Topic: AI-Driven Autonomous Localization: Multimodal Perception, Learning, and Spatial Intelligence

Accurate, reliable, and adaptive localization is fundamental to perception, navigation, and decision-making in autonomous systems, with applications in mobile robots, unmanned vehicles, industrial platforms, and intelligent infrastructure. Advances in artificial intelligence, deep learning, and multimodal sensing are driving localization toward intelligent paradigms that integrate learning, sensor fusion, physical knowledge, and geometric reasoning for complex environments.

This Special Issue aims to showcase recent advances in AI-driven localization and autonomous positioning, focusing on multimodal perception, spatial intelligence, learning-based methods, SLAM, sensor fusion, physics-informed and geometric learning, uncertainty-aware estimation, and cooperative localization. Contributions addressing indoor, underground, GNSS-denied, dynamic, degraded, and industrial environments are particularly welcome.

The Special Issue seeks to connect multimodal perception, spatial representation, localization, mapping, and autonomous navigation, providing a platform for emerging methodologies, benchmarks, and real-world applications in intelligent autonomous systems.

Topics of interest include, but are not limited to:

AI-Driven Localization, Mapping, and Navigation

  ● Learning-based localization and state estimation;

  ● Deep learning and self-supervised localization;

  ● AI-driven SLAM and semantic localization;

  ● Geometric deep learning and differentiable localization;

  ● Physics-informed and hybrid localization;

  ● Learning-driven navigation and localization.

Multimodal Perception and Spatial Intelligence

  ● Visual, LiDAR, inertial, magnetic, UWB, and wireless localization;

  ● Multisensor fusion and multimodal localization;

  ● Semantic perception and spatial representation;

  ● Spatial understanding and semantic localization;

  ● Cooperative localization and distributed perception;

  ● Infrastructure-assisted positioning.

Robust and Adaptive Localization in Complex Environments

  ● Localization in dynamic and changing environments;

  ● GNSS-constrained, denied, and degraded environments;

  ● Sensor failures, interference, and occlusion;

  ● Long-term and persistent localization;

  ● Domain adaptation and cross-environment generalization;

  ● Localization in indoor, underground, and confined spaces.

Localization Applications in Intelligent Autonomous Systems

  ● Mobile and service robots;

  ● Industrial and warehouse robots;

  ● Autonomous vehicles and UAVs;

  ● Multi-robot systems;

  ● Intelligent infrastructure and digital twins;

  ● Localization-driven autonomous navigation and decision-making.

Reliable Localization and Real-World Deployment

  ● Localization robustness and generalization;

  ● Uncertainty quantification and propagation;

  ● Safe localization and fault detection;

  ● Localization verification and safety assurance;

  ● Benchmark datasets and evaluation platforms;

  ● Real-world testing and system deployment.