Search

Real-world robotic systems have to deal with uncertain and dynamic environments to reliably perform tasks. State-of-the-art cognitive robotic systems use an abstract symbolic representation of the real world that is used for high level reasoning. Some aspects of the world, such as object dynamics, are inherently difficult to capture in an abstract symbolic form, yet they influence whether the executed action will succeed or fail. This paper presents an integrated system that uses a physics-based simulation for predicting robot action results and durations, combined with a Hierarchical Task Network (HTN) planner and semantic execution monitoring. We describe a fully integrated system performing functional imagination, which is essentially contributed by a Semantic Execution Monitor (SEM). Based on information obtained from functional imagination, the robot control decides whether it is necessary to adapt the plan that is currently being executed. As a proof of concept, we demonstrate PR2 able of carrying objects on a tray without the objects toppling. Our approach achieves this by considering the robot and object dynamics in simulation. A validation shows that robot action results in simulation can be transferred to the real world. The system improves on state-of-the-art AI plan-based systems by feeding simulated prediction results back into the execution system., RACE