AbstractThis project focuses on realizing a series of operational

improvements for WPI’s unmanned ground vehicle Prometheus with the end goal of a winning entry to the

Intelligent Ground Vehicle Challenge. Improvements include a practical implementation of stereo vision on an NVIDIA GPU, a

more reliable implementation of line detection, a better approach to mapping and path planning, and a modified

system architecture realized by an easier to work with GPIO. The end result of these improvements is Prometheus has improved autonomy, robustness, reliability, and usability.

Background

GoalsDevelop a robot capable of being competitive in the national IGVC competition with the ability to:

• Autonomously navigate to GPS waypoints• Avoid all obstacles• Avoid crossing any painted white lines• Navigate around flags based on their color

Control Architecture

Goals:• Exchange cRIO for Arduino• Move peripherals to computerBenefits:• More robust system• Drastically reduced programming time

Obstacle Detection

Accomplishments Robust modular system Competitive performance

Implementation of new features over last year

Recommendations: Smaller, differential drive platform

Sponsors:

References2010 MQP Report: Design and Realization of an Intelligent Ground Vehicle2011 MQP Report: Realization of Performance Advancements for WPI’s UGV – Prometheus

System Integration and Intelligence Improvementsfor WPI’s UGV - Prometheus

Craig DeMello (RBE), Eric Fitting (RBE/CS), Sam King (RBE), Greg McConnell (RBE), Mike Rodriguez (RBE)

Advisors: Professor Taskin Padir (ECE/RBE) and Professor William Michalson (ECE/RBE)

The world as Prometheus sees it using its SICK Lidar• The green outline represents the robot footprint• The red grid cells represent obstacles• The yellow cells represent virtual inflation, to keep the robot a safe

distance from obstacles.

Figure 4: 2011 Architecture Figure 5: 2012 Architecture

Figure 6: Robot point of view Figure 7: Virtual map

Line Detection

Figure 8: Robot view of line

Figure 9: Line in virtual map

Prometheus has the capability to determine the existence and location of lines it cannot cross by:1. Morphing the image from the camera into a

birds eye view2. Blurring the image3. Filter out the lines using a Hue Saturation

Value filter and pre determined values4. Running a Hue lines algorithm

Path PlanningUsing its sensory information, Prometheus can intelligently plan paths.• The red outline is the robot footprint• The blue line is the path from the current

position to the goal• The red line is the short term path based

on the blue line and tentaclesFigure 10: Robot path planning

Localization Prometheus’s Extended Kalman Filter:• Integrates GPS, Wheel Encoders and

Compass • Reduces error from sensor drift• Provides an accurate estimate of absolute

position and heading

Figure 11: EKF Results

Stereo VisionPromethus can detect obstacles using it’s two cameras and stereo vision

The shade of grey determines the distance to the item in view

Figure 12: Right stereo camera

Figure 13: Left stereo camera Figure 14: Stereo vision disparity map

2010 2011 2012

Mechanical Construction

Tentacles Implemented

Did not qualifyRookie of the

year award

ROS Implemented

Dual cameras and DGPS boom mounted

DGPS and Lidar moved to main computer

Qualified, 13th place in navigation challenge

Use 5% of pre existing code

Stereo visionEKFWheel Encoders

addedMotors and

Compass to main computer

Peripherals to Arduino

Prometheus is an ongoing project at WPI, with the project goal centered around developing a robot capable of being competitive at the international Intelligent Ground Vehicle Competition.

Figure 1: 2010 robot Figure 2: 2011 robot Figure 3: 2012 robot