It is envisioned that the future wireless communication is more data driven. Given that new frequency bands with large bandwidth aided by mobile edge cloud, beamforming and Artificial Intelligence techniques result in a number of opportunities for joint sensing and localization. Fixed and mobile short-range ad hoc, point to point communications can be created for motor vehicles, drones, robotics, health monitoring, etc. Such new applications can be created by combining sensing and localization via complex high-dimensional data gathered by observations.

In wireless networks, there is a challenge in terms of high-accuracy centimetre-level user localization. Previously, machine learning methods for localization mainly focused on some form of supervised learning strategy using regression and classification of data. Machine learning techniques are not suitable when the data acquired is noisy, multi-modal with nonlinear characteristics. Artificial intelligence techniques have seen a massive rise in popularity due to the capability of end-to-end learning, prediction, and decision making. Artificial intelligence methods can simultaneously model complex radio signal characteristics and fuse many sensor inputs. However, the challenge is mainly the lack of labelled data.

The aim of this Special Issue is to bring together original research and review articles discussing artificial intelligence techniques for joint sensing and localization in future wireless networks. Experts and researchers in both industry and academia are invited to submit their innovative ideas and practices through original research articles. The aim is to present a comprehensive collection on the challenges and research directions to facilitate combined sensing and localization towards more reliable six-generation (6G) mobile wireless networks.

Potential topics include but are not limited to the following:

• Consistent propagation models
• Passive and active sensing methods
• Sources and detectors for localization
• Waveform designs and channel estimation
• Chip technologies increased output power and efficiency
• Energy-efficient techniques for accurate sensing and localization
• Online learning and adaptive models
• Optimization algorithms
• Computing resource optimization
• Intelligent reflective surfaces for enhanced mapping and localization
• Beam space processing for increased accuracy
• Cognitive-radio techniques
• Security and privacy algorithms for sensing and localization
• Sensing models for arrival and departure angle estimation
• Metrics for localization