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 MATLAB®, which is a public domain Matlab package that enables one to interface with and control LEGO mindstorms.

The RWTH – Mindstorms NXT Toolbox for MATLAB® 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

Kevin Knuth
Albany NY

CLARAty Reusable Robotics Software

CLARAty (Coupled-Layer Architecture for Robotic Autonomy) is a framework for reusable robotics software. It was developed in part by my former colleagues at NASA Ames Research Center in collaboration with Jet Propulsion Laboratory, Carnegie Mellon, and the University of Minnesota (my alma matter).

They are in the process of making the framework and several modules publicly available. 

Videos of systems using CLARAty can be found here.
Presentations on CLARAty can be found here.
Publications can be found here.

Kevin Knuth
Albany NY

Why Intelligent Machines Appear Intelligent (or Not)

I have been working for about 48 hours (straight with intermittent cat naps) on my robotic arm, which is equipped with a point light sensor.  I have re-programmed it to characterize polygons as well as circles.  However, the main purpose of this research project is to develop an inquiry engine that is generally engineered to decide which experiment the robot should perform to obtain the information that it requires.  In this case, an experiment is characterized by the location of potential light measurements.

Here is a link to an older post that references a research paper, a slide presentation, and a video of my talk on this topic.

One thing that has surprised me is just how intelligent the instrument appears.  It selects measurements that are obviously the smart measurements to take.  What is strange, is that I can intrepret these measurements in terms of the techniques that I would employ to solve the problem, such as: “It is trying to find the edge of the polygon” or “It is verifying that the center of the polygon is where it thinks it is” or “It is checking to see if there is a vertex at a given position”. 

The important fact is that the robot is not using heuristics at all, which is what makes this intelligent system a powerful and generic plug-and-play system.  Instead, the robot is maximizing the relevance of the experimental question with respect to the issue that the robot is programmed to resolve (in this case characterizing a white shape on a black background).  The relevance is related to the entropy, and the inquiry engine performs its computations by sampling a posterior probability of models and considering the entropy of the set of predictions that this set of models makes regarding the outcomes of potential measurements.

How can an instrument that simply performs computations with entropy select manuevers which I, who uses heuristics (or general problem-solving strategies), easily recognize as intelligent.  The only reason I can imagine is that my heuristics work!  The heuristics that I employ to solve such problems are excellent approximations to computing relevance via entropy.

An interesting consequence of this is that sometimes the robot chooses a measurement that I cannot interpret as intelligent.  However, when I study the results of the measurement, I always find that these measurements provide a great deal of information; more than the measurement I would have selected.

The system still has some difficulties, which involves two issues.  The first issue is the fact that the current algorithm design requires that the new measurements be analyzed in conjunction with all of the past measurements.  I could get around this with particle filters, but this is an approximation to the complete inference problem, and I’d like to avoid that.  I am working on a solution to this. 

The second issue has to do with the fact that I require a diverse set of probable models to query to perform the entropy calculations.  If the set is not sufficiently diverse, the robot does not consider the wide variety of possible solutions when it is planning the next experiment.  There are easy ways to assure that the set of samples is diverse, but this takes computation time, which I am aiming to avoid.

In the near future, I will have a video of the robot in operation.

Kevin Knuth
Albany NY

Wolfram Web Resources

I received this brochure from Wolfram Research (Mathematica) describing their web resources.  I am going to lose it… so I will remember it here in my Online Cortex. is updated regularly with information on new breakthroughs and developments for Mathematica users and technology enthusiasts around the world.  This site features demonstrations and videos on the core Wolfram products, a secure and reliable online store, and a variety of valuable resources for professionals, academics, and students in any field.

The Wolfram Demonstrations Project
The Wolfram Demonstrations Project is an open-code resource that brings to life concepts in science, technology, mathematics, art, finance, and a remarkable range of other areas. From elementary education to front-line research, topics span an ever-growing array of categories, with new interactive visualizations added each day by Mathematica users.

Wolfram Mathematica Documentation Center
All Mathematica documentation is now deployed both in-product and online, featuring over 50,000 carefully chosen examples, animations and tutorials, as well as over 100,000 links.  Used every day as an indispensible reference guide, for Mathematica users, the uniquely powerful documentation system is also ideal for those new to the system who want to learn more about Mathematica’s 2500+ high-level functions for visualization, programming, and computation.

Wolfram Mathworld
MathWorld is the web’s most extensive mathematics resource.  Assembled over more than a decade and updated regularly with contributions from the world’s mathematics community.  MathWorld features downloadable Mathematica notebooks, interactive applets, and nearly 13,000 entries on topics ranging from pre-algebra to calculus, number theory, and more.

A vast colelction of Mathematica-related material, including thousands of articles, references, and courseware programs, conveniently indexed and organized.

A unique webMathematica-powered site for instantly solving integrals online.

The worlds largest collection of formulas and visualizations about mathematical functions.

Wolfram Science
The official website of Stephen Wolfram’s A New Kind of Science, with full-text and enhanced features.

Original music mined from the computational universe, featuring free-downloads and a generator to create your own personal tones.
A homepage from Mathematica creator, A New Kind of Science author, and Wolfram Research CEO Stephen Wolfram.

Robots and the Coming Creation

‘Am I already in the shadow of the Coming Race? and will the creatures who are to transcend and finally supersede us be steely organisms, giving out the effluvia of the laboratory, and performing with infallible exactness more than everything that we have performed with a slovenly approximativeness and self-defeating inaccuracy?’
                – George Eliot,
                   The Impressions of Theophrastus Such, 1879.

The robot creation is about to happen.
– We know how to design machines that reason
– We know how to design machines that learn
– We know how to design machines that question
and more..

Could it really be that the ultimate achievement of the Human Race will be to create Life itself? 
Boldly I ask “Why Not?”

We have already reached into the Heavens and find the experience inviting.  But how much higher than the spire of the Tower of Babel can we reach?  The Moon is certainly high, and the other worlds of our Solar System higher still, yet at this very moment… right now as you read this… we are exploring these heights with the precursors to the Coming Race. (mars, saturn, sun, mercury, pluto, venus).

Reaching into the sky, while a fantasy of the Babylonians, has become commonplace to us.  But the Act of Creation is another thing altogether.

How amazing it will be when we send our first true Creations up, away, and deep into the  Heavens to travel about with God’s bacteria. 
A bold and arrogant notion?  YES!

And on that most glorious of days,
God Himself will ascend to become a Creator of Creators.

Kevin Knuth
Albany NY