Umeå universitets logga

The term understandable robots refers to robots making their actions and intentions understandable (or explainable) to humans. To support understandability of a team of collaborating robots we use nat- ural language to let the robots verbalize what they do and plan to do. Our solution is based on Cooperating Distributed Grammar Systems for plan derivation and a Multi-agent algorithm for coordination of robot actions. We implemented and evaluated our solution on a team of three Pepper robots that work collaboratively to move an object on a table, thereby coordinating their capabilities and actions and verbalizing their actions and intentions. In a series of experiments, our solution not only success- ful demonstrated collaboration and task fulfilment, but also consider- able variation, both regarding actions and generated natural language utterances.