Trajectory Optimization for Coordinated Human-Robot Collaboration

Effective human-robot collaboration requires informed anticipation. The robot must simultaneously anticipate and react to the human's actions. Even more, the robot must plan its own actions in a way that accounts for the human predictions, while expecting the human's behavior will change based on what the robot does. The back-and-forth game of prediction and planning is extremely difficult to model using standard techniques.

In this work, we exploit the duality between behavior prediction and control to design a novel Model Predictive Control algorithm that simultaneously plans the robot's motion and predicts the human's behavior. We also develop a novel technique for bridging finite-horizon motion optimizers to the problem of spatially consistent continuous optimization.