Learning Robotic Contact Juggling

Robotic contact juggling is a challenging task in which robots must control the movement of a ball rapidly and indirectly without holding it while keeping the ball in and sometimes out of contact with the robot’s body. In this work, we address the problem of learning such robotic contact juggling from trial and error via model-based reinforcement learning (MBRL). The key insight is that complex robot-ball interactions of the contact juggling actually consist of a small set of simple dynamics that each corresponds to a distinct interaction "primitive" such as touching and releasing the ball. Accordingly, we develop a tailored MBRL method that incrementally fits a set of simple dynamics models to the movements of a robot and a ball while also learning a switching model that can select a proper dynamics model depending on the current state and action. The learned model can then be used in an MBRL framework to seek optimal juggling control. We demonstrated the effectiveness of our approach on a simulator of contact juggling performed by a robotic arm.

Authors

• Kazutoshi Tanaka
• Masashi Hamaya
• Devwrat Joshi
• Felix von Drigalski
• Ryo Yonetani
• Takamitsu Matsubara
• Yoshihisa Ijiri

Keywords

• Switches
• Reinforcement learning
• Manipulators
• Robot learning
• Trajectory
• Task analysis
• Robots
• Learning Models
• Dynamic Model
• Optimal Control
• Robotic Arm
• Switching Model
• Model-based Reinforcement Learning
• Time Step
• Artificial Neural Network
• Prediction Error
• State Space
• Backpropagation
• Butterfly
• Ensemble Model
• Local Solution
• Reward Function
• Markov Decision Process
• Robot Manipulator
• 2D Space
• Ball Position
• Target Trajectory
• Gate Model
• Ball Throw