Intro to Robotics Projects - Part 1

At the end of ES450 Intro to Robotics, students are tasked with coming up with a task to automate that integrates computer vision and a robot manipulator.

Here the camera sees and object and determined its color, then the robot used the computer keyboard to send a text message, with the object's color, to a mobile phone using Matlab (Ruttum & Baker)

Here the Scorbot plays TicTacToe Against a human. It uses the camera to detect the state of the board, computes the best move, and moves the blocks (it is hard to write with a pen using the robot). It is always able to at least draw against a human player. (Valdez)

A GUI to control the scorbot. Robot scolds you if you click outside workspace. (Hatch & Landholt)

Goin' Ballistic

November marked another semester's ES300 ballistics lab, but this semester there was a twist. Instead of the typical lecture and demo period in the Bancroft Hall Rifle Range, ES300 students got to fire a potato gun. For those not familiar, a potato gun is made from readily available PVC pipe, and is fired using any number of household aerosols, including hairspray and deodorant to propel the common Idaho spud to distances exceeding 200 yards. Gun construction is very simple and involves a hacksaw and PVC cement. The real trick is getting the correct fuel-air mixture, and igniting it with sufficient spark to get good combustion. This year's lab succeeded on all counts, launching potatoes from 1st class parking, all the way across Hospital Point into the Severn.
After the potato gun lab, students were brought down to the range and given a demo on interior, exterior and terminal ballistics. The indoor range cannot handle the energy from a rifle round, so only handguns were tested, including .22, 9mm, .40 and .45 pistols. Impact media included ballistics gel (just like in Mythbusters), Kevlar armor, and some proprietary molded armor from a company called MACRO Industries. The intent was to show how combat ammunition performs on various targets and in different scenarios. Students gained an appreciation for the marksmanship skills necessary to effectively dissuade the enemy from pursuing a negative course of action.

3rd Annual Worm Chariot Race

For the third consecutive year, students in Es451 make robotic worms using the Bioloid Robotics Kit. Engineering issues considered include gait design, stability, traction, sensing and responding to obstacles. The Chariots contain the batteries and small computers which store the programs.

The first test is the 10 foot dash. It is graded based on how straight the robot moves (<6" deviation from straight line over a 10 ft course) .

Turning is one of biggest challenges. I have to say this is the ugliest robot snake turn I have seen but it is remarkably close to 90 degrees (the goal). And reliable too! The turn is triggered by the presence of an obstacle as measures by an IR range sensor.

And they are off! (they really shouldn't be touching the robots once the race starts but it didn't effect the outcome)

Congratulations:

Winners (1st period): Midn 1/C Hatch, Meyer, Myers

Winners (3rd period): Midn 1/C Felps, Honan, Beates

Essay Contest Winner!

Congratulations to ENS Daniel Umpa (USNA, Systems, '09)!

He was announced as the winner of the "Commander William Earl Fannin, Class of 1945, Capstone Essay Contest". His essay, "The Pilotless Squadron" which discusses the obstacles for adoption of unmanned systems (AUVs in particular) in the US military, appeared in the September issue of the Proceedings of the US Naval Institute.

Note: You have to be a Proceedings Subscriber to see the full article (sorry!)

http://www.usni.org/magazines/proceedings/archive/month.asp?ID=277

Projects Galore!

The Robo-Goat (He's gnarly and he's old and he's never been to school)

In Jan 2009, a team of 6 midshipman set out to design and build Robo-Goat, USNA's first entry into the Intelligent Ground Vehicle Competition, in Rochester Michigan. Mids Lacy, and Calvanico traveled to compete, along with then 2/C Bush and Advisers Profs. Joel Esposito and Brad Bishop.

The team won the Rookie of the Year Award! Placing solidly in the middle of the pack out of the 30 teams that qualified. About 20 teams did not pass the qualifying round.

As part of ES402 Systems Engineering Design, the mids undertook a systematic component selection process. The vehicles uses a camera to detect lane markings in the grass and a scanning laser range finder (aka LADAR) to avoid obstacles. You can see the lane following in action in this video:

Here the obstacle avoidance algorithm is tested:


The final event (and our best) was the GPS challenge, in which the vehicle had to hit as many way points as possible within 7 minutes.



We've already statred improving the old goat. We can't wait for the 2010 competition!

AUV 2009

The Systems Engineering Department sent three May graduates and one second-class midshipman to represent USNA at the 12th Annual Association for Unmanned Vehicle Systems International (AUVSI) International Autonomous Underwater Vehicle (AUV) competition this August.

During the 2008-2009 academic year a team of eight midshipmen designed and built an AUV as their capstone design project. After two semesters of design, fabrication, and programming; four of the team members flew out to the SPAWAR Systems Center Pacific's TRANSDEC Facility in San Diego for the week long competition. Contending with numerous technical issues, the team worked as many as 18 hours per day troubleshooting electrical problems, testing controllers and applying theory learned as Systems Engineers. Despite the long hours, the team remained optimistic, motivated, and focused.

“I was entirely amazed as to how many people were cheering for our team. Even though teams from San Diego were entered into the competition, USNA was viewed as more of the hometown team. It was very rewarding to hear that high ranking officials and officers held our team in high regard. Looking at other teams, I realized how rare an opportunity USNA’s Systems Department presented me with by entrusting me to work with high value sensors and equipment. This was definitely a unique project and a unique experience,” said team member ENS Dan Umpa.

The team achieved 4th place out of 30 teams in the static competition. (Oh yeah

.

..there is also the lasting benefit of the problem solving and time management skills learned th

roughout the ten months of development will serve the team members well as they enter serve in the world’s most technically advanced Navy)

BE$T JOB IN AMERICA? Systems Engingeering!

Every year Money Maganize names the 50 best jobs in America based on a variety of factors such as pay, lifestyle and demand. Guesss what this years' #1 job was?

Yep. It was Systems Engineering.

Check out the Article. They cite high demand, high pay, and the opportunity to manage creative solutions to high level problems.

Systems Engineer Stats
Median salary
(experienced) $87,100
Top pay $130,000
10-year job growth (2006-2016) 45%
Total jobs (current) 88,000
Online want ad growth (April 2009-August 2009) 22%
Personal satisfaction A
Job security B
Future growth B
Benefit to society C
Low stress C

Towers of Hanoi

Legend has it that somewhere in Hanoi, there is a temple in which a group of Buddhist monks have 64 rings on a set of pegs. They need to move the rings from one peg to another, but you can only move one ring at time and are not allowed to place a larger on on top of a smaller one. When they complete the task...the world will end!

Sounds boring though huh? That is where the robots come in! Robots are suited to dirty dull and dangerous tasks that humans would rather not do. Here is our Intro to Robotics lab. (oh, by the way, if you do the math, turns out if they move one ring per second, the world won't actually end for another few billion years so don't worry)


ps - What is up with the arcing?

Robot Road Report

( by Prof. Esposito)
I am currently at the Intelligent Robots ad Systems Conference in St. Louis. Here are some observations:

1. Everybody seems to be trying to buy a Vicon, motion tracking system. In case you don't know, this is a system that uses high speed IR cameras to track moving objects to within 1 mm accuracy and can compute position and orientation up to 1000 times/sec. Its like a really fast, really accurate indoor GPS systems. It is also used alot in the biomedical, video game and movie industries. Within 3 hours of arriving here at IROS, I met 3 colleagues from other institutions who were in the process of planing orders. Seems like we're practically trend setters. Prof. Bishop and I got the idea to buy one, way back in early 2008.

2. Hokuyo came out with a new scanning laser range finder that retains the slim form factor of the URG (about 2" X 2" X 2"). However this one gets both power and data through the USB connection, eliminating the need for a separate power supply. Oh yeah, it is half the price too! (1200 USD vs 2500)

3. I got the chance to meet Nao, the new small humanoid robot from Alderbaran Robotics. It is quite cool, and at 10,000 USD / unit it is no toy. So far their primary market is the RoboCup Universities that are participating in the humanoid league.

http://www.aldebaran-robotics.com/eng/Nao.php

Micro Bots

Check out these micro robots that Midn Eastman and Watson worked on with Prof. Piepmeier and Firebaugh (EE). The ultimate goal of the project is to have the robots play soccer in the Robocup Nanogram League. Here is a video of the through a microscope.

They are approximately 60 X 120 microns in size. The desig is refered to as a scratchdrive abd was build here at USNA. By varying the voltage on the playing surface the robots move along like an inchworm.

Welcome back LT Searock!

LT Jeremy Searock is a 2003 graduate of our very own Systems Engineering department. As a first class midshipman, LT Searock worked along with Professor Brad Bishop and John Vranish, an engineer at NASA’s Goddard Space Flight Center, on a next generation planetary rover. The project was designed to improve the obstacle clearance capabilities of a rover comparable to the NASA Sojourner, which landed on Mars in July of 1997. The project used a unique mobility concept entitled the “mountain climbing team method.” This method enabled a similar rover of comparable size to the Sojourner to traverse an obstacle 75% taller, while also increasing its ground speed. LT Searock’s first class design project won the 2003 David R. Marsh Design Project Award.

Upon graduation from the United States Naval Academy, LT Searock entered the Robotics Masters program at the Robotics Institute at Carnegie Mellon University. LT Searock worked along with Manuela Veloso and Brett Browning in developing the capabilities of a Segway Robot Mobility Platform to play a modified game of soccer along with humans. The project was funded under DARPA’s mobile autonomous robot software program (MARS). LT Searock designed and built two 250+lb robots capable of playing soccer along with humans riding the Segway Human Transport. ("Turning Segways into Soccer Robots". In Proceedings of IROS 2004). His master’s thesis involved creating a method to prevent robots from entering unrecoverable states and thus improving their overall robustness. ( "Learning to prevent failure states for a dynamically balancing robot", Proceedings of AAAI 2005.)

Upon completion of the naval nuclear power training pipeline, LT Searock reported to USS Nevada SSBN-733 in Bangor, WA in October 2006. He served as the Reactor Controls Assistant, Main Propulsion Assistant, Quality Assurance Officer, and Assistant Engineer. He completed several patrols and an Engineered Refueling Overhaul.

In March of 2009, LT Searock reported to USNA once more to become one of our military instructors. He is located in Maury 244.

System Ball: Remember when?

With System Ball less than a week away I thought it would be fun to look back. Here is a 1996 article from the capital on this. (Sorry for the poor reproduction quality but hey, it was 1996!)

_____________________
This year's systems ball competition will take place Wednesday April 22nd, at 1530 in Rickover 102. Professor Knowles will give his farewell lecture, then the four robots will abttle until the end. Immediately following will be the 1/C BBQ.

Hope to see everyone there!

System Ball April 22nd, at 1530

This year's Systems Ball competition (a battle bots type event) will take place Wednesday April 22nd, at 1530 in Rickover 102. Professor Knowles will give his farewell lecture, then the four robots will abttle until the end. Immediately following will be the 1/C BBQ.

Everyone is invited. Hope to see everyone there!

Sail Bot

Imagine trying to teach a robot to sail. That is exactly what this group of students had to do when they entered the first international autonomous sailboat competition, hosted here on the Chesapeake Bay. They retro-fitted a standard, small, sailboat with digital sensors such as GPS, a compass and wind speed indicators. All that information was fed into an on-board computer which controlled various motors to adjust the rudder and sails.

Our team, which consisted of systems majors and naval architects, placed second in this international competition!

Roombas

Most of us have seen the iRobot Roomba vacum cleaner robot. Professor Esposito wrote a Matlab Toolbox for the Roomba that allows you to control a Roomba from your PC.

The ES451 Mobile Robotics class used this along with a pretty sophisticated scanning laser rangefinders to program the robots to track along within 2 feet of the wall (the tape lines on the ground are just for reference the robot cannot see them) and when it finds an open door it is able to drive through it.


Mids Warren Leonne

These are the same sensors that have been used succesffully in the DARPA Urban Challenge

Alumni

Even wonder what some of our Alumni do when they enter the civilian engineering world?

Dear Dr. Knowles,

My name is Matt Wallace. I am a 1984 USNA grad, and you were my advisor and professor a long long (long) time ago.

I was a systems major, and was at the time interested in robotics. Of course, I had little opportunity to exercise that interest while driving fast attack subs around various oceans - though that was mighty cool too. However, when I left the Navy, you were kind enough to write me a recommendation for graduate school in 1990 - despite the fact that I was far from your best student. I ended up at Caltech for a masters program, which I somehow survived (way harder than plebe summer), and was then hired at NASA's Jet Propulsion Laboratory, which is run by Caltech.

I believe it's been 20 years since you have heard from me. And no, I don't need a recommendation for a PhD program. In fact, I really only wanted to send this to let you know that your support made a difference for me. I have been working in planetary robotics now for most of those 20 years.

Over the last 15 years or so, I've been focused on the Mars Program run here at JPL. I played a part in the 1997 Mars Pathfinder mission (I lead the power system development on the small Sojourner rover among other things). I was also the assembly test and launch operations (ATLO) manager for the 2004 Spirit and Opportunity rovers, as well as the Opportunity mission manager for the Mars surface phase. And I am now the spacecraft manager for the 2009
Mars Science Laboratory (MSL) mission. MSL is a beast - 4000 kg all together with a 900 kg car-sized Rover stuffed with 10 different science payloads.

As you might expect, there is not a lot of exotic cutting-edge technology on these vehicles since we focus on high-reliability, mature approaches were possible. You're students today would probably scoff at our Power PC computers and 1553 bus. But the systems engineering and integrated design requirements push the boundaries of the industry. And of course, the application-level is fairly unique (not a lot of folks trying to land on Mars).

I still draw on the advice you gave me 25 years ago - I learned a lot about how to solve problems from you I believe. And I would not have had this career opportunity at JPL without the sequence set in motion by your recommendation.

Matt Wallace, Systems Engineering, Class of 1984, now at JPL

Trackin'

Tracking moving objects is an important objective for many autonomous systems. Computer vision is one way to do that.

Anthony Guinipero
Using cues about color and shape helps you find the object in the image. But when the object moves fast or there is shadows or glare the results can be disapointing. Enter the Kalman Filter...

Lisa Knauft

It helps blend noisy measurements with a predicative model of motion resulting in the "smooth like butter" trackers seen in these videos.

Stephen Allen

Attack of the bioloids!

Last year we started experimenting with he Bioloids Kit. Its a very powerful set of motors and a small computer that enables us to do some pretty neat things in ES451Mobile Robotics.

We had a good time with the 2nd annual "Worm Chariot Races"


Simple walking behavior are possible.


You can program the to react to their surroundings too.


Let's not forget about the Dancin Queens


And the dirtiest dancer of them all?


Seriously?

Tic Tac Toe

Tic Tac Toe is a pretty simple game to learn compared to chess or even checkers. But programming a robot to play is a lot more difficult than you might think. For starters there are 9! possible board configurations. Then there is the problem of sensing the board and moving the pieces. A group of students tackled this in Intro to Robotics:

A REALLY tiny project

1/C Eric Eastman (ESE) and 1/C Bryan Watson (ESE) attended the RoboCup US Open 2008 at Carnegie Mellon University on May 24-25 to participate in the Nanogram League demonstration. The Nanogram League is one of the newer leagues constraining the robotic devices to fit within a 300micrometer × 300micrometer footprint. The action takes place under the lens of a microscope with a 2.5 mm playing field and 50micrometer diameter balls. USNA also participated in the first Nanogram League Competition in 2007 in Atlanta, GA. The team plans to compete in 2009 in Vienna, Austria.

A Firm Grip

This year, for the first time we did open ended final projects in ES450 Intro to Robotics. There were lots of really creative entries, but this was one of the most original. The robot handshake:

Mids Warren and Smith

The robot uses a camera system to identify skin tones in the image. It computes the center and orientation of that group of pixels in space to try to estimate where it should move to meet your hand. The only problem? The grip is just a little too firm.