International Conference on Intelligent Robots and Systems (IROS) 2020

The 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems will be held on October 25–29, 2020 in Las Vegas at The Caesars Forum Conventional Center. As a flagship conference, IROS gathers the world’s leading roboticists and academic, industrial and government stakeholders. For over 30-years, IROS has been annually held in Europe, Asia, and The Americas. IROS was last held in the US in 2014 and finally returns and is themed “Consumer Robotics and Our Future”. This serves to reflect the growth in commercial robot products and services. Such growth comes along with breakthroughs in artificial intelligence (AI), big data, and the Internet-ofThings (IOT). These are exciting times given mass interest in driverless cars and services, personal drones, augmented reality, wearable prosthetics, and smart assistants.

IROS 2020 expects record attendance. But moreover, IROS 2020 is designed to enhance the attendee experience, leveraging Las Vegas’ leadership in hosting largescale conferences.

MathWorks is an exhibitor at this event. MathWorks is also organizing a full-day tutorial, as detailed below:

From perception to planning and intelligence: A hands-on course on robotics design and development using MATLAB and Simulink

Sunday, October 25, 2020 - Full day

Content

An autonomous system must reliably process sensor data and operate actuators to execute individual tasks or an entire mission consisting of various tasks. The design of such a system is challenging and its complexity depends on the desired level of autonomy and intelligence.

Perception, planning, and control are the key technologies to enable autonomy of a robotics system. Perception relies on sensory data to acquire self and global awareness that allows the robot to accomplish navigation tasks. Planning provides a safe, collision-free path towards a desired destination in presence of obstacles. Finally, a control system gets the robot’s actuators to execute a specific set of motions and forces to closely follow the path to the goal in a realistic setting full of uncertainty and disturbances.

MATLAB and Simulink have long been used in industry, research, and education for a wide variety of applications. Industries as automotive, aerospace, and industrial automation have successfully used MATLAB and Simulink for Model-Based Design including automatic code generation, test and verification, and real-time prototyping. Moreover, thousands of researchers around the world use MATLAB and Simulink to carry out their research including data analysis and algorithm development. Newer features and functionalities for deployment of algorithms via automatic code generation on embedded hardware platforms are becoming increasingly relevant for advanced autonomous systems.

Features for advanced perception algorithms development, embedded planning and control algorithms, machine learning tools, ROS connectivity, automatic code generation, and hardware deployment make MATLAB and Simulink suitable environments for design and development of advanced robotic systems both in desktop simulation and on physical robots.

During the tutorial, participants will have the opportunity to learn about the enabling technologies of a robotics system from a series of lectures around prototyping and deployment using MathWorks tools. We will present how Model-Based Design aligns with the development of advanced robotics applications.

The tutorial will be comprised of four sessions: Perception, Planning, Machine Learning for Controls, and Implementation and Deployment. The first three sessions will have two parts: one lecture by an esteemed professor to introduce the main concepts of the topic and one hands-on tutorial by a MathWorks engineer who will show the use of MATLAB and Simulink towards that topic in a robotic system application. Finally, the fourth session will be dedicated to automatic code generation and hardware deployment. Moreover, during the same session, ROS connectivity through MATLAB and Simulink will also be explored.

Throughout the tutorial, participants will have access to MATLAB, Simulink and various toolboxes, via a temporary license, to allow active participation during the hands-on sessions.

Tentative Schedule:

Sessions

Time

Presenter

Details

 

8:30

Roberto Valenti

Welcoming Remarks

Perception

8:40

Davide Scaramuzza

Lecture: Perception in robotics

9:30

Valerie Leung

Hands-on:  Deep learning workflow

 

10:30

Coffee Break

Motion Planning

11:00

Taskin Padir

Lecture: Motion planning

11:45

YJ Lim

Hands-on: Motion planners

 

12:30

Lunch Break

Machine Learning for Controls

13:30

Kyriakos Vamvoudakis

Lecture: Reinforcement Learning for Robotics

14:15

Craig Buhr

Hands-on: Reinforcement learning workflow

 

15:15

Coffee Break

Implementation and Deployment

15:45

Valerie Leung

Hands-on: From MATLAB to C/C++

16:30

YJ Lim

Hands-on: Using MATLAB and Simulink with ROS

 

17:30

Anastasia Mavrommati

Adjourn

The participants will be required to download a list of MathWorks tools, prior to the tutorial, in order to follow the hands-on sections. Such list along with a temporary license will soon be provided in this website.

Organizers

Speakers

  • Taskin Padir, Professor at Northeastern University, USA
  • Davide Scaramuzza, Professor at ETH Zurich, Switzerland
  • Kyriakos Vamvoudakis, Professor at Georgia Institute of Technology, USA
  • Craig Buhr, Development Manager, MathWorks
  • Valerie Leung, Application Engineer, MathWorks
  • YJ Lim, Technical Product Manager, MathWorks

 

For more information visit International Conference on Intelligent Robots and Systems (IROS) 2020.

Location & Dates

Las Vegas, Nevada
25 Oct 2020 - 29 Oct 2020