Pruthvi Geedh

Making Sim2Real smoother for roboticists. [GitHub link in post ⬇️] This minimal toolkit lets you train a reinforcement learning policy in Isaac Lab and deploy it directly on the Kinova Gen3 arm using only ROS 2. No simulation tools needed at runtime. ✅ Train with Isaac Lab using rsl_rl or rl_games ✅ Deploy in the real world using a lightweight ROS 2 setup ✅ Pretrained policies included so you can skip training ✅ Fully open-source and modular for custom tasks and robots ✅ Clean step-by-step guide for both fake and real hardware If you’re tackling Sim2Real, this toolkit makes it easier to go from a trained model to a moving robot, but without the mess. https://lnkd.in/diSAtGEy And thank you, Louis Le Lay, for sharing!

290

6 Comments

Check out our latest work "An MPC framework for efficient navigation of mobile robots in cluttered environments" with Daniel Zhang, Raffaele Soloperto, Andrea Carron, and Melanie Zeilinger: https://lnkd.in/gHCFps6v. We propose an MPC approach that integrates a finite-segment shortest path planner directly into the trajectory optimization. The method guarantees collision avoidance and convergence, even in environments cluttered with obstacles. In hardware experiments, a human operator dynamically set targets, which the robot reached within 2-3 seconds. In fact, it was often faster than we could assign new targets. 🔧 Want to try it yourself? We've open-sourced the code: https://lnkd.in/gYT4Usf8.  You can dynamically select targets with a drag-and-drop interface and the algorithm navigates the robot arounds the obstacles in real time. #PredictiveControl #Robotics #ModelPredictiveControl #AutonomousSystems ICS - Intelligent Control Systems NCCR Automation 

1,831

45 Comments

I made a post last week on how a Robotics roadmap will be mostly useless but at the same time, one of the most common questions I have gotten is on getting started and roadmaps in Robotics. The skills below have been compiled based on 100s of job posts in robotics industry and finding what is common to the vast majority. There is also no order of importance in how they are arranged. While this is not a roadmap or and there is no compulsory starting point, there are certain skills you need to master to become a robotics engineer or work in the industry. You do not need to know all and there is hardly anyone that is proficient in all. You only need a small percentage and maybe a faint idea of some others and ability to also wear multiple hats and learn when situation demands. The simple truth is that you wont stop learning and what you will be learning will be dependent on project(s) you are working on. You just need to pick a domain of what interests you. That is why I have highlighted the skills in color to categorize them. If there is a skill missing, please kindly include in the comment section. These are what I could come up with at first thought. I will be compiling resources and courses on the internet you can use to learn them. If you have any suggestion or you have taken one, please kindly link them in the comment section.

756

22 Comments

A new Open Source Suite to Manage Data from your ROS 2 Robots? I’ve been following Mosaico, an upcoming open-source project led by Gabriele Lini, and I genuinely think it could become a new standard about how we handle data in robotics. Most existing tools weren’t built for robotics so they are not always adapted to robotics constrains and it can be challenging to adapt for our use cases. Mosaico is building the robotics suite we’ve been missing to handle our data. The project will drop on GitHub soon, and I’ll definitely keep you posted. For anyone working with ROS 2 platforms, robots, perception systems… this could be a powerful add-on in your toolkit. 🔗 You can follow their Linkedin page to learn more about the project! How are you managing the data of your Robotics projects? Let's connect and share new Robotics projects 🔽 #ROS2 #Robotics #OpenSource #PhysicalAI

106

19 Comments

Our group at IISc Bangalore will present seven cutting-edge papers at the 2025 IEEE International Reliability Physics Symposium (IRPS) next week in Monterey, CA! I am sharing an overview of these works. If you are attending IRPS, please drop a text.  [1] Advanced SCR-Based ESD Protection Concept: A novel SCR-based protection concept providing ultra-low leakage, reduced latch-up susceptibility, and significantly lower parasitic capacitances—advancing ultra-high-speed I/Os. [2] GaN-on-Si RF HEMT: We have bridged the performance and reliability gap between GaN-on-Si and GaN-on-SiC through a novel and efficient electric field engineering approach, significantly enhancing device reliability, current collapse, and reducing self-heating. [3] Ultimate Tunability in a Novel ESD Protection Device: We report a groundbreaking approach to achieve ultimate holding voltage and trigger voltage tunability, solving a long-standing industry problem. [4] 2D Material Reliability: We will present a new approach to develop insights into the reliability physics of 2D TMDs. [5] Breakdown Mechanisms in GaN HEMTs: We have experimentally validated how back-gating phenomena and buffer-trap dynamics affect breakdown and leakage currents in GaN HEMTs under pulsed operations. [6] Next-Generation β-Ga₂O₃ Devices: Our group reports for the first time and provides first-ever insights into dynamic breakdown behavior of β-Ga₂O₃ devices. [7] Electric Field Dynamics in AlGaN/GaN Structures: Our research validates buffer trap-driven field dynamics controlling breakdown and leakage trends in AlGaN/GaN heterostructures. Looking forward to insightful discussions and collaborations at IRPS. References: [1] M. Goyal, et al., "Novel Trigger Circuit & SCR Device Co-Engineering Based Local (I/O-VSS & I/O-VDD) ESD Clamp Concepts with improved Latch-up Susceptibility, Lower Leakage and Lower Capacitance for Ultra High Speed I/Os", IEEE IRPS, 2025. [2] M. A. Munshi, et al., "Bridging the Performance and Reliability Gap of GaN-on-Si with GaN-on-SiC RF HEMTs by Efficient Electric Field Management Using a Novel p-type Oxide Passivation", IEEE IRPS, 2025. [3] M. Yadav, et al., "Proposal to achieve the ultimate holding voltage tunability in silicon controlled rectifier (SCRs) for a wide range of ESD protection application", IEEE IRPS, 2025. [4] U. Patbhaje, et al., "Small Signal Analysis of Degradation and Breakdown in TMD FETs", IEEE IRPS, 2025. [5] M. A. Munshi, et al., "Evidence of Back-Gating and its Impact on Breakdown in GaN-on-Si HEMTs with Carbon Doped Buffer Under Pulsed Conditions", IEEE IRPS, 2025. [6] H. Raj, et al., "First Observations and Physical Insights of the Dynamic Breakdown Voltage and Overvoltage Margin Under Pulsed Conditions in β-Ga2O3 Based Devices", IEEE IRPS, 2025. [7] R. R. Malik, et al., "Experimental Validation of Buffer Traps-Driven Electric Field Dynamics Governing Breakdown and Leakage Trends in AlGaN/GaN Heterostructures", IEEE IRPS, 2025.

363

8 Comments

CppCon, The C++ Conference 2024 - Aditi Pawaskar: "Leveraging C++ for Efficient Motion Planning: RRT Algorithm for Robotic Arms" youtu.be/CEY4qRLcLmI Motion planning algorithms play a crucial role in enabling robot arm to navigate complex environments efficiently. They are required to determine a robot's trajectory and optimize its motion to minimize cycle time and maximize throughput. In this talk, we delve into optimizing a robotic arm motion planner using the CHOMP algorithm, highlighting the significance of employing good coding practices and design patterns. Beginning with an overview of motion planning techniques and the rationale behind selecting the CHOMP algorithm for robotic arm manipulation, we scrutinize the initial naive code implementation. Transitioning to modern C++ implementation, we introduce key concepts utilized in the refactor and present code snippets illustrating the transformation from legacy to modern paradigms. Attendees will glean insights into identifying and addressing challenges in legacy code, mastering essential modern C++ concepts for motion planning optimization, and quantifying the tangible benefits through performance metric comparisons. It will further encourage them to integrate design patterns into robotics programs. --- Aditi Pawaskar is graduating from Worcester Polytechnic Institute, where she is pursuing her Masters in Robotics. She has her masters thesis on Manipulation of objects using robot arms and soft robotic hands.

12

🤖 Excited to Share: ROS2 Autonomous Navigation Demonstration! 🚀 I'm thrilled to showcase this practical demonstration of ROS2 autonomous navigation that I developed for our M.Sc. Robotics program at the University of West London, School of Computing and Engineering! 🎓 🔧 Technical Highlights: ✅ Mecanum wheels with encoder control for omnidirectional movement ✅ RGBD camera + LiDAR sensor integration ✅ ROS2 Foxy framework (stable version) ✅ RTAB-Map (Real-Time Appearance-Based Mapping) for SLAM 🎯 What's happening in this demo: The robot performs real-time simultaneous localization and mapping (SLAM), accurately estimating its pose, and autonomously navigating to multiple waypoints while maintaining precise orientation control. The loop closure detection ensures map accuracy over time, even in large-scale environments. 💡 Practical Applications: This multi-waypoint navigation capability opens doors for: 📦 Warehouse automation 🚚 Autonomous delivery systems 🏭 Industrial material handling 🏥 Hospital logistics This demonstration showcases the future of autonomous robotics and the hands-on learning experience we provide to our students at UWL! #Robotics #ROS2 #AutonomousNavigation #SLAM #RTABMap #UniversityOfWestLondon #UWL #ArtificialIntelligence #ComputerVision #Engineering #RoboticsEducation #Innovation #Technology #HigherEducation #MSc

28