AI and Robotics Projects for Engineers

When people ask me where the journey into robotics and AI truly begins, I often point to one of the simplest—and most powerful—learning platforms: an automatic solar tracker. Have you done it before? It may look basic, but it teaches the foundational principles behind intelligent machines: 🔹 Sensors & Perception — Light sensors detect environmental changes, just like cameras, LiDAR, or tactile sensors do in advanced robots. 🔹 Actuation & Motion — Motors adjust panel angles, mirroring how robots manipulate their joints or autonomous vehicles steer. 🔹 Control Systems — Closed-loop feedback algorithms keep the tracker aligned with the sun, exactly the same principle used in drones, robotic arms, and AI-driven automation. 🔹 Optimization & Yield Learning — Solar trackers can boost panel efficiency by 25–35%, a real-world example of how intelligent control drives measurable outcomes. 🔹 Real-Time Decision Making — The system constantly evaluates data and adjusts—fundamental to everything from industrial robots to AI-based simulation environments. From following the sun ☀️ to following patterns, people, and complex environments, this is where intelligent automation begins. What starts as a simple project can grow into advanced robotics, digital twins, full automation systems, and AI-driven decision engines. For many engineers, makers, and students, building a solar tracker is the “aha moment” that opens the door to autonomy, robotics, and applied AI. #Robotics #AI via @learnelectroc #RenewableEnergy #STEM #Automation #SolarEnergy #Innovation #Engineering #FutureTech

🚀 What happens when artificial intelligence starts programming PLCs? We don’t need to imagine it anymore — Beckhoff’s AI CoAgent is already doing it. It’s not just a chatbot. It’s a full AI assistant that understands your automation project: 🧠 Generates TwinCAT PLC code from plain English 🔌 Configures I/O and fieldbus setups 📺 Designs HMI pages from rough sketches 📚 Uses Beckhoff’s internal documentation and your existing project structure 💡 And it’s already used by global leaders: ✅ BMW Group – streamlining PLC coding for production line changes, testing logic, and HMI updates. CoAgent helps engineering teams reduce downtime when switching car models — with automated test sequences and clean documentation. ✅ Oceaneering Mobile Robotics Robotics – programming logic for a fleet of 1,700+ AMRs. Engineers describe scenarios like “two AGVs meet in a narrow corridor” and CoAgent writes the traffic coordination code. It also assists in EtherCAT mapping and diagnostic analysis. ✅ Malisko Engineering, Inc. Engineering (USA) – preserving and scaling expert knowledge as senior engineers retire. CoAgent helps junior engineers create high-quality automation logic faster — accelerating delivery for food, beverage, and pharma clients. ✅ Schirmer Maschinen GmbH Maschinen (Germany) – combining Beckhoff’s IP67 MX-System with CoAgent to build window profile production machines. Engineers use natural language prompts to generate machine logic and HMI — cutting setup time and simplifying commissioning. 📉 Less time programming 📈 Fewer human errors 🧰 More creativity and scalability 💬 All through conversation This is not about AI replacing engineers — it's about engineers becoming 10x more powerful by using AI. 🛠️ The ones who do will lead the future of industrial automation.

Y Combinator’s Spring 2025 batch is out, and the US robotics cohort is particularly compelling. This group isn't just about flashy demos; they're tackling real-world problems with practical solutions. Here are the standouts: Mbodi AI – A game-changer in industrial robotics. Mbodi enables robots to learn new tasks instantly through natural language commands. Their AI platform combines generative models with classical robotics techniques, allowing real-time adaptation in high-mix, low-volume production environments. Their collaboration with ABB Robotics underscores their already impressive impact in making automation more accessible and flexible. SAVA Robotics – Addressing the skilled labor shortage in sheet metal manufacturing, SAVA is developing intelligent robots to operate existing machinery, starting with CNC press brakes. Their plug-and-play solution allows manufacturers to automate without overhauling their current setups. Zeon Systems (YC X25) – Revolutionizing lab work, Zeon offers AI-powered robotics that automates manual tasks in scientific labs. Scientists can describe experiments in plain English, and Zeon's system translates that into code, executing tasks with robotic arms. They're already piloting with labs at Stanford and UCSF. Vassar – Still in deep Stelath mode, so not much information is available, but the name and category suggest work in adaptive or flexible automation. We’ll be watching. The Robot Learning Company (YC X25) – Empowering engineers to build intelligent robot applications regardless of their experience level. By simplifying the development, training, and deployment of AI-powered robot control, they're removing barriers to in-house automation Notus Systems –  Their drones and land swarm robots run autonomous missions as coordinated groups, reducing military response time from minutes to milliseconds. HABIT – Deploying robotic services to neighborhoods, starting with robotic car detailing, OrangeDetail. Their approach combines the speed and convenience of automated services with the meticulous care of professional detailers, aiming to provide on-demand robotic cleaning services that are cost-effective and efficient for all areas. Kaizen – Leveraging browser agents to enable instant integration into websites without APIs. Kaizen allows leading AI companies to read and write data from legacy portals in logistics, healthcare, and financial services, streamlining workflows and enhancing productivity. #Robotics #YCombinator #AI #YC2025

This time on my journey to make cool stuff, I developed an autonomous AI-powered robot! This project explores how deep learning and artificial intelligence are increasingly being applied to robotics, creating models that can not only learn to complete tasks but also fully control a robot to execute them. For this, I constructed two robotic arms: a leader arm and a follower arm. The leader arm was used to teleoperate the follower arm, demonstrating how to pick up a block and place it in a box. All these movements were recorded as data points, which, when combined with footage from a camera monitoring the entire scene, formed the foundation for our AI model. I then trained a specialized neural network called an action chunking transformer using this data. Through training, this network learned how to perform the task and can be applied back to the follower arm to predict and execute the necessary movements autonomously. A huge shoutout to Remi Cadene, Jessica Moss, and the Hugging Face LeRobot team for putting together the guides, robot design, and open source resources together in an approachable and intriguing format. I’m looking forward to further developing my robotics skills alongside my AI expertise! You can see the entire journey from start to finish of creating this robot in my latest video: https://lnkd.in/esu9-ZJd