Cognitive Toy Factory with Two Teams of Heterogeneous Robots

Posted on September 16th, 2013

We consider a toy factory with two teams of robots, where each team is located in a separate workspace collectively working toward completion of an assigned task. In particular, Team 1 manufactures nutcracker toy soldiers through the sequential stages of cutting, carving and assembling, while Team 2 processes them by going through stages of painting in black, painting in color, and stamping. Each workspace is depicted as a grid, contains an assembly line along the north wall to move the toys and a pit stop area where the worker robots can change their end-effectors. Each workspace also includes some static obstacles.

The teams are heterogenous, as each team is composed of three types of robots with different capabilities. Worker robots operate on toys, they can configure themselves for different stages of processes, and they can be exchanged between teams; charger robots maintain the batteries of workers and monitor team’s plan, and cannot be exchanged between teams. Worker robots are further categorized into two based on their liquid resistance. In particular, wet (liquid resistant) robots can perform every stage of the processes involved in manufacturing and painting of the toys, while dry (non-liquid resistant) robots cannot be employed in painting and cutting stages, since there processes involve liquids. All robots are holonomic and can move from any grid to another following straight paths.

We have tested this cognitive toy factory scenario with dynamic simulations and with a physical implementation.

This video utilizes KuKa youBots and Lego NXT robots for physical implementation of a cognitive toy factory.

This video utilizes KuKa youBots for dynamic simulation of a cognitive painting factory.

Several different local optimizations are performed in these dynamic simulations of the cognitive painting factory scenario.

Comments are closed.