Planning for Sustainable and Reliable Robotic Part Handling in Manufacturing Automation. Rovida, F., Krueger, V., Toscano, C., Veiga, G., Crosby, M., & Petrick, R. In
abstract   bibtex   
Robots have been used effectively in factories for many years, however, it is only recently that they have begun to take on roles requiring large amounts of autonomy and high-level reasoning capabilities. Autonomy is becoming increasingly necessary due to greater variability in factory-generated products (e.g., end-user customisation) leading to assembly lines that must involve more than just simple repetitions of the same task with the same components. For example, in car manufacturing—the application domain for this work—each car is built to the specification of the user, meaning that the parts required for assembly may be different for each car on the line. Not only does this require more complex assembly line robots, but robots are starting to be used in preparing the parts for delivery to the assembly line. This system demonstration illustrates work that is being performed as part of the STAMINA1 project to address this latter task: using autonomous mobile robots with the ability to pick parts from around the factory to be delivered to the assembly line at the appropriate time (see Figure 1), a process called kitting. In particular, we focus on the high-level reasoning components in our framework consisting of a logistic planner, which acts as the central information provider in the system; a mission planner, which is tasked with creating and assigning initial high-level plans and goals to the robots in the fleet; and a task planner, which is responsible for managing planning activities for individual robots. Additionally, the robot fleet uses a skills framework which modularises robot capabilities into high-level, symbolic planning actions, meaning that the robots are pre-calibrated to use planning-like constructs. Plans are produced in a format that maps planned actions to skills to facilitate execution. This setup allows the technology to be quickly adapted to new situations when robot capabilities or the environment change, as happens when the factory floor is rearranged, new parts become available, or new robots are added to the fleet.
@InProceedings{icaps16-demo-8,
  author =   {Francesco Rovida and Volker Krueger and César Toscano and Germano Veiga and Matthew Crosby and Ron Petrick},
  title =    {Planning for Sustainable and Reliable Robotic Part Handling in Manufacturing Automation},
  abstract = {Robots have been used effectively in factories for many years, however, it is only recently that they have begun to take on roles requiring large amounts of autonomy and high-level reasoning capabilities. Autonomy is becoming increasingly necessary due to greater variability in factory-generated products (e.g., end-user customisation) leading to assembly lines that must involve more than just simple repetitions of the same task with the same components. For example, in car manufacturing—the application domain for this work—each car is built to the specification of the user, meaning that the parts required for assembly may be different for each car on the line. Not only does this require more complex assembly line robots, but robots are starting to be used in preparing the parts for delivery to the assembly line.
  
This system demonstration illustrates work that is being performed as part of the STAMINA1 project to address this latter task: using autonomous mobile robots with the ability to pick parts from around the factory to be delivered to the assembly line at the appropriate time (see Figure 1), a process called kitting. In particular, we focus on the high-level reasoning components in our framework consisting of a logistic planner, which acts as the central information provider in the system; a mission planner, which is tasked with creating and assigning initial high-level plans and goals to the robots in the fleet; and a task planner, which is responsible for managing planning activities for individual robots. Additionally, the robot fleet uses a skills framework which modularises robot capabilities into high-level, symbolic planning actions, meaning that the robots are pre-calibrated to use planning-like constructs. Plans are produced in a format that maps planned actions to skills to facilitate execution. This setup allows the technology to be quickly adapted to new situations when robot capabilities or the environment change, as happens when the factory floor is rearranged, new parts become available, or new robots are added to the fleet.}
}

Downloads: 0