Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Generating Tests for Robotized Painting Using Constraint Programming / 4200
Morten Mossige, Arnaud Gotlieb, Hein Meling

Designing industrial robot systems for welding, painting, and assembly, is challenging because they must perform with high precision, speed, and endurance. ABB Robotics has specialized in building highly reliable and safe robotized paint systems using an integrated process control system. However, current validation practices are mainly limited to manual test scenarios, which makes it difficult to exercise important aspects of a paint robot system, such as the need to coordinate the timing of paint activation with the robot motion control. To address these challenges, we have developed and deployed a cost-effective, automated test generation technique aimed at validating the timing behavior of the process control system. The approach is based on a constraint optimization model written in Prolog. This model has been integrated into an automated continuous integration environment, allowing the model to be solved on demand prior to test execution, which allows us to obtain the most optimal and diverse set of test scenarios for the current system configuration.