2014 IEEE-RAS International Conference on Humanoid Robots. November 18-20th 2014. Madrid. Spain. YoutubeGoogle+FacebookTwitterEmail
humanoidsweb2014

MathWorks Lunch & Learn Event: MATLAB/Simulink for Robotics Research and Teaching

Type and Duration: Tutorial, 14:00-15:00, November 19th, 2014

Room: Comendador

Meal: During the presentation cold meal packs will be distributed

Presenters

Lucas Garcia (MathWorks)

Valerie Leung (MathWorks)

Yanliang Zhang (MathWorks)

Organizer

Yanliang Zhang (Ph.D.)
Robotics Marketing Manager
Address: The MathWorks Inc.,
                 3 Apple Hill Drive,
                 Natick, MA 01760, USA
Direct:     508.647 8625
Email:      This email address is being protected from spambots. You need JavaScript enabled to view it.

URL: http://www.mathworks.com/company/events/tradeshows/tradeshow93612.html

Abstract

MATLAB and Simulink are used throughout the automotive, aerospace, communications, electronics, and industrial automation industries as fundamental tools for research and development. They are also used for modeling and simulation in increasingly technical fields, such as financial services and computational biology. MATLAB and Simulink enable the design and development of a wide range of advanced products, including automotive systems, aerospace flight control and avionics, telecommunications and other electronics equipment, industrial machinery, and medical devices. More than 5000 colleges and universities around the world use MATLAB and Simulink for teaching and research in a broad range of technical disciplines.

There is a long history of MATLAB/Simulink use in robotics teaching and research. MATLAB/Simulink forms the basis of tutorials and laboratories for many robotics courses around the world.   In more recent times there has been interest in using MATLAB/Simulink for robotics problems beyond the classical arm-manipulator kinematics, dynamics and control, for example computer vision, path planning SLAM, and connecting MATLAB/Simulink to real-world robots such as LEGO MINDSTORMS and NAO robot, and robot middleware (e.g., ROS).

This 1-hour workshop will cover three topics:

  • MATLAB/Simulink Support for Low-cost Hardware (e.g., Arduino, Raspberry Pi, and LEGO NXT)
  • Programing NAO Robot inside MATLAB
  • ROS Support from MATLAB

MATLAB/Simulink Support for Low-cost Hardware

To address the growing concern in research and teaching for low-cost, easy to use hardware and software environments, MATLAB and Simulink now include the capability to program low-cost hardware such as Arduino, Raspberry Pi, LEGO MINDSTORMS and other platforms.

In this session, we will demonstrate how to develop and test robot control algorithms that access and use standard LEGO MINDSTORMS sensors and actuators, and automatically generate code to program the robot using MATLAB and Simulink. Highlights include:

  • Learning how to easily connect Simulink to hardware
  • Designing, simulating and testing algorithms in Simulink
  • Programming low cost hardware with auto-generated code
  • Real-time parameter tuning with hardware-in-the-loop simulations

Programing NAO Robot inside MATLAB

NAO is a small programmable humanoid robot developed by Aldebaran Robotics. The MATLAB API provided by Aldebaran allows you to develop robotics applications with NAO using MATLAB/Simulink. Using a face-tracking example, this session will address the following topics:
  • Establish connection with NAO from MATLAB/Simulink
  • Acquire sensor data from NAO into MATLAB/Simulink
  • Send instructions to NAO from MATLAB/Simulink

Demonstrations of NAO mimicking the movement of a person, as well as NAO on a swing will also be given.

ROS Support from MATLAB

With ROS support from MATLAB, you can interact with robots and simulators that provide a ROS interface. You can also create a self-contained ROS network directly in MATLAB. These features allow you to develop your robotics algorithms in MATLAB, while giving you the ability to exchange messages with other nodes on the ROS network.

In this session, the following MATLAB-ROS interactions will be demonstrated:
  • Create ROS nodes, publishers, or subscribers directly from MATLAB
  • Create and send ROS messages from MATLAB
  • Enable publishers to publish MATLAB data to their advertised topics
  • Enable subscribers to execute arbitrary user-defined MATLAB functions
  • Enable launching of ROS masters on the local host from MATLAB
  • Connect to a TurtleBot Simulator inside Gazebo from MATLAB
  • Connect to a TurtleBot from MATLAB