Objective: Deliver robot agility performance metrics, test methods. information models, and planning approaches that will enable manufacturers to more easily and rapidly reconfigure and re-task robot systems in assembly operations.
Technical Idea: The new technical idea for this project is to develop the measurement science in the form of an integrated agility framework enabling manufacturers to assess and assure the agility performance of their robot systems. This framework will include 1) robot agility performance metrics and test methods, 2) information models, 3) planning approaches, and (4) an integrated agility framework. With this agility framework, the following will be possible:
- Using the test methods and metrics, manufacturers will be able to determine a robotic system’s ability to handle new assembly operations.
- Using the test methods and metrics, manufacturers will be able to quantify a robot’s performance when confronted with unexpected events or failures.
- Using the information models and planning approaches, manufacturers will be able to quickly and easily re-task their robots when new assembly operations are needed. Based on current situations, it often takes an order of magnitude longer to program and configure the robot than the task would take to complete by hand.
- Using the information models and planning approaches, manufacturers will be able to assess the robot’s ability to cope with part and environmental variations. Many subcomponents have component-by-component or lot-by-lot variations. Today’s high-precision robotic systems are not able to adapt automatically to such variations.
- Using the information models, the robots will be able to enumerate and make explicit the necessary knowledge for achieving rapid re-tasking and being agile. Manufacturers will be able to answer critical questions such as: “What does the robot need to know?”, “When does it need to know it?”, and “How will it get that knowledge?”
- The overall framework will tie all of the above components together, providing a cohesive system to allow manufacturers to address their agility challenges.
Research Plan: To accomplish the objective, this project will undertake four tasks:
- Metrics and Test methods: This task will develop use case scenarios to better understand industries’ expected challenges. These use case scenarios will then serve as a basis for formal test methods, including testing procedures, initial and goal states, environmental conditions, and metrics.
- Information Models: This task will develop formalized robot description and environment models of manufacturing assembly operations to capture relevant information about a robot’s capabilities, specifications, and configuration. Requirements for the robot model will be determined, and a thorough robot model literature review will be performed. We will leverage existing robot models, such as the Unified Robot Description Format (URDF), while adding further information, such as robot capabilities, to allow us to assess robot agility. Existing environmental models will also be elaborated to address robot assembly challenges. Formal approaches, such as ontologies, will be used to represent the information in the models, and interfaces will be created to realize them in simulation environments.
- Planning Approaches: This task will develop plan information model and planning protocols to allow for dynamic tasking and re-tasking of robot assembly systems. We will leverage existing planning approaches, such as the Planning Domain Definition Language (PDDL), while extending them to read from a dynamic database of world states to allow for robot agility in a changing environment. The output of task 1 will serve as the requirements for the database and planning information models.
- Integrated Agility Framework: This task will leverage the output of the above three tasks. Starting in year one, a thorough analysis of simulation systems will be performed. An underlying framework will be built on this simulation environment, which will provide interfaces to ties in the output of the other tasks as initial results become available. This task will culminate in an framework that will be applied to a single robot and to multiple robots and/or humans.