MIT: Independent Activities Period: IAP

IAP 2016 Activities by Category - A.I. and Robotics

Expand All | Collapse All


Build a CNC painting robot

Ben Tritt, CEO ArtMATR

Enrollment: Limited: Advance sign-up required
Sign-up by 01/01
Limited to 10 participants
Attendance: Participants must attend all sessions
Prereq: none
Fee: $40.00 for supplies

We are seeking a team of students who want to bridge the divide between computer science and art. We are creating devices which can produce complex and layered oil paintings and seeking to link that output to existing digital painting software. Part of this project involves collaboration with the e-David robotic painting device at the University of Konstanz in Germany.  Their team has developed a simulator which emulates the physical output of the e-David device.


Students will work with a simple CNC system at MIT to develop a "repertoire of marks,"  i.e. the basic building blocks of paintings and their parametric attributes.  A secondary goal is to understand how the e-David hardware, software and algorithmic strategy work with the brush simulator. This will require close collaborative efforts with the researchers and code developers in Germany. Follow on steps will include a research residency in Konstanz and subsequently having the e-David visit MIT for further development.

 

 

Contact: Sam Magee, E15-205, 617 253-4004, SAMMAGEE@MIT.EDU


Jan/05 Tue 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/06 Wed 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/07 Thu 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/08 Fri 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/09 Sat 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/12 Tue 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/13 Wed 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/14 Thu 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/15 Fri 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary
Jan/16 Sat 12:00PM-02:00PM W20-429 /START STUDI, Bring your laptop / times may vary

Meeting times, not dates, may vary.

Ben Tritt - CEO ArtMATR


Build an RC Bot you can control with your smartphone using Cypress Programmable System-on-a-Chip (PSoC)

Danielle Class, Patrick Kane, Mike Daly, Craig Cheney, Steven Leeb, Greg Landry

Jan/26 Tue 10:00AM-05:00PM EDS, 38-501
Jan/27 Wed 10:00AM-05:00PM EDS, 38-501
Jan/28 Thu 10:00AM-05:00PM EDS, 38-501

Enrollment: Limited: Advance sign-up required
Sign-up by 01/10
Limited to 30 participants
Attendance: Participants must attend all sessions
Prereq: Programming, circuits, soldering experience helpful

The goal of the competition is to build an RC Bot that can be controlled using the Bluetooth Low
Energy (BLE) protocol. If you have an iPhone 4 or newer or an Android device, BLE is already
built into it.
You will compete in a Programmable System on a Chip (PSoC) design competition using a
Cypress CY8CKIT-042-BLE PSoC 4 Pioneer Bluetooth Low Energy development kit. PSoC 4
BLE is a programmable device with an ARM Cortex M0, programmable digital and analog
blocks, and a BLE radio all on a single chip!
Workshop Breakdown
• Session 1: Combination of lecture and hands-on labs to introduce you to PSoC 4 BLE
and its design environment (PSoC Creator), as well as the RC Bot structure.
• Session 2: Hands-on RC Bot build day.
• Session 3: Finish RC Bot project and present your version of the solution.
Space is limited. To apply, please e-mail your full name, MIT class year and major, and MIT email
address to iap-psoc@mit.edu. We’ll let you know after January 10th if you have received a
spot in the class. We will maintain a waiting list in the event that spots open up.

Circuit boards sponsored by Sunstone Circuits -  quoting.sunstone.com

Sponsor(s): Electrical Engineering and Computer Science
Contact: Danielle Class, iap-psoc@mit.edu


RACECAR - Rapid Autonomous Complex-Environment Competing Ackermann-steering Robot

Prof. Sertac Karaman, Dr. Michael Boulet, Owen Guldner, Ken Gregson, Dr. Luca Carlone, Postdoctoral Associate, Aero/Astro

Jan/04 Mon 01:00PM-05:00PM 32-081
Jan/06 Wed 01:00PM-05:00PM 32-081
Jan/08 Fri 01:00PM-05:00PM 32-081
Jan/11 Mon 01:00PM-05:00PM 32-081
Jan/13 Wed 01:00PM-05:00PM 32-081
Jan/15 Fri 01:00PM-05:00PM 32-081
Jan/20 Wed 01:00PM-05:00PM 32-081

Enrollment: Limited: Advance sign-up required
Sign-up by 01/01
Limited to 30 participants
Attendance: Participants must attend all sessions
Prereq: See description.

Modern robots tend to operate at slow speeds in complex environments, limiting their utility in high-tempo applications. In this course you will push the boundaries of unmanned vehicle speed. Teams of 4-5 will develop dynamic autonomy software to race an RC car equipped with LIDAR, cameras, inertial sensors, and embedded processing around a large-scale, “real-world” course. Working from a baseline autonomy stack, teams will modify the software to increase platform velocity to the limits of stability. The course culminates with a timed competition to navigate the MIT tunnels. Classes will provide lectures on algorithms and lab time with instructor-assisted development. Must attend every class and plan on 6-10 hr/week of self-directed development.

Prereqs: Advanced undergraduates and graduates with some background in controls or robotics. Majors include AeroAstro, Mechanical, Ocean, and EECS. Students with a background in computer science with interest in robotics and controls may also effectively participate. Must have experience with software development. Past exposure to robotics algorithms and/or embedded programming will be useful. Email racecar-iap-course-subscribe@mit.edu with a brief description of your programming/robotics experience.

*This work is sponsored by the Dept. of the Air Force under Contract FA8721-05-C-0002.  Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the U.S. Government.

Sponsor(s): Aeronautics and Astronautics, Lincoln Laboratory, Electrical Engineering and Computer Science
Contact: Owen Guldner, racecar-iap-course-subscribe@mit.edu


Technologies for Speech and Language Processing

Tuka AlHanai, Research Assistant at CSAIL, Mandy Korpusik, Research Assistant at CSAIL

Enrollment: Limited: Advance sign-up required
Limited to 15 participants
Attendance: Participants must attend all sessions
Prereq: Some programming experience.

Do you want to build your very own Siri? Ever cared to automatically detect sentiment? Curious about what can be done with the 6,000+ languages out there? This course covers some of the hottest topics and technologies in the domain of Speech and Language Processing, the playground of Amazon, Google, and Apple. You'll be learning theory on acoustic-phonetics, machine learning, natural language processing, and techniques for data collection. You'll leave with working knowledge on some of the tools available and the potential of their usage for your next project, hackathon, and start-up.

Sign-up Here

Contact: Tuka Al Hanai, 32-G424, TUKA@MIT.EDU


Acoustic Phonetics

Jan/08 Fri 02:00PM-04:00PM 66-148, Bring your laptop

Language Modeling

Jan/11 Mon 02:00PM-04:00PM 66-148, Bring your laptop

Acoustic Modeling

Jan/13 Wed 02:00PM-04:00PM 66-148, Bring your laptop

Building a Recognizer

Jan/15 Fri 02:00PM-04:00PM 66-148, Bring your laptop

Bringing Speech Tech to the World

Jan/19 Tue 02:00PM-04:00PM 66-148, Bring your laptop

The Science and Engineering of Intelligence: A bridge across Vassar Street

Andrea Tacchetti

Jan/15 Fri 10:00AM-05:00PM 46-3002

Enrollment: Unlimited: No advance sign-up
Prereq: None

Neuroscience has made huge advances in the last few years. We now know more about how the brain works than we have ever known before. Likewise, Computer Science and Artificial Intelligence have made enormous steps forward and have become part of our every-day lives. The interaction between Neuroscience and Computer Science has inspired most recent advances in Artificial Intelligence and this interaction has become a critical stepping stone for the understanding of intelligence. We assembled a stellar list of speakers at the intersection of Neuroscience and AI from both sides of Vassar Street who will give an account of how this multi-disciplinary interaction affects their work. The tentative list of speakers includes:

Professor Ed Boyden
Professor Tomaso Poggio
Professor Nancy Kanwisher
Professor Feng Zhang
Professor Bill Freeman
Professor Joshua Tenenbaum

Schedule and other information about the event can be found here: http://cbmm.mit.edu/science-engineering-vassar

 

Sponsor(s): Brain and Cognitive Sciences
Contact: Andrea, Tacchetti, N/A, atacchet@MIT.EDU