unmanned vehicles—such as aerial drones, ground robots, and autonomous marine systems—requires a shift toward learning frameworks that generalize across tasks and adapt to changing environments. These vehicles are increasingly deployed in heterogeneous and often unpredictable settings, including urban infrastructure monitoring, autonomous delivery, disaster response, and remote exploration, where hand-engineered solutions or single-task learning approaches often fall short. In such contexts, robust generalization, sample efficiency, and rapid adaptation are essential.
This special issue invites high-quality submissions focused on cross-task learning for unmanned vehicle systems. We seek contributions that leverage meta-learning, transfer learning, and multi-task learning to enable robust generalization, rapid adaptation, and reduced retraining in both centralized and decentralized deployments. Approaches that integrate shared representations, hierarchical learning, or knowledge reuse across different vehicle platforms are especially encouraged.
Topics of interest include:
· Cross-task and continual learning for UAVs, UGVs, and USVs
· Transfer learning across domains, sensors, or missions
· Meta-learning for fast adaptation in uncertain environments
· Multi-agent coordination and federated learning
· Visual perception, SLAM, and multi-modal sensor fusion
· Simulation-to-reality transfer and domain generalization
· Efficient learning under sparse data or partial observability
· Real-time adaptation for onboard and resource-constrained systems
We welcome contributions demonstrating practical impact in simulation or real-world scenarios.
Keywords
unmanned vehicles, autonomous systems, meta-learning, transfer learning, multi-task learning, adaptive learning, task generalization, dynamic environments, sample efficiency, sensor fusion, perception and control, real-world deployment, simulation-to-reality transfer, scalability
Login
Register
Submit a Paper
Propose a Special lssue