Boston Dynamics Big Dog


   

By now, almost everyone has seen Boston Dynamics’ Big Dog.
This quadruped robot is dynamically stable enabling it to accommodate a wide variety of terrain as well as changes in the dynamical environment, such as slippage or being kicked (my favorite!)

Here are some older, but fun, videos…

Posted under companies, mobility

This post was written by admin on August 31, 2008

Tags: , , ,

Intelligent Instruments

Intelligent Robotic Arm

The LEGO Mindstorm NXT robotics system is an excellent testbed for research in machine learning and artificial intelligence. At Knuthlab Robotics at the University at Albany, we are developing intelligent instruments using LEGOs.

Our first instrument is a robotic arm that is designed to locate a characterize a white circle on a black background using the LEGO light sensor. It relies on Bayesian inference, which is implemented using a technique called Nested Sampling, which was developed by John Skilling. This software allows the robot to learn the characteristics of the circle using the light sensor data that it has collected. The real advance here is the inquiry engine, which uses Bayesian adaptive exploration to decide which measurements to take next. It does this by considering all the possible measurements that it could take, and computes the expected gain in information from each possible measurement. It then chooses to take the measurement with the greatest expected information gain. The process then repeats as the robot learns about the circle.

The system is easily generalized to solving other problems, such as exploring rooms, interpreting people’s emotions, and doing real science.

We recently presented our research at the MaxEnt 2007 workshop in Saratoga Springs NY. Below are links to a video of the talk, my slides, and our research paper.

Video: Designing Intelligent Instruments, K.H. Knuth

Slides: Designing Intelligent Instruments, K.H. Knuth

Research Paper:
Knuth K.H., Erner P.M., Frasso S. 2007. Designing intelligent instruments. K.H. Knuth, A. Caticha, J.L. Center, A. Giffin, C.C. Rodriguez (eds.), Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Saratoga Springs, NY, USA, 2007, AIP Conference Proceedings 954, American Institute of Physics, Melville NY, In press.

Posted under intelligence, mindstorms, research

This post was written by admin on August 31, 2008

Tags: , , , ,

Matlab Package for LEGO Mindstorms

I recently received a comment on my post on controlling NXT robots with Matlab that pointed me to the RWTH – Mindstorms NXT Toolbox for MATLABĀ®, which is a public domain Matlab package that enables one to interface with and control LEGO mindstorms.

The RWTH – Mindstorms NXT Toolbox for MATLABĀ® was developed as a student project in the Institute of Imaging and Computer Vision at RWTH Aachen University in Aachen Germany. It provides a Matlab interface with the NXT brick that includes Bluetooth communication, sensor interface and motor interface. It requires a working Matlab license, of course.

The package is very easy to set up. It took me less than ten minutes to successfully test the example programs over Bluetooth.

There are some very nice motor features, such as motor synchronization and speed ramp-up and ramp-down.

I have yet to explore how easy it is to modify or extend the code, but it ought to be a straightforward matter.

The package can be downloaded from
http://www.mindstorms.rwth-aachen.de

Posted under mindstorms, software

This post was written by admin on August 31, 2008

Tags: , , , , ,

Robots Learn to Follow from Behavioral Cues

Graduate Student Michael Chueh, undergraduates William Au Yeung and Calvin Lei, and Associate Professor Sanjay Joshi at UC Davis recently published the following paper where they describe a methodology for enabling mobile robots to follow a leader based on behavioral cues.

M. CHUEH, Y.-L. YEUNG, K.-P. LEI, and S. JOSHI, Following Controller for Autonomous Mobile Robots Using Behavioral Cues, IEEE Transactions on Industrial Electronics, Vol. 55, No. 8, August 2008, pp. 3124-2132.

More information can be found on the UC Davis website.

Posted under mobility, research

This post was written by admin on August 31, 2008

Tags: , , ,

Basic Electronics Supplies for Beginners

I am getting interested in more general robotics projects, but will still be relying on LEGOs for their construction. The LEGO brick is a bit too limited with its specialized programming languages and limited sensor and motor ports.

So for those interested in some LEGO electronics hacking, here is a list of supplies that will get you up and running fast for about $275… just a but more than the cost of a single Mindstorms kit. Plus you’ll now get to learn electronics!

First, check out the book:
Making Things Talk: Practical Methods for Connecting Physical Objects

This book explains how to wire, program and interconnect various microcontrollers, some of which are very closely related to those used by the NXT Brick.

Supply List

Item Number Description Quantity Unit Price Total
Amazon.com
  Making Things Talk 1 $19.79 $19.79
 
Jameco.com
19166 Desoldering Pump 1 $4.95 $4.95
159291 Wire Stripper 1 $10.15 $10.15
161411 Diagonal Cutter 1 $7.49 $7.49
35474 Needlenose Pliers 1 $5.49 $5.49
127271 Mini Screwdriver 1 $1.89 $1.89
681002 Helping Hands 1 $8.75 $8.75
159611 Power Connector 2 $1.79 $3.58
10444 Alligator Test Clip Leads 2 $4.39 $8.78
103377 Header Pins 10 $0.16 $1.60
119011 Push Button (PCB Type) 10 $0.27 $2.70
29082 Potentiometer 2 $1.05 $2.10
242115 LM1117T-3.3 Voltage Regulator 3 $1.39 $4.17
51262 7805T 5v Voltage regulator 3 $0.32 $0.96
38236 2N2222A Transistor NPN 5 $0.41 $2.05
32993 TIP120 Power Transistor 5 $0.45 $2.25
643488 3.3V Zener Diode 5 $0.03 $0.16
35991 1N4004 Diode 5 $0.04 $0.20
152792 LED Yellow 10 $0.17 $1.70
152805 LED Red 10 $0.21 $2.10
153139 LED Orange 10 $0.35 $3.50
156962 LED Green (567 nm) 10 $0.20 $2.00
334529 LED Bargraph Red 1 $1.31 $1.31
334537 LED Bargraph Yellow 1 $1.23 $1.23
334511 LED Bargraph Green 1 $1.28 $1.28
17187 7-segment LED Display 3 $0.88 $2.64
38818 4-switch DIP 4 $0.48 $1.92
38842 8-switch DIP 2 $0.89 $1.78
103166 Resistor Refill 1 $12.95 $12.95
15270 0.1 uF 10 $0.15 $1.53
94161 1 uF 10 $0.12 $1.20
29891 10 uF 10 $0.06 $0.60
158394 100 uF 10 $0.11 $1.08
 
MPJA
4443 TE Solderless Breadboard 1 $4.95 $4.95
4447 TE Large Solderless Breadboard 1 $22.95 $22.95
7027 TE Jumpers 2 $3.95 $7.90
14213 TE Digital Multimeter 1 $14.95 $14.95
15860 TL Mini Soldering Station 1 $14.95 $14.95
 
Sparkfun
Wiring Platform DEV-00744 1 $84.95 $84.95
 
Radio Shack
64-025 Lead Free Solder 1 $3.89 $3.89

Note that the light gray items are optional, and not necessary.

Also, this list does not include some sort of power supply. Pulling one out of an old computer is an easy option. Or rechargeable batteries work well too (in which case you will need battery holders).

Last, there are special items in the book Making Things Talk that you may decide to purchase separately, such as flex sensors, or bluetooth boards, etc.

You can store your electronics in much the same way you store your small LEGO parts. Check out the article on Storage.

Enjoy Hacking!

Posted under electronics, hacking

This post was written by admin on August 31, 2008

Tags: , , ,

Launch of Autonomous Exploration, Inc.

Autonomous Exploration Banner

Autonomous Exploration Banner

Autonomous Exploration Inc. was created in 2008 by former NASA scientist and academician Kevin H. Knuth and the former president of Creative Research Inc. Julian Center.

This company is focused both on practical machine learning solutions for autonomous systems, as well as, novel computer circuitry designs based on the invertebrate ganglia.

Posted under companies, exploration

This post was written by admin on August 31, 2008

Tags: , , , , , ,

Robot Controlled by Rat Neurons

Mark Hammond a PhD Research Assistant in Kevin Warwick’s Cybernetics Lab at Reading University recently developed a robot that uses 300,000 neurons to assist it in navigation. These cortical neurons were cultured and exposed to 80 electrodes connected to a computer and interfaced to the robot. These electrodes are monitored for regions that are responding coherently to the incoming electrical stimuli. Above is a video.

The New Scientist article is here.

Posted under cyborgs, neuroscience

This post was written by admin on August 31, 2008

Tags: , , , , , , ,