From Embedded to Empowered: The Rise of Software-Defined Product
In automotive, it’s called a “software-defined vehicle.” But the move toward software-defined products is also happening in aerospace, industrial systems, medical devices, and other industries. Until now, most customer-visible capabilities in products have been implemented as mechanical and electronic subsystems, with certain critical operational functions implemented using embedded software. As a result, much of the functionality has been set at production.
Going forward, the features that represent brand-distinctive attributes and customer-perceived value will be defined through software, providing the ability to generate new value throughout the lifespan of the system. This transformation to “software-defined” requires changes in development processes, new synergies between teams, and new ways to leverage products like MATLAB® and Simulink®. In this talk, discover key approaches to capturing the value while mitigating the risks associated with the disruptive changes.
Modeling and Simulation in Robotics & Automation for Manufacturing
Accelerating Software Development, Verification and CI/CD Integration
Model-Based Design Empowers Virtual Simulation and Testing
Model-Based Systems Engineering (MBSE) represents an evolution of traditional Systems Engineering by embedding modeling as a core methodology throughout the entire lifecycle of engineered systems. Systems Engineering itself is a transdisciplinary and integrative approach aimed at ensuring the successful realization, use, and retirement of complex systems through the application of scientific, technological, and management principles. Building upon this foundation, MBSE formalizes the use of models to support critical activities such as requirements definition, system design, performance analysis, verification, and validation.
By shifting from document-based processes to model-driven practices, MBSE enables engineers to create a single source of truth that integrates different disciplines and stakeholders. This provides the ability to perform virtual simulation and testing early in the conceptual design phase and to continuously refine the system throughout development and later life cycle stages. As a result, MBSE improves collaboration, reduces design risks, shortens development cycles, and accelerates innovation by allowing organizations to explore alternatives, detect issues earlier, and validate decisions in a virtual environment before physical implementation.
Autonomous Concrete Finishing Robot: From Simulation to Deployment
Intelligent mobile robotics is transforming industrial automation by enabling flexible, adaptive, and software-defined factories. With MathWorks tools such as MATLAB® and Simulink®, engineers can design, simulate, and deploy advanced robotics algorithms including perception, navigation, control, and coordination. Model-Based Design accelerates development by providing a unified workflow from system-level simulation to real-time deployment on embedded hardware. This approach supports rapid prototyping, integration with industrial systems, and continuous software updates, empowering factories to achieve higher efficiency, safety, and adaptability in dynamic production environments.
.png?width=200&height=200&name=Benjamin%20Ma%20(1).png)
Automated Visual Inspection with Deep Learning for Quality Assurance
Automated visual inspection with deep learning is transforming quality assurance in modern software-driven factories. Using MathWorks tools, engineers can develop, train, and deploy deep learning models for defect detection, classification, and anomaly recognition directly from production data. The integrated workflow—from data preparation and model training in MATLAB® to real-time deployment on embedded and edge devices—enables scalable, reliable, and cost-effective inspection systems. This approach accelerates defect detection, reduces manual inspection effort, and ensures consistent product quality, supporting the vision of intelligent, software-defined factories.
.png?width=200&height=200&name=Gerald%20(1).png)
Battery Energy Storage Systems: Modeling to System Integration
.png?width=200&height=200&name=Jihan%20(1).png)
AI for Electrification: Smart Control and Optimization
Electrification is transforming industries from automotive to energy systems, demanding smarter, more efficient, and scalable control strategies. Artificial Intelligence (AI), combined with Model-Based Design (MBD), enables the development of intelligent control and optimization algorithms that can adapt to dynamic operating conditions and maximize system performance. With MathWorks tools, engineers can accelerate this transition through data-driven modeling, reinforcement learning, and automated code generation for real-time deployment. This session will highlight how AI-powered workflows for electrification can be integrated into software factories, streamlining the design-to-deployment pipeline while ensuring quality, scalability, and traceability across electrified products.
Accelerating Electrification Workflows with Hardware-in-the-Loop Testing
Electrification is driving rapid innovation across industries, from automotive to energy systems. This talk highlights how engineers and researchers can leverage real-time testing and hardware-in-the-loop (HIL) workflows with Speedgoat to prototype, validate, and deploy electrification technologies with confidence. Real-world use cases will showcase how to accelerate development, reduce risk, and bridge the gap between simulation and implementation
Accurate Load Forecasting: Modeling and Predictive Analytics with MATLAB
.png?width=200&height=200&name=Douglas%20(1).png)
Accelerating Radar and Satellite Communication System Design with MATLAB
- - Importance of integrated radar & satellite communication system
- - Scenario Modeling includes asset trajectories, orbits & visualization
- - Link Budget Analysis & Performance Evaluation
- - Joint Radar/Satcom use cases & rapid prototyping
RF and Wireless System Prototyping on FPGA and SoC
.png?width=200&height=200&name=JonathanTEE%20(2).png)
Modeling the Full Transceiver Chain: MATLAB Workflows for Antenna to Digital Bits
- - End-to-end transceiver chain development workflow
- - Design methods and tools for antenna elements and arrays
- - Baseband components for receiving algorithm development and optimization
- - RF front end design and architectural exploration
AI-Augmented Wireless Communication Systems
Whether you use machine learning, deep learning, or reinforcement learning workflows, you can reduce development time with ready-to-use algorithms and data generated with MATLAB ® and wireless communications products. You can easily leverage existing deep learning networks outside MATLAB; streamline training, testing, and verification of your designs; and simplify deployment of your AI networks on embedded devices, enterprise systems, and the cloud. With MATLAB, you can:
- - Generate training data in the form of synthetic and over-the-air signals using the Wireless Waveform Generator app
- - Augment signal space by adding RF impairments and channel models to your generated signals
- - Label signals collected from wireless systems using the Signal Labeller app
- - Apply reusable and streamlined training, simulation, and testing workflows to various wireless applications using the Deep Network Designer and Experiment Manager apps
- - Add custom layers to your deep learning designs