Architecture for incorporating Internet-of-Things sensors and actuators into robot task planning in dynamic environments

摘要

Robots are being deployed in a wide range of smart environments that are equipped with sensors and actuators. These devices can provide valuable information beyond the perception range of a robot's on-board sensors, or provide additional actuators that can complement the robot's actuation abilities. Traditional robot task planners do not take these additional sensor and actuators abilities into account. This paper introduces an enhanced robotic planning framework which improves robots' ability to operate in dynamically changing environments. To keep planning time short, the amount of knowledge in the planner's world model is minimized.