Trigger-action programming for personalising humanoid robot behaviour

In the coming years humanoid robots will be increasingly used in a variety of contexts, thereby presenting many opportunities to exploit their capabilities in terms of what they can sense and do. One main challenge is to design technologies that enable those who are not programming experts to personalize robot behaviour. We propose an end-user development solution based on trigger-action personalization rules. We describe how it supports editing such rules and its underlying software architecture, and report on a user test that involved end user developers. The test results show that users were able to perform the robot personalization tasks with limited effort, and found the trigger-action environment usable and suitable for the proposed tasks. Overall, we show the potential for using trigger-action programming to make robot behaviour personalization possible even to people who are not professional software developers.