NRI-Small: The Intelligent Workcell - Enabling Robots and People to Work Together Safely in Manufacturing Environments

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

The research objective of this award is to investigate methods to enable people and industrial robots to work safely within the same workspace. Current robotic manufacturing practice requires the physical separation of people and robots, which ensures safety, but is inefficient in terms of time and resources, and limits the tasks suitable for robotic manufacturing. This research will develop an "Intelligent Workcell," which augments the traditional robotic workcell with perception systems that observe workers within the workspace. Methods to explicitly track workers and estimate their body pose will enable dynamically adaptive safety zones surrounding the robot, thereby preventing the robot from injuring workers. Algorithms will be developed to recognize the activities that workers are performing. These algorithms will learn a task-independent vocabulary of fundamental action components, which will form the building blocks for a hierarchical activity recognition framework. Finally, mechanisms for providing feedback to workers about the robot's intended actions will be studied. This research is expected to provide new capabilities in robotic workcell safety and monitoring, allowing people and industrial robots to work safely and effectively in the same environment. Such capabilities would improve the efficiency of existing robotic workcells, since the robot would not be required to stop whenever a person enters the workspace (as is current practice). Furthermore, new manufacturing processes that involve robots and people working together on a single task would be enabled. Students at the graduate and undergraduate level will benefit from using the prototype Intelligent Workcell in project courses, and grade-school students will participate in short courses and workshops designed to ignite interest in STEM activities related to industrial robotics and computer vision.