Please join MathWorks for a series of live MATLAB & Simulink webinars with our North American Academic Engineering team!
We invite you to attend the following free sessions focusing on how our tools support various disciplines and research areas across academia.
Register below for your preferred sessions. You can register for as many sessions as you like. Please note that seats are limited and therefore registration is required.
MATLAB and Simulink with Python
Monday, April 19th at 11:00 am - 12:00 pm PDT
Engineers who rely only on Python may find themselves encountering difficult or challenging tasks when it comes to embedded applications, building interactive dashboards, parallelizing applications, and deep learning. Contrarily, MATLAB® is a full-stack advanced analytics platform that empowers domain experts to rapidly prototype ideas, validate models, and push applications into production with ease; however, sometimes it is advantageous to integrate MATLAB and Python. One example is the need to combine the MATLAB library of advanced analytic capabilities with supplemental models available in the open-source community. Another, using Python as a language that is well suited to pipe data between different IT systems or the web.
There are several ways to integrate MATLAB and Python either as R&D tools or as scalable components of your production infrastructure. The latter gives business users and decision-makers immediate access to many of the built-in analytic capabilities in MATLAB from deep learning, optimization, signal and image processing, computer vision, data mining, time-series forecasting, embedded code generation, and more.
Watch the many ways in which MATLAB and Python can interface and integrate with each other.
- Calling Python libraries directly from MATLAB
- Calling Python from within a Simulink® model
- Calling a live MATLAB session from Python
- Package MATLAB analytics as royalty-free .py libraries
- Scaling hybrid MATLAB and Python applications via MATLAB Production Server™
About the Presenter
Sean de Wolski is a Senior Application Engineer at MathWorks focused on the MATLAB product stack with a specialty on developing production applications. Throughout his time at MathWorks he has supported customers across all industries and sizes with their use of MathWorks' products. Sean holds a M.S and B.S. in Civil Engineering with a Structural Engineering focus from the University of Maine. His research focused on developing tools to better characterize microstructural properties of concrete using x-ray microtomography and image processing.
Scaling Up MATLAB Applications to Clusters and Clouds
Tuesday, April 20th at 11:00 am – 12:00 pm PDT
In this session, you will learn how to solve and accelerate computationally and data-intensive problems using multicore processors, GPUs, clusters, and the cloud. We will introduce you to high-level programming constructs that allow you to parallelize MATLAB applications and run them on multiple processors. We will also discuss how to take advantage of GPUs to speed up computations without low-level programming. You will learn how to prototype on the desktop and scale to more resources on clusters and in the cloud without recoding.
- Toolboxes with built-in support for parallel computing
- Scaling desktop workflows to clusters for additional resources, without recoding
- Using the cloud for additional compute capacity
- Accelerating MATLAB applications with NVIDIA GPUs
- Working with big data
About the Presenter
Bo Luan is an application engineer at MathWorks based in the Bay Area. He supports users in the field of data analytics, parallel computing, and application deployment. His experience focused on signal/image processing, statistics, machine learning, and mixed-signal embedded hardware. He holds a Ph.D. in Electrical Engineering from the University of Pittsburgh.
The Use of MATLAB in Open Science
Wednesday, April 21st at 11:00 am – 12:00 pm PDT
Learn how to write transparent and comprehensible code using MATLAB®, create MATLAB code that is intra-operable with other languages, share research artifacts with your community, including those without a license, and use MATLAB on Science Gateways.
The different offerings for Open Science are divided into three categories aimed at making code transparent, available, and accessible:
- Making code more transparent deals with Live Scripts and using source control with MATLAB.
- The section on availability shows how to package software in projects and share them as MATLAB toolboxes. It introduces File Exchange as a platform for re-usable software and explains how you can share your code with non-MATLAB users through third-party access for academia or MATLAB integration with Python and other languages.
- Finally, the section on accessibility introduces MATLAB in a Docker container, Parallel Computing Toolbox™ for faster execution, and MATLAB Online™ and Simulink Online™. This section also shows what successful MATLAB integration on a Science Gateway looks like for researchers using online shared resources.
About the Presenter
Dr. Shubo Chakrabarti is the EMEA Science Gateway Strategist at MathWorks and helps researchers using and hosting online portals to effectively share and easily access MATLAB and Simulink for their research.
Shubo earned his PhD in neuroscience at the Penn State University Medical College in the US. Before joining MathWorks, Shubo worked as a senior neuroscientist and project leader for several years at the Universities of Göttingen and Tübingen. He is an Alexander von Humboldt fellow and a reviewer for several scientific journals and the German Research Society (DFG).
What's New in MATLAB and Simulink for Automated Driving Development
Thursday, April 22nd at 11:00 am - 12:30 pm PDT
Automated driving spans a wide range of automation levels, from advanced driver assistance systems (ADAS) to fully autonomous driving. As the level of automation increases, the use scenarios become less restricted and the testing requirements increase, making the need for modeling and simulation more critical. MATLAB®, Simulink®, and RoadRunner support engineers are developing automated driving systems with increasing levels of automation.
In this session, you'll discover new features in R2020b and R2021a that will allow you to:
- Analyze, calibrate, and label sensor data
- Simulate sensors, scenarios, and vehicle dynamics
- Design detection, localization, sensor fusion, planning, and controls algorithms
- Deploy to C, C++, GPU, and ROS
- Test functionality and code
About the Presenter
Pitambar Dayal is product manager for automated driving toolbox at MathWorks. In the past, he has worked on building MATLAB examples for deep learning, image processing, and computer vision and on developing healthcare solutions in developing countries. Pitambar graduated with a B.S. in Biomedical Engineering from New Jersey Institute of Technology.
Design Industrial Robot Applications from Perception to Motion
Tuesday, April 27th at 11:00 am – 12:30 pm PDT
Advanced robotics systems are core in the factory of the future. Designing autonomous robotics systems requires knowledge and experience in many engineering domains, including mechanical design, perception, decision making, control design, and embedded systems. In this talk, you'll hear about a complete autonomous robotics workflow that allows engineers to easily learn and apply the many functional domains of robotics. You will also learn about the key features that enable engineers to develop an end-to-end workflow from perception to motion for industrial robot application designs.
Some additional topics you'll hear about include:
- Performing scalable physics simulation
- Designing perception algorithms using computer vision and deep learning
- Setting up co-simulation with sensor and environment models
- Using motion planning for obstacle avoidance
- Achieving advanced control via reinforcement learning
- Connecting hardware through ROS network and deployment
- Physical modeling and simulation
- Robotic perception
- Motion planning for robot manipulator
- Robot motion control and reinforcement learning
- Hardware connection and deployment
About the Presenter
YJ Lim is a Sr. Technical Product Manager for robotics at the MathWorks. Before joining MathWorks, YJ worked for Vecna Robotics in Waltham, MA, leading a team working on Vecna's advanced robotic system. Prior to Vecna, YJ served as the Chief Innovation Officer at Hstar Technologies, a firm focused on agile mobile robotic platform and healthcare service robotics system. Before that, YJ led development teams at Energid Technologies for robotic software development. His first job started in automotive industry, Daewoo Motors, S. Korea, for advanced platform research. YJ received his Ph.D. in mechanical engineering from Rensselaer Polytechnic Institute (RPI) and his Master from KAIST in S. Korea.
Developing Autonomous UAV Applications with MATLAB and Simulink
Wednesday, April 28th at 11:00 am – 12:30 pm PDT
Learn how MATLAB and Simulink can be used with UAV Toolbox for workflows to design and simulate autonomous UAV applications, including:
- Approximating UAV dynamics for fast design iterations on the autonomous algorithms
- Constructing UAV scenarios and simulating in cuboid environments
- Using Unreal Engine co-simulation with sensor models for closed-loop 3D simulations
- Automatic code generation for deployment to PX4 autopilot hardware and onboard computes
- Analyzing post-flight telemetry data with the interactive Flight Log Analyzer app
- UAV Simulation Models: Approximate UAV behaviors for fixed-wing and multirotor platforms
- Planning and Controls: Motion planning with waypoint follower, trajectory-following, and path planning algorithms
- Creating UAV Scenarios: Simulation scenarios including environmental obstacles (e.g. buildings), UAV platforms, and sensors
- Cuboid Simulation: Generate sensor data and test controllers, tracking algorithms, and sensor fusion algorithms in simplified 3D environment
- Unreal Engine Co-Simulation: Simulate UAV applications in a realistic 3D simulator with sensor models
- Deployment to Autopilots and Onboard Computes: Automatically generate code to implement onto autopilot and onboard compute hardware, such as PX4 autopilots and NVIDIA Jetson
- Connect with MAVLink Protocol: Communicate with UAV hardware with MAVLink communication protocol support
- Flight Log Analyzer App: Interactively load and analyze UAV autopilot flight log data
- Visualize Custom Flight Logs: Define customized signals and plots to visualize data
About the Presenter
Ronal George, application engineer for robotics and autonomous systems. Ronal has a Master's degree in Electrical Engineering from North Carolina State University. As a part of his Master's, Ronal worked with the Advanced Diagnosis, Automation and Control (ADAC) Laboratory to develop planning and localization algorithms for multi agent systems. Prior to joining MathWorks in April 2019, Ronal worked as an Inside Sales Engineer at SPX Transformer Solutions and as an Electrical Design Engineer at WindLabs.
Lidar Processing for Autonomous Systems
Thursday, April 29th at 11:00 am – 12:30 pm PDT
Learn how to use MATLAB to process lidar sensor data for ground, aerial and indoor lidar processing application. In this session you will learn how to use MATLAB to:
- Import and visualize live and recorded lidar data
- Apply deep learning to lidar data
- Calibrate lidar and cameras
- Track objects in lidar
- Create 3-D maps and terrain maps using SLAM
- Generate C/C++ and GPU Code
- Lidar Labeler App: Interactive, semi-automated, and custom automated labeling of lidar point clouds
- Lidar-Camera Calibration: Calibrate lidar and camera sensors to estimate cross-sensor coordinate transform
- Deep Learning for Lidar Point Cloud Processing: Use deep learning networks to detect and segment objects in lidar point cloud data
- Shape Fitting: Fit shape and track detected objects in a lidar point cloud sequence
- Feature Matching: Extract and match lidar point cloud features
- Lidar Object Tracking
- Simulating Lidar Sensor Data
- 2-D Lidar Processing: Simulate and process 2-D laser scan data and estimate the pose between two scans
- Velodyne LiDAR Streaming: Connect and stream lidar point clouds from Velodyne LiDAR sensors
- Lidar File Readers: Support for Ibeosensor, LAS, and LAZ file formats
- Code generation for CPU and GPU
About the Presenter
Avinash Nehemiah, Principal Product Marketing Manager for computer vision, automated driving and deep learning at MathWorks, has ten years of experience in computer vision. Prior to joining MathWorks he led a team that created a computer vision-based solution for patient safety in hospital rooms. Avinash has a Master's degree in electrical and computer engineering from Carnegie Mellon University, where his research focused on object recognition in radar imagery.
Simulink Was Made for Mechatronics: The Evolution of Testing Intelligent Machines
Friday, April 30th at 11:00 am – 12:30 pm PDT
As today's systems have grown ever smarter, embedded software has taken on an increasingly significant role in integrating a diverse range of electrical and mechanical components to make what seems like magic happen. Developmental testing guides the software design process to optimal system performance, while continuous operational testing assesses the quality and identifies any necessary upgrades. As we all know, more and better testing always helps! But how do you iterate the build and test process and remain fast?
Simulink enables you to replace prototypes with simulations that directly support the software design process. Once hard constraints on time and money for prototypes are relaxed, see what great ideas can come to life in the form of new and better systems!
Our specific agenda:
- Prototype plant and control in Simulink
- Model mechanics – import designs from tools like SolidWorks, CATIA, NX, etc.
- Develop control algorithms informed by the mechanical and electrical design.
- Deploy field-oriented control for permanent magnet synchronous motor (PMSM).
- Prototype testing and tuning control algorithm in real-time while connected to PMSM motor
- Create a real-time application from a Simulink model, step-by-step
- Connect and interact with hardware such as actuators and sensors
- Log data and tune parameters while running in real-time
- Create graphical user interfaces for real-time testing
About the Presenters
Terry Denery, Ph.D.
Prior to MathWorks, Terry developed rocket motors at Hercules Aerospace (Now Aliant Technologies), and focused deeply on mechanical design and analysis at MSC, supporting use of products like ADAMS, Working Model, and visual NASTRAN. Since joining MathWorks in 2004, Terry has met thousands of engineers to discuss control design and modeling electro-mechanical devices.
Education: Ph.D. in Aeronautics/Astronautics, Stanford University; B.S. in Chemical Engineering and M.S. in Mechanical Engineering, University of Virginia
Before joining The MathWorks in May 2007, he worked for 14 years in the aerospace industry where he was involved in Hardware-in-the-Loop testing of guidance, navigation, and control systems, including real-time, closed-loop simulation incorporating sensors such as GPS, accelerometers, gyros, and autopilots.
Education: M.S. in Aerospace Engineering (Combustion) from Georgia Institute of Technology, B.S. in Aerospace Engineering (Fluid Dynamics) from Syracuse University.