Applied Intuition

So proud of all the work that went into launching TRATON OS and for the continued partnership we've developed with TRATON GROUP! Underlying the speed of deployment is a foundation of trust, accountability, and collaboration.

What used to take months of automotive software development can now happen in minutes. Nissan showcased this new reality live on stage at last week’s AWS Summit Japan with Applied Intuition’s AI-native Vehicle OS development environment on a Nissan Leaf demo vehicle. Audience members chose a vehicle software feature to modify—a welcome sequence involving blinking lights—and engineers built, validated, and deployed it over-the-air in real time. The demo wasn't really about the welcome sequence. It was about development velocity and what's possible when an AI-powered, integrated toolchain replaces traditional fragmented, manual workflows. Teams can spend less time navigating tools and more time building applications that create differentiated experiences for their customers. In the AI-defined vehicle era, the future of vehicle intelligence will be shaped as much by how quickly software is built as by the software itself. Learn more about our work: https://lnkd.in/grSFuyvX

A lot has changed since the first Autonomous Haulage Systems were deployed for mining. Modern perception capabilities are enabling a new level of safety, flexibility, and scalability for both mining AND construction. This blog explains how we're thinking about sensor stack design at Applied Intuition. https://lnkd.in/eu_CUfN8

“Find where the tectonic plates are shifting and stand on the fault line. That is where the most profound opportunities are.” Congratulations, Dr. Younis! https://lnkd.in/gGcgRFia

Even though I talked AI at a commencement speech, the students didn't throw tomatoes at me (!) https://lnkd.in/g6YHQdtB

Autonomous haul trucks operate with no lane lines, no curbs, no signs – just berms, unmaintained haul roads, and obstacles of every size, shape, and material composition. Perception is the biggest challenge and a single sensor isn’t enough. Here is how we address that challenge with layering sensors that help our autonomous trucks see in any site condition: ➡️ Lidar provides 360° coverage, working in low to no visibility. But some materials absorb rather than reflect, producing returns too weak to register as obstacles. ➡️ Cameras add visual data that feeds into the perception stack, making the model's understanding of the environment more precise than lidar alone. While cameras can struggle with low-light perception, together the two sensors compensate for each other's blind spots. ➡️ Radar measures, through the Doppler effect, the radial velocity of a moving object, giving the system the data it needs to assess whether a collision course is developing - something neither lidar nor cameras can do well. Rounding out the suite are localization sensors: a GNSS/INS unit, an Inertial Measurement Unit, and wheel encoders. Most existing autonomous systems respond to uncertainty by stopping. When the perception stack lacks sufficient confidence, the system defaults to the most conservative action available: a hard stop. Our SDS is built to a different standard. Rather than treating uncertainty as a binary pass/fail, our system uses learned models trained across diverse real-world scenarios to produce a probability distribution over possible actions. Learn more about the sensor stack behind our self-driving system: https://lnkd.in/gaxnPG3h

World foundation models can generate photorealistic, physically grounded sensor data for scenes that were never driven: any weather, any lighting, any ODD. Applied Intuition has built a complete toolchain around world foundation models that lets autonomy developers turn their fleet data into diverse, validated sensor datasets for production use. We've built a reference implementation around NVIDIA Cosmos world foundation models and are excited to share this with developers. The pipeline runs in five stages, end-to-end: ➡️ Curate and auto-label fleet data into conditioning-ready segments ➡️ Extract scenario, map representations, and model sensor geometry to ground the model in the real world ➡️ Generate recipes, conditioning and prompts to guide model response ➡️ Post-train to match sensor configurations and run model inference in batch on cloud ➡️ Validate every batch with autonomy-specific checks and image quality metrics The model is powerful. The pipeline is what makes it usable in production. Read the full pipeline breakdown here: https://lnkd.in/gvTaAYVs

The UNECE just approved the first global safety standard for autonomous vehicles. For OEMs, that means one compliance path across type-approval markets like the EU, Japan, and the UK, and with a corresponding standard for self-certification markets like the US and Canada. No more rebuilding your safety case for every market. The standard requires evidence-based safety cases, a human driver performance baseline, and simulation as valid validation — with a real credibility bar attached. This is how Applied Intuition has always built. Safety-case methodology, traceable validation, simulation fidelity that holds up under scrutiny. Our approach is now the global standard. What this means for your program: https://lnkd.in/geQU82P5

Something significant happened across our TRATON GROUP family last week. TRATON and Applied Intuition publicly shared the story behind TRATON ONE OS, the single software platform that will eventually run trucks across all TRATON brands. Scania, MAN, International, and Volkswagen Truck & Bus. One operating system. The foundation for software-defined vehicles across the group. What stood out wasn't just the technology. It was the speed. 200 engineers onboarded in the first quarter—twelve months from a system demo on a laptop to prototype trucks in testing. That's not how a 120-year-old industrial company is supposed to move. Here's what made it possible. The teams built the partnership before they built the product. They agreed on how decisions would be made, how disagreements would be handled, and how to operate as one team. Engineers owned execution directly. The technology side of digital transformation gets all the attention. But the harder work is almost always organizational. How do you decide? How do you trust? How do you build together? #DigitalTransformation #SoftwareDefinedVehicles #TRATON

Building an Autonomy Industrial Base starts with closing the gap between development and deployment. Every military service needs to develop, test, and field autonomous systems at scale – from productionized software, integration infrastructure, accessible data, and persistent access to platforms. At Second Front’s Offset Symposium, our Head of Federal Growth Ezra Shapiro spoke about our work with the DoW Chief Digital and Artificial Intelligence Office (CDAO) on Autonomy Factory to build an enterprise autonomy pipeline that speeds up autonomy development and deployment across the United States Department of War at mission speed. Learn more about how we’re accelerating the Autonomy Industrial Base: https://lnkd.in/gF3xrRtB