Real-time human-robot interaction and service provision using hybrid intelligent computing framework.

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Existing query-processing systems for robots suffer from high computational costs, inefficient service matching, and high failure rates in dynamic environments.
• Effective human-robot interaction is crucial across various sectors like healthcare, customer service, and industrial automation.

Purpose of the Study:

• To develop a Hybrid Intelligent Computing Model (HICM) for autonomous robot inquiry processing.
• To enhance robots' real-time response capabilities with efficient, personalized, and context-specific solutions.

Main Methods:

• The HICM integrates a decision-support system utilizing self-organized computing approaches.
• It combines annealing and Tabu Search techniques to evaluate query characteristics and service relevance.
• Tabu Search is employed to treat query resolution as a non-convergent optimization problem, preventing incompatible query responses.

Main Results:

• HICM demonstrated significant improvements over existing models (CDS, DGTA, CCS) in performance metrics.
• Reduced calculation time by 8.67%, service time by 15.09%, and failure rates by 7.87%.
• Achieved an 11.8% higher success factor, a 14.88% higher matching ratio, and a 6.22% lower failure rate.

Conclusions:

• The HICM model significantly enhances robotic query processing efficiency and reliability.
• It enables robots to provide timely, accurate, and context-specific services in real-time human-robot interactions.