Undergraduate Research Project on Swarming Intelligence
Abstract
The goal of this project was to develop a swarm of intelligent agents using NXT Mindstorms robots capable of efficiently completing given tasks. This goal was achieved by developing a communication protocol and designing a sonar-based navigation system for multiple agents.
The communication protocol utilizes the Bluetooth API and object-oriented message routing for message delivery to agents via a host PC, which serves as a communication hub, network backbone for processing robot data, and decision-making logic center. The swarm control system on the host PC is multithreaded, making it scalable in terms of task parallelism. Low-level and high-level communication protocols for multiple agents were developed and tested.
The navigation system is based on an ultrasound beacon approach comprising several subsystems:
- An Arduino Mini microcontroller attached to the NXT robot, responsible for receiving pulse data from the beacons and transmitting it serially to the LEGO NXT Brick.
- A transmitter interface managing four ultrasound beacons with piezoelectric transducers and an RF antenna to monitor robot positions.
- A receiver interface attached to the robot that receives and processes RF and ultrasound pulses.
- Algorithms based on mathematical techniques that transform the robot's received positional data within the arena into coordinates in the XY plane.
Through this work, we developed an NXT LEGO Mindstorms platform for studying intelligent swarming behavior.