Advancing Robotics Technology

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down: 1. We use Apple Vision Pro (yes!!) to give the human operator first person control of the humanoid. Vision Pro parses human hand pose and retargets the motion to the robot hand, all in real time. From the human’s point of view, they are immersed in another body like the Avatar. Teleoperation is slow and time-consuming, but we can afford to collect a small amount of data.  2. We use RoboCasa, a generative simulation framework, to multiply the demonstration data by varying the visual appearance and layout of the environment. In Jensen’s keynote video below, the humanoid is now placing the cup in hundreds of kitchens with a huge diversity of textures, furniture, and object placement. We only have 1 physical kitchen at the GEAR Lab in NVIDIA HQ, but we can conjure up infinite ones in simulation. 3. Finally, we apply MimicGen, a technique to multiply the above data even more by varying the *motion* of the robot. MimicGen generates vast number of new action trajectories based on the original human data, and filters out failed ones (e.g. those that drop the cup) to form a much larger dataset. To sum up, given 1 human trajectory with Vision Pro  -> RoboCasa produces N (varying visuals)  -> MimicGen further augments to NxM (varying motions). This is the way to trade compute for expensive human data by GPU-accelerated simulation. A while ago, I mentioned that teleoperation is fundamentally not scalable, because we are always limited by 24 hrs/robot/day in the world of atoms. Our new GR00T synthetic data pipeline breaks this barrier in the world of bits. Scaling has been so much fun for LLMs, and it's finally our turn to have fun in robotics! We are creating tools to enable everyone in the ecosystem to scale up with us: - RoboCasa: our generative simulation framework (Yuke Zhu). It's fully open-source! Here you go: http://robocasa.ai - MimicGen: our generative action framework (Ajay Mandlekar). The code is open-source for robot arms, but we will have another version for humanoid and 5-finger hands: https://lnkd.in/gsRArQXy - We are building a state-of-the-art Apple Vision Pro -> humanoid robot "Avatar" stack. Xiaolong Wang group’s open-source libraries laid the foundation: https://lnkd.in/gUYye7yt - Watch Jensen's keynote yesterday. He cannot hide his excitement about Project GR00T and robot foundation models! https://lnkd.in/g3hZteCG Finally, GEAR lab is hiring! We want the best roboticists in the world to join us on this moon-landing mission to solve physical AGI: https://lnkd.in/gTancpNK

Most robotics startups don’t die from bad ideas. They die in the wrong city. 📸 That's why you should move to Zurich if you are building such a company Indeed, Silicon Valley is great for software. Robotics plays by different rules: 1️⃣ You need the right talent People who understand mechanics, electronics, manufacturing, software, and AI. Able to integrate them end to end. 2️⃣ You need new ideas New research publications. Cutting-edge approaches. Experimental testing spaces. 3️⃣ You need real-world validation Factories, customers, and partners who stress-test the tech early. No lab-only assumptions. 4️⃣ You need patient capital Because robotics doesn’t move in straight lines. 5️⃣ You need startup founders helping each other Like in SF. Shared context. Shared pain. Shared shortcuts. Zurich covers almost all of this: 1️⃣ ETH Zürich supplies a constant stream of talents 2️⃣ ETH labs, Disney Research, and RAI Institute keep ideas circulating 3️⃣ Industrial players provide early customers and validation 4️⃣ Many deep-tech investors and grant opportunities are designed here for long B2B cycles and hardware risk. That’s why Zurich works well, with many robotics startups (look at the map or the list below). What’s missing? 5️⃣ A stronger startup culture where founders actively support each other. At Forgis, we want to help build that. That's why we’re opening our Schlieren office on weekends for founders and future founders to work together. Comment "ecosystem" to get access. ANYbotics, Gravis Robotics, Verity, mimic, Bota Systems AG, Duatic, RIVR, Flexion Robotics, Voliro, Sevensense, Tethys Robotics, Embotech, Ascento, Wingtra, Auterion, Loki Robotics, Nautica Technologies, Bubble Robotics, Cerrion and student initiatives such as ETH Robotics Club

China is turning fire trucks into drone launch systems. And that is a much bigger shift than it sounds. What interests me here is not just the hardware. It is the new logic of emergency response. Instead of relying only on ladders and human entry, these systems pair fire trucks with drones that can reach high-rise fire zones quickly, fly into smoke, and send live intelligence back to crews. That is what is new. The truck is no longer just transport. It becomes a mobile aerial response base. And that matters because in dense high-rise environments, access is often the real bottleneck. To me, this is where the story gets interesting. This is not just about fighting fires better. It is about changing who gets exposed to danger first. → drones go where ladders cannot → commanders get visibility earlier → crews make faster decisions → fewer firefighters enter blind conditions That is a serious innovation. And it opens up important use cases: → faster high-rise reconnaissance → targeted suppression from outside upper floors → better coordination in smoke-heavy environments → safer response where humans cannot reach quickly That is why I would not dismiss this as just another drone demo. It is a glimpse of what emergency response looks like when robotics, data, and frontline operations finally converge. What do you think matters more here: faster firefighting, or the fact that robots may now take the first risk instead of humans? #AI #Robotics #Drones #Firefighting #Innovation #EmergencyResponse #SmartCities #FutureOfWork #Technology

The timeline for humanoid robots to work completely independently without human assistance depends on advancements in AI, robotics, and sensory technologies. When do you think that would be possible? Here are the key considerations: 1. Current Capabilities Humanoid robots like Boston Dynamics' Atlas, Tesla's Optimus, and Hanson Robotics' Sophia can perform tasks such as walking, object manipulation, and basic communication. However, these tasks often rely on pre-programmed behaviors or limited autonomy. Atlas excels in dynamic movement but lacks decision-making for complex, real-world tasks. Optimus is designed for simple repetitive tasks in controlled environments. Sophia can hold conversations but lacks physical versatility and decision-making independence. 2. Challenges to Autonomy AI Complexity: Generalized intelligence capable of independent reasoning and decision-making remains a significant challenge. Current AI excels in narrow tasks but struggles with adaptability and creativity. Robust Sensing and Perception: While robots can use sensors like cameras and LiDAR, understanding dynamic, cluttered environments with human-level precision is difficult. Energy Efficiency: Robots need better battery technology to function independently for extended periods. Social and Ethical Barriers: Society must address ethical concerns, liability, and regulations for fully autonomous robots in public or professional spaces. 3. Predictions for the Future Experts estimate different timelines depending on the level of autonomy: 2025–2035: Humanoids might perform repetitive or structured tasks (e.g., manufacturing, logistics) with limited supervision. 2040–2050: Robots may handle unstructured, complex environments like caregiving, construction, or public service without significant human intervention. Beyond 2050: Full autonomy across diverse tasks and environments could be possible, potentially rivaling or exceeding human abilities. Current Research and Developments Google DeepMind and OpenAI are advancing general AI capabilities. Companies like Boston Dynamics are improving robot agility and adaptability. Researchers focus on integrating AI with physical robots for real-world applications, such as robotic exoskeletons and disaster recovery #Ai #Innovation #Technology

Reindustrializing #Europe in the age of AI 🤖”—our latest report outlines what it will take: Amid intensifying global competition in AI and #Robotics, Europe faces a defining moment: reindustrialize or risk falling irreversibly behind. Robotics can help restore industrial sovereignty, address demographic headwinds, and boost productivity. We propose a 5-point strategic roadmap to reposition Europe as a credible competitor alongside the US and China: 1️⃣ A European Robotics Roadmap – Focus on building champions in high-impact, under-robotized sectors: logistics, hospitality, agrifood, healthcare, aerospace, and defense. Prioritize strategic autonomy, not chasing lost ground in humanoids or autonomous vehicles. 2️⃣ Capital Access for Robotics Startups – Address the 7x VC funding gap with the US by scaling Europe’s venture capital market and reinforcing complementary funding streams. 3️⃣ Bridging Innovation and Market – Tackle fragmentation through innovation clusters, regional champions, and greater public-private investment coordination. We recommend increasing the 2028–2034 EU budget by at least 5% with a dedicated robotics allocation. 4️⃣ Upskilling the Workforce – Tackle skill shortages across factory floors and engineering teams. From frontline operators to system integrators, we need a unified "Robot Skills Framework" and modern vocational training. 5️⃣ Smart Regulation – Align AI and robotics regulation to promote innovation. Use regulatory sandboxes, harmonized safety standards, and dynamic, risk-based approaches to support adoption—especially among SMEs. 📘 Download the full report: https://lnkd.in/evxEPDgn #Robotics #AI #IndustrialPolicy #Reindustrialization #Innovation #VentureCapital #FutureOfWork #TechSovereignty #Automation #Manufacturing #Ludonomics #AllianzTrade #Allianz

What does it really look like when AI transforms logistics...not in theory, but at scale? I recently had a great conversation with Marcus Hand at Seatrade Maritime News about what’s next for logistics. We’re not talking pilots or proof of concept. AI is live across our operations - boosting inventory accuracy to 99.97%, cutting issue resolution time by more than half, and helping reduce emissions by 20%. From computer vision and machine learning to robotics and automation, we’ve scaled over 30 projects and integrated 150+ robotics solutions. And yes, performance matters. But this is also about building smarter, more resilient supply chains that can flex with a volatile world. Spoiler: it involves humanoid robots, real-time insights, and predictive logistics that help us stay ahead of disruption. AI is just getting started. Here’s what that looks like in practice: https://lnkd.in/dd7Gz2dV I would love to hear how others are applying AI in logistics or driving innovation across the supply chain. Drop your thoughts below.

Understanding user intent is foundational to improving any AI-driven product experience. In this tech blog, Udemy’s engineering team shares how they evolved their intent-understanding system by incorporating LLMs, ultimately improving the user experience of the Udemy AI Assistant. - For the Assistant to work well, the very first step is figuring out what a learner actually means so that the system can take the right action. Early versions relied on a lightweight sentence-embedding model: user messages were mapped to a vector space and matched against example utterances to identify the closest intent. This approach worked reasonably well at the start, but as the Assistant grew to support more features and nuanced intents, it began to struggle, leading to more misclassifications and weaker responses. - To improve accuracy, the team explored larger embedding models and eventually tested using LLMs directly for intent classification. While this LLM-only approach significantly improved understanding by leveraging full conversational context, it also came with higher latency and cost. The key was a hybrid strategy: use embeddings when confidence is high, and fall back to a smaller LLM only when intent is ambiguous. This delivered a strong balance between accuracy and efficiency in production. What stands out is how real-world constraints shaped the final design. In production systems, there are always trade-offs between quality, speed, and cost—and the “best” architecture is rarely the most complex one. Udemy’s approach is a useful reminder that combining lightweight methods with LLMs in the right places can meaningfully improve user experience without over-engineering the solution. #DataScience #MachineLearning #LLM #ProductAI #AppliedML #MLSystems #IntentUnderstanding #SnacksWeeklyonDataScience – – –  Check out the "Snacks Weekly on Data Science" podcast and subscribe, where I explain in more detail the concepts discussed in this and future posts:    -- Spotify: https://lnkd.in/gKgaMvbh   -- Apple Podcast: https://lnkd.in/gFYvfB8V    -- Youtube: https://lnkd.in/gcwPeBmR https://lnkd.in/ga5JJuzN

Stop trying to build one massive AI agent. You're setting yourself up for hallucinations and latency spikes. Here are 5 architectural patterns that separate fragile demos from robust, production systems. ⬇️ I see too many teams struggle because they treat agent development like advanced prompt engineering. It's not just about prompts—it's about architecture. The 'just chat with it' phase is over. Building production-grade agents requires real engineering. 1. Decomposing Workflows Break down complex tasks into smaller, specialized agents. Have a 'supervisor' agent route requests to the right specialist—one for understanding user intent, another for retrieving data, a third for complex reasoning. This approach simplifies maintenance and makes scaling much easier. 2. Future-Proofing Your Architecture The complex logic you build today could become a single API call tomorrow as models improve. The field is moving incredibly fast. Design your system in a modular way, so you can easily swap out custom components when a better, native solution becomes available. 3. Embedding Multimodality Text-only is no longer enough. The best agent systems are built with multimodality from day one. They can process user images, understand visual context, and even generate visual outputs. Don't treat it as an add-on; it's fundamental for a complete and accurate solution. 4. Leveraging Open Protocols Stop wasting engineering cycles on custom API wrappers. Adopt open standards for both agent-to-agent (A2A) and agent-to-tool communication (MCP). This allows your decomposed agents (see point #1) to collaborate seamlessly and lets them dynamically discover and use tools with a standardized format. You're building a scalable ecosystem, not a maintenance nightmare of fragile, custom integrations. 5. Separating Reasoning & Execution Never let an LLM perform calculations or write directly to a database. That's a critical mistake. Use the LLM for what it's good at: reasoning and understanding intent. Then, force its output into a strict format (like a Pydantic model), validate it, and pass it to reliable, deterministic code for the actual execution. Let the LLM think, let your code do. Building reliable agents is a serious engineering challenge. Respect the fundamentals. What's the biggest architectural lesson you've learned building AI agents? ♻️ Repost this if you find it useful. 🔔 Follow me for more on production AI. #AgenticAI #MLOps #EnterpriseArchitecture #AIStrategy

America’s Robotics Challenge: Building Useful Robots Instead of Impressive Ones A former NASA robotics leader argues that the United States risks focusing on robotics demonstrations and technical showmanship while China concentrates on deploying robots that deliver strategic economic and industrial value. According to the author, the future robotics race will be won not by the most impressive machines, but by the countries that successfully integrate robotics into their broader economic and manufacturing ecosystems. The article points to China's highly publicized humanoid robot demonstrations as examples of technological signaling. While such displays attract attention, the author believes the more important story is China's systematic effort to scale robotics across factories, logistics networks, infrastructure projects, healthcare systems, and industrial production. The emphasis is not merely on what robots can do, but on where and how they are deployed. In contrast, the United States remains a global leader in robotics innovation. American companies have developed remarkable machines capable of advanced mobility, manipulation, and autonomy. Robots from leading firms demonstrate extraordinary technical capabilities, including complex movements, object handling, and operation in challenging environments. However, the author argues that technical excellence alone does not guarantee strategic advantage. The key concern is deployment at scale. The author contends that America may be investing heavily in breakthrough demonstrations while underinvesting in the industrial infrastructure, supply chains, workforce training, and commercialization pathways necessary to integrate robotics throughout the economy. Meanwhile, China is aggressively positioning robotics as a national competitiveness tool designed to offset labor shortages, increase productivity, and strengthen manufacturing leadership. Key Takeaways: The article argues that robotics success should be measured by economic impact rather than technological spectacle. While the United States leads in many areas of robotics innovation, China is focusing on large-scale deployment and industrial adoption. The author believes America must prioritize practical implementation, workforce development, manufacturing integration, and commercialization if it hopes to maintain long-term leadership in robotics and automation. The broader implication is that robotics is evolving from a technology sector into a strategic national capability. Just as previous industrial revolutions were shaped by the widespread deployment of transformative technologies, the next phase of economic competition may be determined by which nations can most effectively integrate intelligent machines into their productive economies. In that contest, deployment strategy may prove more important than impressive demonstrations. Keith King https://lnkd.in/gHPvUttw

Here's why local manufacturing is important for tech innovation. The conventional wisdom says innovation happens in Silicon Valley and manufacturing in Shenzhen. But after three decades in tech, I've learned that separating thinking from making is innovation's biggest bottleneck. When design teams sit continents away from production lines, products get optimised for boardrooms, not reality. The feedback loop stretches from days to quarters. Market insights get lost in translation. By the time products reach end users, the world has moved on. Local manufacturing compresses this cycle dramatically. Engineers can walk the factory floor in the morning and redesign by afternoon. Quality issues become innovation opportunities in real-time. More importantly, proximity to actual users sparks insights that distant R&D centres might miss entirely. Consider India's unique challenges - extreme temperatures, voltage fluctuations, dust, humidity variations. Products designed for controlled environments fail spectacularly here. But when manufacturing happens locally, these constraints become innovation drivers. Suddenly, products emerge that work not just in ideal conditions but in real-world chaos. The ecosystem effect multiplies this impact. Local suppliers stop being just vendors - they become innovation partners. Educational institutions align with industry needs. Startups emerge to solve niche problems. The entire value chain starts thinking, not just executing. Critics point to global supply chain efficiencies. True, but efficiency without relevance is meaningless. The technology that transforms lives in Tier 3 cities needs fundamentally different innovation than what works in Taipei or Toronto. Innovation isn't about where you think. It's about how close you are to the problems worth solving. . . #TechInnovation #LocalManufacturing #MakeInIndia #ProductDesign #HardwareInnovation #TechForIndia #ProductDevelopment