Jim Tung, MathWorks

Organizations with digital transformation initiatives are making the shift from visionary ambitions to practical projects. These organizations have defined their high-level digital transformation objectives, and are now looking to their engineers and scientists to achieve them. This will involve learning new technologies, collaborating with unfamiliar groups, and proposing new products and services. To meet this challenge, technical organisations must master how to systematically use data and models, not only during the research and development stages, but also across groups throughout the lifecycle of the offering. An effective digital transformation plan needs to consider changes in people’s skills, processes, and technology. Join us as Jim Tung describes this pragmatic approach to digital transformation and demonstrates how engineering and scientific teams are leveraging data and models to achieve their digital transformation objectives.

Peter Brady, MathWorks

Learn about new capabilities in the MATLAB^® product families to support your research, design, and development workflows. This talk highlights features for deep learning, machine learning, and other application areas. You will see new tools for preprocessing and analyzing data; developing algorithms; creating interactive apps; packaging and sharing simulations; and modeling, simulating, and verifying designs.

Michelle Hirsch, MathWorks
Heather Gorr, MathWorks

Are you getting the most out of MATLAB^®, or are you still using it just the way you were taught your first year in university? With over 2,000 people working year-round to design, build, test, and document MathWorks products, it is a safe bet that there are more than a few useful features you don’t know.

This fast-paced talk will introduce at least 21 features you can start using today to make your use of MATLAB more efficient, more effective, and more fun. Some features will be very new, while others may be 5, 10, or maybe even more than 15 years old. How many of them will be new to you?

Harshita Bhurat, MathWorks

Identifying product defects and reducing manufacturing errors in industrial applications can help reduce labor and manufacturing costs. While traditional techniques for automated optical inspection tend to be brittle, deep learning based techniques are more robust and more accurate.

Whether you are new to deep learning or an expert, MathWorks tools MATLAB^® can help you detect and localize different types of abnormalities so you can  and hence replace traditional inspection processes with accurate, repeatable, and reliable vision inspection.

Gabriele Bunkheila, MathWorks

Datasets are essential to AI models. They provide the truth by which we train AI models and the tests by which we measure AI success. While researchers tend to reuse well-known datasets, engineers building real-world systems must create datasets that represent all scenarios in which the AI model is expected to operate. This is often an iterative process that requires application-specific resources, tools, and expertise.

In this session, we will explore a well-known practical example: waking up voice-enabled devices using trigger phrases like „Hey Siri” or „OK Google.” We will cover a number of data-specific best practices focused on data labeling and annotation, data ingestion, data synthesis and augmentation, feature extraction, and domain transformations. This practical example provides general considerations that can be applied to a wide range of applications.

Jack Erickson

Designing deep learning, computer vision, and signal processing applications and deploying them to FPGAs, GPUs, and CPU platforms like Xilinx Zynq™ or NVIDIA^® Jetson or ARM^® processors is challenging because of resource constraints inherent in embedded devices. This talk walks you through a MATLAB^® based deployment workflow that generates C/C++ or CUDA^® or VHDL code.

For system designers looking to integrate deep learning into their FPGA-based applications, the talk helps teach the challenges and considerations for deploying to FPGA hardware, and details the workflow in MATLAB . We will briefly show how to explore and prototype trained networks on FPGAs using prebuilt bistreams from MATLAB. You can further customize your network to meet your performance requirments and hardware resource usage, generate HDL, and integrate it into an FPGA-based edge inference system.

Valerie Leung, MathWorks

Reinforcement learning allows you to solve control problems using deep learning but without using labeled data. Instead, learning occurs through multiple simulations of the system of interest. This simulation data is used to train a policy represented by a deep neural network that would then replace a traditional controller or decision-making system.

In this session, you will learn how to apply reinforcement learning using MATLAB^® and Simulink^® products, including how to set up environment models, define the policy structure, and scale training through parallel computing to improve performance.

Seth DeLand, MathWorks

While many organizations get excited about adopting machine learning techniques, success does not come easy. Come to this talk to learn about applications where machine learning generates considerable ROI, including fleet data analysis, energy forecasting, and smart manufacturing.  We will also demonstrate how engineers are integrating machine learning techniques with their controls and signal processing workflows to improve system performance.

Throughout the presentation we will highlight new features in MATLAB^® that accelerate deploying machine learning. This includes applying automation techniques to feature selection, model selection, and hyperparameter optimization (AutoML). We will also cover new ways for integrating machine learning models with production workflows such as updating deployed models and C/C++ code generation.

Come to this talk to learn how your peers have applied machine learning, and to get inspiration for how machine learning could be applied to your own work.

Marco Dragic, MathWorks
Paul Urban, MathWorks

Developing complex systems with quickly evolving customer requirements presents challenges for development, verification, and compliance with safety standards.

Model-Based Design accelerates agile system development by allowing you to gain early insights into system feasibility and to speed development through simulation, automatic code generation, and continuous testing. With test-driven development, requirements are first captured as test cases that drive the implementation. Model-Based Design provides a framework that supports test-diven development. Bringing together these approaches achieves agility in the system development process. As a result, development teams can better understand customer requirements, quickly respond to changes, identify errors earlier, refactor the design, and deliver working systems faster. We will discuss how you can apply test-driven development by authoring tests that drive system development and implementation in the context of Model-Based Design.

Paul Urban, MathWorks

Systems engineering is a challenging problem, and often the tools used to tackle these challenges do not connect well to the other tools used throughout the design process. MathWorks systems engineering tools combine with MATLAB^® and Simulink^® to create a unified modeling environment, enabling the use of a single platform throughout systems engineering, design, implementation, and verification processes.

In this talk, we present a workflow for systems engineering and architectural modeling with a tight connection to Model-Based Design.

Highlights:

• Building a bridge between early architecture work and downstream design
• Creating architecture models and extending the language through stereotypes and profiles
• Analyzing architectures
• Moving to design and implementation

Adam Sifounakis, MathWorks

How do you manage your code and models as they grow, become more complex, and require multiple people to work on them simultaneously?

This session will introduce some of the software development tools available in MATLAB^® and Simulink^® to better manage your files, track changes, work collaboratively, and write more robust applications. We will also discuss how to automate testing and deploy your tests to continuous integration (CI) systems to ensure your application always works.

Highlights:

• Managing your code and model dependencies using Projects
• Tracking changes and working collaboratively using source control (Git)
• Writing better, robust, and portable code and models
• Creating tests to prove your applications works as expected
• Leveraging CI systems (such as Jenkins) to automate testing and reporting

Jens Lerche, MathWorks

In this session, we will show how industrial systems engineers can use desktop simulation to design and test control logic and predictive algorithms without the need for a physical prototype.

Through automatic generation of C/C++ code and code compliant with the IEC 61131-3 standard, you can accelerate deployment of embedded algorithms onto industrial controllers like PLCs, and stay hardware platform independent.

We show how to leverage simulation models of industrial systems using Model-Based Design to develop control logic and condition monitoring algorithms, automatically generate code for PLCs, and perform real-time testing.

Weiwu Li, MathWorks

As simulation becomes increasingly important across an organization, engineering teams need to share their Simulink^® simulations with adjacent groups, suppliers, and clients.

In this presentation, you will see how to share Simulink simulations as standalone executables and browser-based web apps that can be accessed with unique URLs. In addition, you will see how to deploy your simulations on MATLAB Production Server™ as APIs that can be called from enterprise applications.

Hisham El-Masry, MathWorks

Many organizations use one or more cloud environments for efficiency, scalability, and mobility, especially for the development and deployment of AI models and applications.  Cloud environments can be difficult to set up, maintain, and ultimately use. 

In this talk we show you how to configure and use MATLAB^® in cloud environments, demonstrated with an AI workflow. We will use several cloud environments:

• Your own private cloud environment hosted on-premise
• Public clouds such as AWS or Azure
• The MathWorks Cloud with MATLAB Online™
• A hybrid cloud setup, using two or more of these cloud environments

In each cloud configuration, we will show how MATLAB, MATLAB Parallel Server™, and MATLAB Production Server™ can be used.

Aditya Baru, MathWorks

Many organizations use one or more cloud environments for efficiency, scalability, and mobility, especially for the development and deployment of AI models and applications. Cloud environments can be difficult to set up, maintain, and ultimately use. 

In this talk we show you how to configure and use MATLAB^® in cloud environments, demonstrated with an AI workflow. We will use several cloud environments:

• Your own private cloud environment hosted on-premise

• Public clouds such as AWS or Azure

• The MathWorks Cloud with MATLAB Online™

• A hybrid cloud setup, using two or more of these cloud environments

In each cloud configuration, we will show how MATLAB, MATLAB Parallel Server™, and MATLAB Production Server™ can be used.

Dan Lluch, MathWorks

Industrial IoT [Industry 4.0 in EMEA] has brought the rise of connected devices that stream information and optimize operational behavior over the course of a device’s lifetime. Applying digital twin strategies to IIoT systems refers to the ability to create virtual representations of the operating devices and use those representations to optimize operational behavior.

This presentation covers how to develop and deploy MATLAB^® algorithms and Simulink^® models as digital twin and IoT components on assets, edge devices, or cloud for anomaly detection, predictive maintenance, control optimization, and other applications. It will also cover how digital twin models are an extension of Model-Based Design when considering the overall system design and operation. Using a real hardware system demonstration, the presentation will cover both data-driven and physics-based approaches for digital twin modeling, and show how those models are used in operational applications.

YJ Lim, MathWorks

Autonomous robotics requires knowledge and experience in many engineering domains, including mechanical design, perception, decision making, control design, and embedded systems. This talk explains a complete autonomous robotics workflow that allows an engineer to easily learn and apply the many functional domains of robotics. We will walk through the development of a robot arm pick-and-place application.

Some of the topics that will be covered include:

• Developing kinematic and dynamic models of robots
• Perception algorithm design using deep learning
• Multi-sensor fusion for accurate localization
• Gazebo cosimulation for sensor models and environment simulation
• Path planning with obstacle avoidance

Supervisory logic and control using Stateflow^®

Mihir Acharya, MathWorks

In order for autonomous systems to move within their environment, engineers need to design, simulate, test, and deploy algorithms that perceive the environment, keep track of moving objects, and plan a course of movement for the system itself. This workflow is critical for a wide range of systems including self-driving cars, warehouse robots, and unmanned aerial vehicles (UAVs). In this talk, you will learn how to use MATLAB^® and Simulink^® to develop perception, sensor fusion, localization, multi-object tracking, and motion planning algorithms. Some of the topics that will be covered include:

• Perception algorithm design using deep learning
• Fusing sensor data (cameras, lidar, and radar) to maintain situational awareness
• Mapping the environment and localizing the vehicle using SLAM algorithms
• Path planning with obstacle avoidance
• Path following and control design

Mark Corless, MathWorks

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. In this session, you will learn and how MATLAB® and Simulink® support engineers building automated driving systems with increased levels of automation. You will learn about new features in R2019b and R2020a to:

• Design perception, sensor fusion, planning, and controls subsystems
  
• Test by simulating driving scenarios and sensor models in photorealistic scenes
• Deploy by generating C/C++ code

Abhi Shankar Abhinav, MathWorks

Real-time prototyping and testing can help speed the development of Automated Driver Assistance Systems (ADAS).  This webinar will use a Lane Keeping Assist (LKA) example to demonstrate prototyping and testing workflows with Speedgoat real-time target computers.  The webinar demonstrates workflows for:

• Performing real-time virtual vehicle simulation: Demonstrated in context of a double lane change maneuver and real-time driver in the loop simulator.
• Rapid prototyping and testing of controls:  Rapid prototyping will be demonstrated for the lane keeping controller using model predictive control (MPC). The controller will be tested with a hardware-in-the loop (HIL) system, which models the scenario and virtual vehicle.
• Testing perception and controls: Demonstrated by adding a camera sensor model into the HIL system. The HIL system will be used to test a hardware-accelerated lane detection algorithm with the lane following controller. 

Paul Urban, MathWorks

Production designs that need to comply with industry standards such as ISO 26262 or DO-178C need additional rigor, automation, and insight. Engineers must verify that the design meets requirements, is functionally correct, complies to certification standards, and is correctly implemented. Simulation with Model-Based Design is a key capability to help understand the behavior of complex designs.

This talk discusses verification capabilities of a reference workflow with Model-Based Design to automate manual steps for meeting certification standards. It covers new verification capabilities to support requirements modeling, automated guideline checking, and test. We will show you how to apply these capabilities systematically throughout a production development process to achieve higher quality and productivity.

Bill Potter, MathWorks

Learn how you can use Model-Based Design to develop a flight control system involving software (C code) and an FPGA (HDL code) implemented on an SoC (System on a Chip). We cover development and verification activities required by ARP 4754A, DO-178C, and DO-254 certification standards. System control architecture development and control system design and tuning will also be included.  We will step through system simulation, allocation to software and hardware, as well as automatic code generation for the C and HDL code. Additionally, we show the mapping to the various objectives in the certification standards for the entire Model-Based Design process.

Shang-Chuan Lee, MathWorks

Brushless motors are everywhere. These motors rely on field-oriented control to regulate currents to motor windings. In this session, we will look at some of the challenges and solutions for developing field-oriented control algorithms to achieve the 10-20KHz switching frequency required for efficient and accurate motor operation.

Highlights:

• Approaches for automatically generating fast compact floating-point and fixed-point code from models
• Methods for developing sensorless field-oriented control algorithms
• Approaches for tuning speed and current loop gains
• Techniques to model and parameterize electrical machines for simulation work

Carlos Villegas, MathWorks
Jonathan LeSage, MathWorks

Grid-tied inverters connect renewable energy sources to an electric utility grid. This session will show you how to model, simulate, and implement a controller for a grid-tied solar inverter using Simulink® and Simscape Electrical™.  The demo will use a photovoltaic (PV) inverter to show you how to:

• Build a model to simulate the PV panel, grid load, and grid-tied inverter
• Tune the inverter controller to adjust the DC bus voltage for varying loads
• Develop a maximum power point tracking (MPPT) algorithm to keep the PV system operating at the peak power point under changing solar irradiance, temperature, and load
• Implement plant level control such as fault-ride through, curtailment, and power factor correction
• Generate C code from the controller model and implement it on a Texas Instruments C2000™ microcontroller
• Test the microcontroller code against a real-time hardware-in-the-loop (HIL) simulation of the PV system and inverter using a Speedgoat real-time system

Ruth-Anne Marchant, MathWorks

Learn about new capabilities in the Simulink^® product families to support your research, design, and development workflows. This talk highlights features for physical modelling, algorithm development, team collaboration, and other application areas. You will see a high-level overview of the major capabilities and how you can use Simulink to design, simulate, implement, and test a variety of time-varying systems, including controls, signal processing, physical modelling, and automatic code generation.

Kevin Cohan​, MathWorks
Ed Marquez, MathWorks

Learn about new capabilities in the MATLAB^® and Simulink^® product families to support your research, design, and development workflows. This talk highlights features for deep learning, wireless communications, automated driving, and other application areas. You will see new tools for preprocessing and analyzing data; developing motor control algorithms; creating interactive apps; packaging and sharing simulations; and modeling, simulating, and verifying designs.