Recognition Method of Vehicle Cluster Situation Based on Set Pair Logic considering Driver's Cognition

Area of Science:

• Intelligent Transportation Systems
• Automated Driving Technologies
• Set Pair Analysis

Background:

• Accurate recognition of vehicle cluster situations is vital for safe and efficient advanced driving systems.
• Existing methods may not fully account for the complexities of traffic environments and driver cognition.
• The need for objective and precise identification of vehicle groupings in real-time traffic scenarios.

Purpose of the Study:

• To propose a novel vehicle cluster situation model using interval numbers within set pair logic.
• To develop a recognition method for inferring traffic environments and driving conditions.
• To fully consider the uncertainty inherent in driver cognition and traffic information.

Main Methods:

• Development of a vehicle cluster situation model based on interval number set pair logic.
• Design of a recognition method utilizing the connection number of set pair logic.
• Incorporation of vehicle characteristics, grouping relationships, and traffic flow into the model.
• Addressing relative uncertainty and certainty in driver cognition and traffic data.

Main Results:

• The proposed model effectively expresses traffic environment knowledge within a target vehicle's region.
• Verification confirms the recognition method achieves accurate and objective identification of vehicle cluster situations.
• The method successfully infers traffic environments and driving conditions.

Conclusions:

• The developed set pair logic-based model and recognition method provide accurate and objective vehicle cluster situation identification.
• The anthropomorphic approach enhances the understanding of traffic dynamics.
• This research offers a foundation for autonomous vehicle behavior decision-making.