Engineering Simulation Tools Overview

Researchers at Hong Kong University MaRS Lab have just published another jaw dropping paper featuring their safety-assured high-speed aerial robot path planning system dubbed "SUPER". With a single MID360 lidar sensor they repeatedly achieved autonomous one-shot navigation at speeds exceeding 20m/s in obstacle rich environments. Since it only requires a single lidar these vehicles can be built with a small footprint and navigate completely independent of light, GPS and radio link. This is not just #SLAM on a #drone, in fact the SUPER system continuously computes two trajectories in each re-planning cycle—a high-speed exploratory trajectory and a conservative backup trajectory. The exploratory trajectory is designed to maximize speed by considering both known free spaces and unknown areas, allowing the drone to fly aggressively and efficiently toward its goal. In contrast, the backup trajectory is entirely confined within the known free spaces identified by the point-cloud map, ensuring that if unforeseen obstacles are encountered or if the system’s perception becomes uncertain, the system can safely switch to a precomputed, collision-free path. The direct use of LIDAR point clouds for mapping eliminates the need for time-consuming occupancy grid updates and complex data fusion algorithms. Combined with an efficient dual-trajectory planning framework, this leads to significant reductions in computation time—often an order of magnitude faster than comparable SLAM-based systems—allowing the MAV to operate at higher speeds without sacrificing safety. This two-pronged planning strategy is particularly innovative because it directly addresses the classic speed-safety trade-off in autonomous navigation. By planning an exploratory trajectory that pushes the speed envelope and a backup trajectory that guarantees safety, SUPER can achieve high-speed flight (demonstrated speeds exceeding 20 meters per second) without compromising on collision avoidance. If you've been tracking the progress of autonomy in aerial robotics and matching it to the winning strategies emerging in Ukraine, it's clear we're likely to experience another ChatGPT moment in this domain, very soon. #LiDAR scanners will continue to get smaller and cheaper, solid state VSCEL based sensors are rapidly improving and it is conceivable that vehicles with this capability can be built and deployed with a bill of materials below $1000. Link to the paper in the comments below.

Very glad to share our latest work -- first paper in LES of offshore wind farms -- on "Evaluation of Six Subgrid-Scale Models for LES of Wind Farms in Stable and Conventionally-Neutral Atmospheric Stratification" https://lnkd.in/dwMBS_am. As far as we know, it is the first time such a comprehensive comparison of 6 sgs models has been done within a single LES code, looking at wind farm wakes. The key goal is to investigate how these perform in stable thermal stratification as we know wind farm wakes extend the longest under such conditions. In addition, how sensitive is the sgs model to the grid size, i.e. can we obtain a good solution of the flow physics at a relatively coarse grid? Details are on the preprint but we've seen the Anisotropic Minimum-Dissipation model is working best. Excellent work led by a brillian PhD student Mina Naem co-supevised with Tim Stallard and David Schultz. LES ran on #ARCHER2 thanks to #UKTC support. EPSRC, Supergen Offshore Renewable Energy (ORE) Hub

🗺️𝗧𝗵𝗶𝘀 𝗶𝘀 𝘄𝗵𝘆 𝗶𝘁'𝘀 𝗰𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝘁𝗼 𝗯𝗲 𝗮𝗯𝗹𝗲 𝘁𝗼 𝗲𝗮𝘀𝗶𝗹𝘆 𝘀𝘄𝗶𝘁𝗰𝗵 𝘄𝗶𝗻𝗱 𝗳𝗹𝗼𝘄 𝗺𝗼𝗱𝗲𝗹𝘀.🗺️ WAsP? CFD? VORTEX? GWA? Mesoscale? Downscaled? Ensembled? Calibrated? It is never true that one wind flow model is "right" and all others are "wrong". 𝗔𝗹𝗹 𝘄𝗶𝗻𝗱 𝗺𝗮𝗽𝘀 𝗮𝗿𝗲 𝗷𝘂𝘀𝘁 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝗱𝗲𝗴𝗿𝗲𝗲𝘀 𝗼𝗳 𝘄𝗿𝗼𝗻𝗴 𝗶𝗻 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝗽𝗹𝗮𝗰𝗲𝘀. It's your job as a wind engineer to interpret the opinions they provide. There's a 𝗿𝗶𝗴𝗵𝘁 𝘁𝗶𝗺𝗲 and a 𝘄𝗿𝗼𝗻𝗴 𝘁𝗶𝗺𝗲 to decide which modelling approach is "best" ("least terrible"). • ❌𝗧𝗵𝗲 𝘄𝗿𝗼𝗻𝗴 𝘁𝗶𝗺𝗲?❌ Before you've looked at the results of each model. • ✅𝗧𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝘁𝗶𝗺𝗲?✅ After you've calculated the yield from each model.  ℹ️Here are Wind Pioneers top tips for how you should go about selecting a wind flow model(s)ℹ️ 1. 𝗥𝘂𝗻 𝗮𝗹𝗹 𝘆𝗼𝘂𝗿 𝗹𝗮𝘆𝗼𝘂𝘁𝘀/configurations using each wind flow model 2. 𝗖𝗼𝗺𝗽𝗮𝗿𝗲 𝘁𝗵𝗲 𝗼𝘃𝗲𝗿𝗮𝗹𝗹 𝗻𝗲𝘁 𝘆𝗶𝗲𝗹𝗱 of the wind farm with the different models to understand how consequential your choice is. 3. 𝗜𝗱𝗲𝗻𝘁𝗶𝗳𝘆 𝗶𝗻𝗱𝗶𝘃𝗶𝗱𝘂𝗮𝗹 𝗪𝗧𝗚𝘀 where the choice of model is having the biggest impact on yield. 4. 𝗔𝘀𝗸 𝘆𝗼𝘂𝗿𝘀𝗲𝗹𝗳 𝘄𝗵𝘆. Is it because one model handles complex terrain differently? Is one model picking up mesoscale effects that another isn't? Has one model been overfitted to measurements? Has your CFD failed to converge? 5. 𝗔𝘀𝗸 𝘆𝗼𝘂𝗿𝘀𝗲𝗹𝗳 𝗵𝗼𝘄 𝘁𝗼 𝘀𝗼𝗹𝘃𝗲 𝗼𝗻𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗮𝗻𝗼𝘁𝗵𝗲𝗿. Can you calibrate the maps to the measurements differently? Can you downscale a microscale model from a mesosacle model? Can you blend maps? 𝟲. 𝗖𝗼𝗻𝘀𝗶𝗱𝗲𝗿 𝘁𝗵𝗲 𝗳𝘂𝘁𝘂𝗿𝗲. Do your results need to align with what an independent yield consultant will produce in a few months? Will new measurements change your decision? Is your choice of wind map something you might regret later? (E.g. undervaluing an area of the site) 𝟳. 𝗥𝗲𝗽𝗲𝗮𝘁 𝘁𝗵𝗲 𝗽𝗿𝗼𝗰𝗲𝘀𝘀. Whenever there's a significant change to the layouts or available measurements. Lastly, remember one key point: ❗𝘂𝗻𝗹𝗲𝘀𝘀 𝘆𝗼𝘂 𝗵𝗮𝘃𝗲 𝗽𝗿𝗲𝗰𝗶𝘀𝗲𝗹𝘆 𝗺𝗲𝗮𝘀𝘂𝗿𝗲𝗱 𝗮 𝗹𝗼𝗰𝗮𝘁𝗶𝗼𝗻 𝘆𝗼𝘂 𝗵𝗮𝘃𝗲 𝗻𝗼 𝘄𝗮𝘆 𝘁𝗼 𝗸𝗻𝗼𝘄 𝘄𝗵𝗶𝗰𝗵 𝘄𝗶𝗻𝗱 𝗺𝗮𝗽 𝗶𝘀 𝗺𝗼𝘀𝘁 𝗮𝗰𝗰𝘂𝗿𝗮𝘁𝗲 𝘁𝗵𝗲𝗿𝗲❗Cross-verification between two measurement locations does not guarantee extrapolative accuracy to dozens of WTG locations. If you need advice on wind modelling approaches for your site - come talk to us!

Today's a great day! I just completed my experiment on Performance Assessment of Micro Wind Energy Generator! This project was a thrilling journey of understanding the efficiency and potential of micro wind turbines in generating renewable energy. To create an experiment on the *performance assessment of a micro wind energy generator* using Simulink, we can follow a simple step-by-step guide to model the system. Below is an overview of the basic components needed in Simulink and how they are structured for performance assessment: *Understanding the System:* A *micro wind energy generator* typically consists of a wind turbine, a generator (like a Permanent Magnet Synchronous Generator - PMSG), and a load or grid connection. We will assess the system’s performance by measuring the power generated under different wind speeds. *Components in Simulink:* - *Wind Turbine Block:* This simulates the mechanical power generated from wind. It depends on wind speed, air density, rotor area, and the turbine’s power coefficient. - *Generator Block (PMSG):* Converts the mechanical power to electrical power. This can be modeled using a Permanent Magnet Synchronous Generator. - *Controller Block :* If you want to control the turbine’s speed or power output. - *Load/Scope:* To measure the electrical output (voltage, current, power). The Model Generator - Use a *Permanent Magnet Synchronous Generator (PMSG)* block to simulate the electrical generation from the mechanical torque input from the wind turbine. - The mechanical input (torque and speed) comes from the turbine, and the electrical output is connected to the load. *Simulating the System:* - After building the model, run simulations at different wind speeds (for example, 5 m/s, 10 m/s, and 15 m/s) to observe how the power output changes. - Compare the electrical power output at various speeds and observe the system's efficiency. This simple model gives insight into the performance of a micro wind energy generator and helps analyze key metrics like power output and system efficiency under varying conditions. #MicroWindEnergy #RenewableEnergy #ExperimentComplete #InnovationJourney

𝗛𝗨𝗠𝗔𝗡𝗢𝗜𝗗 𝗥𝗢𝗕𝗢𝗧𝗜𝗖𝗦: 𝗪𝗵𝗲𝗿𝗲 𝗦𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 𝗕𝗲𝗴𝗶𝗻𝘀 𝗮𝗻𝗱 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗔𝘄𝗮𝗸𝗲𝗻𝘀 Deep Learning in 3D Simulation is not a lab exercise. It is the moment we begin to teach machines how to exist. Not to repeat motions. Not to merely follow code. But to learn, adapt, balance, reason, and act with purpose. In my project we are not just building robots. We are building a new class of intelligence that experiences the world before it ever touches reality. In these simulation environments, gravity does not remain constant. Terrain does not always cooperate. Obstacles change shape. Sensors lie. Friction shifts. And the humanoid must still stand, walk, grasp, adjust, optimize, and choose its next step. Domain randomization, reinforcement learning, hierarchical policies, and graph neural dependencies no longer sound like academic theory. They become survival tools. Machines begin to develop strategies. They learn how to carry payloads across unstable rubble. They learn energy discipline when battery is low and temperature is high. They learn trajectory planning not as geometry, but as survival logic. When you combine photorealistic environments from Isaac Sim, contact-perfect physics in MuJoCo, embodied navigation in Habitat, and emergent behavior in Unity, you begin to see something different. You see machines build experience. You see memory. You see policy retention. You see adaptation. You see the beginning of abstract perception where simulation is not just testing, but education. The difference between teaching a robot how to walk, and letting it discover how to navigate a collapsing environment with intelligence and intent. This is where humanoid robotics becomes human oriented. Robots that can open doors without templates. Carry supplies without pre-programmed routes. Coordinate convoys. Assist in evacuation. Make real time physical decisions aligned with mission objectives, not static instructions. Simulation gives us time compression. We can give a single humanoid what would have taken humans years of trial. We can compress thousands of failures into one informed policy. This is how we transform capability. Not automation. Cognitive autonomy. Not motion planning. Motion intelligence. Not digital twins. Learning twins. We are building humanoids that do not just survive the environment. They learn from it. If you are in advanced simulation, deep learning pipelines, physics engines, reinforcement learning, biomechanics, embodied cognition, ROS2, Isaac Sim, MuJoCo, Omniverse, Habitat, Unity, Unreal, LLM integration, perception or policy optimization… Then we should not be working apart. We should be building this together. And for those ready to build the next generation of thinking humanoids Singularity Systems is now accepting collaborators, researchers, engineers, architects, and visionaries. Let’s teach machines how to exist. #changetheworld #3D #unity

🚁🏘️🤖📍 I share this paper about a Hardware-in-the-Loop (#HiL) simulation framework 🎛️ for Unmanned Aerial Vehicles (#UAV) to validate 🎯 the simulation models and the performance of #autonomous algorithms 🗺️ under realistic #flight conditions 🌧️. With #digitaltwins 🎨⏱️ in #Simcenter #Amesim and #Simcenter #Prescan (combined). 📰 https://lnkd.in/e-jYB9Wv 🔎 Some extracts: “A real-time simulation of both manual and autonomous flights is completed by coupling the modelled aircraft subsystems and sensors in Simcenter Amesim and Simcenter Prescan with a Pixhawk flight controller.” “Sensor information (position, acceleration and GPS location) coming from the Amesim model, are fed to the flight controller which computes the necessary motor throttle to navigate the UAV according to the desired trajectory.” “The manual flight takes place in the Toulouse environment where a flight path was flown and recorded.” “The autonomous flight simulation was performed in a section of the City of London.” ✔️ Some outcomes: “The simulation with light rain corresponds quite accurately with the ground truth (excluding the corners and the back-and-forth movement in the first stretch).” “The setup shows great promise as an initial step towards safely testing localization algorithms and flight controllers in various scenarios and conditions.” “Successfully operating a real flight controller in a simulated environment is a significant achievement.” 🔗 It’s always nice to see synergies between Siemens products to go some steps further in the analysis. The research presented in this paper has been supported by the MARLOC research project and has received funding from the Flemish government through the VLAIO ICON Program. #Simcenter #SystemSimulation #Amesim #Prescan #drone #quadcopter #aerospace #uam #uav #flightmissions #dronedelivery #autonomoussystems #controls #realtime #cosimulation #flightcontroller #vSLAM #digitaltwin #EngineerInnovation

🚁 What if drones could think? Not pre-programmed — but react live to their surroundings. This week, I explored that exact question — not in theory, but in code. 🧠 My self-learning journey is focused on agentic AI workflows: how can autonomous agents ingest live data, reason about the world, and act in real time? So I set out to simulate it. Using Kafka, Zookeeper, OpenAI, and Docker, I used ai to build a minimal system that lets an AI agent take control — moment by moment. 🎮 The experiment: I created a real-time game where a drone dodges falling obstacles. Instead of writing the rules myself, I stream the live game state into an AI agent — and let it decide what the drone should do next. 📡 The agent reads: The drone’s position The location and size of every falling object A pre-processed danger zone Then chooses: "left", "right", or "stay" — every 500ms. 🧱 The architecture (see image): Zookeeper → Keeps Kafka's coordination intact Kafka → Streams telemetry data in real time Backend → Exposes API endpoints for state + decisions Frontend → A browser-based canvas simulating the drone Agent → Uses OpenAI to analyze the stream and return actions Everything is Dockerized. One command launches the entire swarm. 🎯 Why does this matter? Because real drones fly through uncertain environments. They’ll need to react — not just follow rules. This setup is my stepping stone toward: Swarm AI control Agent-based FPV drones Adaptive automation in physical systems And I’m documenting every bit. — 🛠️ Built in ~24 hours 📸 Image shows my full-stack agent infrastructure 🧠 Goal: Learn how autonomous feedback loops actually run — 📰 I write about this journey — AI, drones, 3D printing, and how it all connects: 👉 https://lnkd.in/gzUhhVjj #AI #Drones #Kafka #Zookeeper #OpenAI #AgenticWorkflows #RealTimeAI #EdgeAI #Docker #LLMops #AutonomousSystems #STEM #FlightClub #OpenSource #DevInfra

Release of Genesis represents something extraordinary. After diving deep into the research paper, I want to share why this isn't just another AI tool - it's potentially the bridge to making personal robots a reality. What is Genesis?  Imagine having a "virtual universe" where robots can practice tasks millions of times in minutes, learning from each experience, all before attempting anything in the real world. That's Genesis - but it's even more fascinating than that. 🔄 The Traditional vs Genesis Approach Let me share a simple example that blew my mind: Teaching a robot to pour water traditionally: - Program every movement manually - Test with real water (risking robot damage) - Repeat thousands of times - Limited to specific cups and situations learned With Genesis: Simply tell it: "Pour water from a pitcher into a cup without spilling" Genesis automatically: - Tests different cup sizes and shapes - Varies water amounts and conditions - Adjusts for different surfaces - Completes millions of practice runs in hours And here's the kicker - it runs 430,000 times faster than real-time! What would take a year to learn traditionally can be learned in 45 seconds. 🤯 🎮 Four Game-Changing Components: 1. Universal Physics Engine - Simulates at 43 million frames per second - 430,000x faster than real-time operation - Accurate physics for multiple material types in one simulation 2. Ultra-Fast Robotics Platform - Processes 1 year of training in 45 seconds - Enables parallel testing of thousands of scenarios 3. Photo-Realistic Rendering - Real-time physics-based rendering - Accurate material and lighting simulation 4. Natural Language Understanding - Converts plain English to robot commands - Handles complex multi-step instructions 💡 Why This Matters: Think about how we currently develop robots - it's like teaching someone to swim without water. Genesis changes this by creating a perfect practice environment where: - Engineers can test wild ideas without physical prototyping - Robots can learn complex tasks through millions of attempts 🌍 Beyond Robotics - Universal Applications: Genesis isn't just for robotics - it's transforming multiple fields: - Healthcare: Medical robots practicing surgical procedures millions of times before touching a patient - Architecture: Building design and structural analysis - Entertainment: Physics-accurate animations and VR - Education: Interactive learning environments - Manufacturing: Manufacturing robots reconfiguring for new tasks through simple instructions 🔮 Future Vision: Imagine describing a task to your home robot in plain language, and it understanding exactly what to do because it's already practiced similar scenarios millions of times in simulation. That future just got much closer. #AI #Robotics #Innovation #TechnologyInnovation #FutureOfWork #ArtificialIntelligence #RoboticAutomation

Big shift in robotics: NVIDIA just open-sourced Isaac Sim and Isaac Lab. Isaac Sim has already been a cornerstone for high-fidelity robotics simulation—RTX-accelerated physics, realistic lidar/camera simulation, domain randomization, ROS/URDF support, and synthetic data pipelines. Now, it’s all on GitHub with full source access. But the real multiplier? The release of Isaac Lab—a modular, open reinforcement learning and robot control framework built directly on top of Isaac Sim. It comes with ready-to-use robots (Franka, UR5, ANYmal), training loops, and environments for manipulation, locomotion, and more. What’s different now: *You’re no longer limited to APIs—developers can modify physics, sensors, and control logic at the source level. *Isaac Lab provides a training-ready foundation for sim-to-real robotics, speeding up learning pipelines dramatically. *Debugging, benchmarking, and custom integrations are now transparent, flexible, and community-driven. *Collaboration across research and industry just got easier—with reproducible environments, tasks, and results. We’ve used Isaac Sim extensively, and this open-source release is going to accelerate innovation across the robotics community. GitHub: https://lnkd.in/gcyP9F4H