Skip to Main Content
In this paper we describe a new randomized path-planning approach presenting two novel features that are useful in various complex real-world applications. First, it handles zones in the robot workspace with different degrees of desirability. Given the random quality of paths that are calculated by traditional randomized approaches, this provides a mean to specify a sampling strategy that controls the search process to generate better paths by simply annotating regions in the free workspace with degrees of desirability. Second, our approach can efficiently re-compute paths in dynamic environments where obstacles and zones can change shape or move concurrently with the robot. The new path planner is implemented within an automated planning application for generating 3D tasks demonstrations involving a teleoperated robot arm on the International Space Station (ISS). A typical task demonstration involves moving the robot arm from one configuration to another. Our objective is to automatically plan the position of cameras to film the arm in a manner that conveys the best awareness of the robot trajectory to the user. For a given task, the robot trajectory is generated using the new path planner. The latter not only computes collision free paths but also takes into account the limited direct view of the ISS, the lighting conditions and other safety constraints about operating the robot. A suitable camera planning system is then used to find the best sequence of camera shots following the robot on its path.