Robot Evaluation and Selection with Entropy-Based Combination Weighting and Cloud TODIM Approach.

Area of Science:

• Robotics and Automation
• Decision Science
• Artificial Intelligence

Background:

• Robots are increasingly vital in manufacturing for quality and productivity.
• Selecting the optimal robot is complex due to numerous options and criteria.
• Decision-makers often face diversified assessments and uncertain information.

Purpose of the Study:

• To develop a decision support model for robot evaluation and selection.
• To address the challenges of diversified assessments and hesitant linguistic information.
• To determine a robust ranking of available robots in manufacturing settings.

Main Methods:

• Utilized a cloud model for representing uncertain data.
• Applied the TODIM (interactive and multiple criteria decision making) method for decision analysis.
• Employed an entropy-based combination weighting technique to determine criterion importance.

Main Results:

• The proposed cloud TODIM approach effectively handles hesitant linguistic information.
• Demonstrated a realistic and flexible robot selection process for manufacturers.
• Validated the model's effectiveness through a comparative analysis with an automotive industry example.

Conclusions:

• The cloud TODIM model offers a superior, flexible, and realistic solution for complex robot selection problems.
• This approach enhances decision-making accuracy in uncertain manufacturing environments.
• Provides a valuable tool for optimizing robot adoption in industry.