Enhancing autonomous vehicle navigation using SVM-based multi-target detection with photonic radar in complex traffic...

Area of Science:

• Engineering
• Computer Science
• Physics

Background:

• Efficient transportation is vital for smart city development.
• Autonomous vehicles and Intelligent Transportation Systems (ITS) are key to safe, sustainable urban mobility.
• Advanced sensing is needed for reliable multi-target detection in complex traffic.

Purpose of the Study:

• To develop an innovative photonic radar system for enhanced multi-target detection in autonomous vehicles.
• To improve obstacle detection and classification accuracy in challenging traffic and weather conditions.
• To contribute a sophisticated solution for Intelligent Transportation Systems (ITS).

Main Methods:

• Utilized Frequency-Modulated Continuous-Wave (FMCW) photonic radar with spatial multiplexing.
• Integrated Support Vector Machine (SVM) classification for target identification.
• Conducted comprehensive numerical simulations to evaluate system performance.

Main Results:

• Achieved a range resolution of 7 cm, even in adverse weather, with a 4 GHz bandwidth.
• Demonstrated accurate detection of targets at various distances and movement states.
• Reported classification accuracies of 75% for stationary and 33% for moving targets.

Conclusions:

• The proposed photonic radar system offers a viable solution for obstacle detection and classification in autonomous vehicles.
• The system's performance in simulations suggests significant improvements in ITS safety and efficiency.
• Low power requirements and compact design make the radar suitable for practical deployment in urban environments.