Recent Advances in mmWave-Radar-Based Sensing, Its Applications, and Machine Learning Techniques: A Review

Area of Science:

• Electromagnetics and Sensor Technology
• Machine Learning and Artificial Intelligence
• Data Science and Signal Processing

Background:

• Millimeter wave (mmWave) radar sensors have advanced significantly, offering unique advantages over other sensing technologies.
• Key benefits include reliable operation in various lighting conditions (bright, dazzling, no-light) and superior antenna miniaturization and range resolution.
• The increasing availability of datasets fuels the integration of mmWave radar data into machine learning (ML) for diverse applications.

Purpose of the Study:

• To provide a comprehensive review of mmWave radar-based sensing.
• To detail key performance metrics, diverse applications, and relevant machine learning techniques.
• To serve as a practical reference for developers utilizing mmWave radar and ML.

Main Methods:

• Review of mmWave radar working bands, types, and key specifications.
• Analysis of mmWave radar data interpretation methodologies.
• Exploration of machine learning algorithms applied to mmWave radar data for various tasks.

Main Results:

• mmWave radar technology enables critical applications such as gesture detection, obstacle avoidance, and automotive driving.
• The review categorizes and discusses the vast application domains of mmWave radar sensing.
• Identified and summarized various machine learning techniques suitable for mmWave radar data processing.

Conclusions:

• mmWave radar sensors are versatile and powerful tools with broad applicability across numerous fields.
• The synergy between mmWave radar data and machine learning significantly enhances sensing capabilities.
• This review offers a foundational guide for leveraging mmWave radar technology with machine learning.