Objective - Deliver a suite of test methods, protocols, and information models to assess and assure that robots working collaboratively, with and without humans-in-the-loop, will complete their assigned tasks correctly while meeting their assembly performance objectives.
What is the new technical idea? Today, collaborations between man and machine are stopgap measures to cut costs in automation without providing actual benefit to the manufacturing process, while collaborations between robots are specialized, brute-forced, and single-point-of-control solutions for specific production tasks. For both human-robot and robot-robot teams, the performance of collaborative robot systems are measured against production goals (throughput, quality, etc.), which do not assess how well these robots work together, whether they can collectively perform as expected, or how effective they are at meeting their respective production performance objectives. This project will provide the methods, protocols, and metrics necessary to evaluate the collaborative capabilities of robot systems, and will use a task-driven decomposition of manufacturing processes to assess and assure the effectiveness of a collaborative team toward the manufacturing performance objectives. This collection of methods, protocols, and metrics will enable end-users to maximize the effectiveness and efficiency of integrating collaborative robots into their production processes. NIST is best positioned to provide these tools given our expertise in collaborative robot evaluation methodologies and performance metrics for a broad spectrum of robotics technologies, and our cutting edge collaborative robot technology testbeds.
What is the research plan? This research plan comprises four principal foci of research: evaluating the coordinated performance of robot systems, decomposing collaborative tasks to model human and robot role representations and assignments, developing protocols for robot-robot and human-robot collaboration communications, and validating the situational awareness of collaborative robot systems. Each of these foci builds upon the capabilities defined or developed in its predecessor. Collectively, they will comprise a total suite of test methods, metrics, and protocols to assess the collaborative performance of robot systems. For each phase of development, the test methods, metrics, and protocols will be evaluated using the NIST collaborative robotics testbed.
- In the first year (FY14), we will deliver test methods and metrics for evaluating the coordinated performance of independent robot systems. These test methods and metrics will be developed through a focused engineering process, including a literature review and platform specific research and development.
- In the second year (FY15), we will deliver hierarchical models of collaborative assembly task decompositions consisting of human and robot role representations and assignments. The process of the hierarchical model building will be based on our current methodology for task decompositions and representations.
- In the third year (FY16), we will deliver protocols for robot-robot and human-robot collaboration communications of high-level, task-relevant information. These protocols will be developed based on an assessment of the needs, hardware and software mechanisms, and capabilities of robots and humans to formulate and exchange information with one another.
- In the fourth year (FY17), we will deliver test methods to validate a robot's situational awareness of a collaborative assembly task. To accomplish this, we will construct numerical models that register the dissimilar situational awareness representations, identify the similarities and differences between them, and then compare both with a ground truth to compensate for errors or gaps.
- In the fifth year (FY18), we will deliver test methods that measure the conformance of collaborative robots to protocols, information models, and performance expectations for assembly tasks. The results of the previous four years' research efforts will be merged to form a suite of tools that will collectively assess the collaborative performance of robot systems.