Interaction learning for dynamic movement primitives used in cooperative robotic tasks

• We present a tightly-coupled robotics systems based on Dynamic Movement Primitives.
• We provide an analytical stability analysis for an equilibration of coupled system.
• We introduce sensory feedback with a predictive learning for the agent interaction.
• We show that such a mechanism allows us to learn an adaptive, sensor-driven interaction.
• We demonstrate that agents learn to cooperate when adding adaptive sensor control.

Since several years dynamic movement primitives (DMPs) are more and more getting into the center of interest for flexible movement control in robotics. In this study we introduce sensory feedback together with a predictive learning mechanism which allows tightly coupled dual-agent systems to learn an adaptive, sensor-driven interaction based on DMPs. The coupled conventional (no-sensors, no learning) DMP-system automatically equilibrates and can still be solved analytically allowing us to derive conditions for stability. When adding adaptive sensor control we can show that both agents learn to cooperate. Simulations as well as real-robot experiments are shown. Interestingly, all these mechanisms are entirely based on low level interactions without any planning or cognitive component.