Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration
This work addresses the challenge of specifying desired collective behaviors for robot swarms without explicit objective functions, which is incremental as it builds on existing automatic design methods by incorporating inverse reinforcement learning.
The paper tackled the problem of automatically designing control software for robot swarms by using demonstrations instead of mission-specific objective functions, and it successfully generated control software for four missions based solely on demonstrations, with results validated in simulation and with physical robots.
Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, Demo-Cho successfully generated control software to perform four missions. We present results obtained in simulation and with physical robots.