World Modeling and Performance Evaluation for AGV Navigation in Unstructured Environments
R. Madhavan and R. Lakaemper
This project is supported by a Temple University Grant (via an ARRA NIST Measurement Science and Engineering Research Grants Program Award# 10D012)
Automated guided vehicles, quantitative performance evaluation, performance metrics, objective testing and evaluations
Automated Guided Vehicles (AGVs) represent an integral component of today’s manufacturing processes. They are widely used on factory floors for intra-factory transport of goods between conveyors/assembly sections, parts/frame movements, and truck-trailer loading/unloading. To offset prohibitively expensive maintenance and installation costs, and thus expand the AGV’s markets and utility beyond what is possible today, it is evident that the dependency on infrastructure is to be minimized (if not eliminated). Adaptability to human-centered collaboration (flexible), the ability to cope with unstructured, dynamic environments (smart), and keeping humans out of harm’s way (safe), are critical enablers for widespread use of AGVs in manufacturing. Developing such smart, flexible, and safe automation has implications not only for the manufacturing industry but also has the potential to tackle many open-ended problems in mobile robotics today.
It is important that end-users’ requirements should drive developers and integrators such that a resulting ‘autonomous’ system is useful and affordable. Only by involving all of the three parties, viz. users, developers and integrators in a coupled fashion, can meaningful solutions be produced which can stand the ever-varying requirements imposed by: 1) tasks that are either application or environment dependent, 2) hardware and software advancements/restrictions that affect the development cycle, and 3) budgetary constraints that interrupt and hamper sustained progress. These factors hold true for manufacturing robotic and automation systems where characterization of components at the system and sub-system levels are needed to develop and deploy fully functional systems that can work around the clock with as much downtime as possible. To guarantee such requirements and to ensure reliability and robustness, repeatable and reproducible test methods are needed to experimentally verify and validate technical methodologies.
The objectives of this project are:
• Experimental verification and validation of world modeling schemes in unstructured environments contributing to the science of performance evaluation and benchmarking, via characterization of components at the system and sub-system levels of autonomous navigation of mobile robots in manufacturing domains.
• Development of repeatable and reproducible reference test methods and measurement methodologies to design scientific experiments that will provide statistically significant results through field exercises.
• Bringing together end-users, developers, and vendors to gather requirements, discuss and devise an action plan to overcome existing barriers by providing reference data sets to work collaboratively in developing shared-solutions across different application areas.
• Raising awareness among and encourage participation of the general public and students via competitions, seminars, and a web-portal.
For additional information please contact:
Dr. Raj Madhavan
Institute for Systems Research
University of Maryland College Park, MD 20742
Intelligent Systems Division
National Institute of Standards and Technology, Gaithersburg, MD 20899-8230