This paper presents a simulation based control architecture that integrates Webots and Simulink for the development and testing of robotic systems. Using Webots for 3D physics based simulation and Simulink for control system design, real time testing and controller validation are achieved efficiently. The proposed approach aims to reduce hardware in the loop dependency in early development stages, offering a cost effective and modular control framework for academic, industrial, and robotics applications.

This paper proposes a framework for training Reinforcement Learning agents using Python in conjunction with Simulink models. Leveraging Python's superior customization options and popular libraries like Stable Baselines3, we aim to bridge the gap between the established Simulink environment and the flexibility of Python for training bleeding edge agents. Our approach is demonstrated on the Quanser Aero 2, a versatile dual-rotor helicopter. We show that policies trained on Simulink models can be seamlessly transferred to the real system, enabling efficient development and deployment of Reinforcement Learning agents for control tasks. Through systematic integration steps, including C-code generation from Simulink, DLL compilation, and Python interface development, we establish a robust framework for training agents on Simulink models. Experimental results demonstrate the effectiveness of our approach, surpassing previous efforts and highlighting the potential of combining Simulink with Python for Reinforcement Learning research and applications.

The DIVA model is a computational model of speech motor control that combines a simulation of the brain regions responsible for speech production with a model of the human vocal tract. The model is currently implemented in Matlab Simulink; however, this is less than ideal as most of the development in speech technology research is done in Python. This means there is a wealth of machine learning tools which are freely available in the Python ecosystem that cannot be easily integrated with DIVA. We present TorchDIVA, a full rebuild of DIVA in Python using PyTorch tensors. DIVA source code was directly translated from Matlab to Python, and built-in Simulink signal blocks were implemented from scratch. After implementation, the accuracy of each module was evaluated via systematic block-by-block validation. The TorchDIVA model is shown to produce outputs that closely match those of the original DIVA model, with a negligible difference between the two. We additionally present an example of the extensibility of TorchDIVA as a research platform. Speech quality enhancement in TorchDIVA is achieved through an integration with an existing PyTorch generative vocoder called DiffWave. A modified DiffWave mel-spectrum upsampler was trained on human speech waveforms and conditioned on the TorchDIVA speech production. The results indicate improved speech quality metrics in the DiffWave-enhanced output as compared to the baseline. This enhancement would have been difficult or impossible to accomplish in the original Matlab implementation. This proof-of-concept demonstrates the value TorchDIVA will bring to the research community. Researchers can download the new implementation at: https://github.com/skinahan/DIVA_PyTorch

You can accelerate the simulation of your algorithms in Simulink by using different execution environments. By using support packages, you can also generate and deploy C/C and CUDA code on target hardware. Simulate and generate code for deep learning models in Simulink using MATLAB function blocks. Simulate and generate code for deep learning models in Simulink using library blocks. This example shows how to develop a CUDA application from a Simulink model that performs lane and vehicle detection using convolutional neural networks (CNN).

Datasets are essential to AI models. They provide the truth by which we train AI models and measure a model's success. Engineers often look to the AI model as the key to delivering highly accurate results, but in reality it is often the data that determines an AI model success. Data flows through every step of the AI workflow, from model training to deployment, and the way it is prepared can be the main driver of accuracy when designing robust AI models. Engineers can use these five tips to improve their data preparation process and drive success when developing a complete AI system.

Artificial intelligence, or AI, is a simulation of intelligent human behavior. It's a computer or system designed to perceive its environment, understand its behaviors, and take action. Consider self-driving cars: AI-driven systems like these integrate AI algorithms, such as machine learning and deep learning, into complex environments that enable automation. AI is estimated to create $13 trillion in economic value worldwide by 2030, according to a McKinsey forecast. That's because AI is transforming engineering in nearly every industry and application area.

Digital twins are emerging as a hot technology, particularly among manufacturers and companies involved with the Industrial Internet of Things. Depending on the use cases, though, customers may opt for one type of digital twin over another. To a certain extent, every digital twin is a unique creation. The ability to create a digitized copy of an actual physical asset, such as a wind turbine or a locomotive, and measure how that model responds and reacts to different inputs is the fundamental breakthrough that is driving adoption of digital twin technologies. But there are a few broad categories of digital twins, and companies that are considering adopting a digital twin would do well to explore how their use cases match up to these types.

MathWorks has introduced the new Release 2020a with expanded AI capabilities for deep learning. The release introduces an enhanced Deep Learning Toolbox that helps users manage multiple deep learning experiments, keep track of training parameters, analyse and compare results and code with the new Experiment Manager app. It can also interactively train a network for image classification, generate MATLAB code for training, and access pretrained models with Deep Network Designer app. Engineers can now train neural networks in the updated Deep Network Designer app, manage multiple deep learning experiments in a new Experiment Manager app, and choose from more network options to generate deep learning code. R2020a introduces new capabilities specifically for automotive and wireless engineers in addition to hundreds of new and updated features for all users of MATLAB and Simulink.

Additional IP now available from Renesas Electronics includes a 7nm process ternary content addressable memory (TCAM) and standard Ethernet time sensitive networking (TSN) IP. Customers will have access to IPs such as advanced 7nm (nanometer) SRAM and TCAM, and leading-edge standard Ethernet time-sensitive networking (TSN) IP, says the company, which is also working on providing a system IP which includes processing in memory (PIM) for use as an artificial intelligence (AI) accelerator. Customers can use these IPs to jump start semiconductor device development projects, such as the development of next-generation AI chips or ASICs for 5G networks. Customers developing custom chips can leverage the IP in the subsystem, or those using FPGA devices can use it to speed up software development while they focus resources on specialty areas to reduce development time. Customers who prefer to use existing software assets can take advantage of Renesas IP assets to achieve more efficient system development by reducing the resources required to develop, verify and evaluate software and boards.

In the next chapter event, we will be exploring How IoT, video data and machine learning can improve predictive models AKA'The Rise of Engineering Driven Data Analytics'. Audio, image, video, and other sensor-generated data is being combined with traditional business and transactional data to create opportunities for sophisticated analytics on more complex phenomena. Our guest speaker, Boris Savkovic, Lead Data Scientist, BuildingIQ will present on'The rise of IoT data analytics and machine learning in the smart building of tomorrow' Large-scale buildings (skyscrapers, hospitals, shopping centres etc.) account for approximately 40% of global energy consumption, with a large proportion of this energy consumed by heating, ventilation and cooling (HVAC) systems that regulate comfort and internal conditions/temperatures in a building. The business challenges in terms of the resulting energy costs and associated greenhouse gas emissions are substantial. However, these challenges also provide opportunities for innovative companies who can provide services and solutions that address these challenges, driving value for building owners while at the same time helping reduce global greenhouse gas emissions in a post-Paris agreement world.