Project Summary (Abstract)

A system of distributed robotics, incorporating neural network based methods of communication, navigation, input processing, and mapping, is proposed for improved performance and environmental interaction. Each robot contains structures to learn from an “expert system” (ideal algorithm), other robots in the system, and self-feedback. A simulation of the robots ability to achieve a simple goal has been created in C++, where 100 observations of the goal’s completion time were measured over 3 trials. Interestingly, results showed an insignificant difference in accuracy between the robots trained from an “expert system” and other robots, and a faster error reduction for the robot-trained system. The neural network has been implemented in a dense, parallel, design using stochastic bitstream arithmetic on a programmable logic (FPGA) integrated circuit. SMIA cell phone cameras are used for visual input to each robot. FPGA interface code has been created in VHDL for receiving the camera data, which is then processed using the SIFT algorithm to find important feature points. A neural-directed database lookup and creation is used for object recognition, which receives feedback from other robots to ensure a standard method is formed. Local maps are created and shared based on the feedback of multiple robots; navigation takes place by finding a target on the local map and using self-feedback until the target is reached. Inter-robot feedback has been found as a viable possibility for distributed robotics, and may be used in future systems for improved performance in minefield clearing, planetary exploration, military surveillance, and other applications.

VSF 2007 Project Information

Grade Grouping: 12
Team Size: 1
Subject Area: Engineering/Computer Science
Language: English
Project Type: Descriptive Type III (Engineering)

Software Tools

Website:
- Macromedia Flash MX Professional 2004
- UltraEdit 12.10a
- Adobe Photoshop CS2
- Adobe Acrobat 6 Professional
- Microsoft Office 2003
Project:
- DJGPP C Compiler
- Microsoft Visual Studio .NET 2003
- Visual Basic 6.0
- MatLab
- PSPICE Student
- Cadence OrCad Capture for schematic design
- Cadence OrCad Layout for printed circuit board design

Special Skills

Website:
- HyperText Markup Language (HTML)
- JavaScript
- Cascading Style Sheets (CSS)
- Macromedia Flash ActionScript
Project:
- Knowledge of programming languages used
- Circuit Design
- Printed Circuit Board Layout
- Small-scale Soldering
- Circuit Troubleshooting
- Software Debugging
- FPGA Programming
- Algorithm Design and Testing
- Love of Coffee :)

Hardware Tools

Website:
- Dell Inspiron 6400 with Windows XP
- Panasonic DMC-FZ7 6MP Digital Camera
Project:
- Dell Inspiron 6400 with Windows XP
- FPGA programming cables
- 30MHz Oscilloscope
- 100MHz 18 Channel Logic Analyzer
- Multimeters
- Logic Probe
- Power Supplies
- Various Components

Source of Idea

I have been interested in electronics for many years, and recently in artificial intelligence as well. While working on my previous project involving desiging a neural network chip, I realized that existing systems of robots do not make use of neural processing as a large-scale network, where robots can receive feedback from each other. I decided to try to design and create a system where this would be possible, to offer improvements to the field of distributed robotics.

Awards Received

Calgary Youth Science Fair (March 2007)
- Gold Medal
- Nortel Networks Innovation and Technology Award
- APEGGA Engineering Award
- Terry Allen Travel Scholarship to Canada Wide Science Fair 2007
Canada Wide Science Fair (Truro, Nova Scotia, May 2007)
- Place on Team Calgary awarded by Calgary Youth Science Fair (fair has not yet taken place)

Previous Virtual Science Fair Projects

2006: A Dynamic Analog Concurrently-Processed Adaptive Chip

A general purpose analog reconfigurable neural network integrated circuit was designed in this project ²². The current project also applies neural networks, but this has been extended to creating an entire system capable of working together to achieve specific tasks.
2005: VORTECS 3D - VLSI Object Recognition Trainable Embedded CMOS System (some pages are currently unavailable)

A 3-dimensional modeling system was created for use with robotics and other applications ²³. This has laid some of the groundwork for the mapping algorithm designed for the current project.
2004: Development of an Embedded 3D Robot Visual System