Towards Human-Like Learning Dynamics in a Simulated Humanoid Robot for Improved Human-Machine Teaming

Akshay, Xulin Chen, Borui He, Garrett E. Katz

Abstract: A potential barrier to an effective human-machine team is the mismatch between the learning dynamics of each teammate. Humans often master new cognitive-motor tasks quickly, but not instantaneously. In contrast, artificial systems often solve new tasks instantaneously (e.g., knowledge-based planning agents) or learn much more slowly than humans (e.g., reinforcement learning agents). In this work, we present our ongoing work on a robotic control architecture that blends planning and memory to produce more human-like learning dynamics. We empirically assess current implementations of four main components in this architecture: object manipulation, full-body motor control, robot vision, and imitation learning. Assessment is conducted using a simulated humanoid robot performing a maintenance task in a virtual tabletop setting. Finally, we discuss the prospects for using this learning architecture with human teammates in virtual and ultimately physical environments.