Enhancing travel advisory zones for autonomous vehicles using interval-valued pythagorean fuzzy Yager-based...

Area of Science:

• Engineering
• Computer Science
• Artificial Intelligence

Background:

• Autonomous vehicles (AVs) offer significant potential to reduce traffic incidents.
• Effective decision-making (DM) in AVs is crucial for safety and efficiency.
• Existing multi-attribute decision-making (MADM) methods face challenges with uncertainty.

Purpose of the Study:

• To introduce novel Interval-Valued Pythagorean Fuzzy (IVPF) Yager Aggregation Operators (AOs) for AV decision-making.
• To develop a new scoring function for ranking IVPF numbers (IVPFNs).
• To address MADM challenges in AV systems using advanced fuzzy logic techniques.

Main Methods:

• Development of two new Yager AOs: IVPFYWA and IVPFYWG operators.
• Formulation of a novel score function for ranking IVPFNs.
• Exploration of essential properties (idempotency, monotonicity, boundedness) of the proposed operators.
• Design of an algorithm for solving MADM problems within the IVPF framework.

Main Results:

• The proposed IVPF Yager AOs effectively handle ambiguous decision-making problems.
• The novel scoring function enables robust ranking of IVPFNs.
• The developed algorithm successfully solves MADM problems in the AV context.
• Application to selecting optimal AV travel advisory zones demonstrated the method's efficacy.

Conclusions:

• The novel IVPF Yager AOs provide a superior approach to MADM for AVs.
• The proposed methods enhance decision-making robustness and accuracy in autonomous systems.
• Comparative analysis validates the superiority of the developed strategies over existing techniques.