The Future of Physical AI Will Depend on Embedded AI
Physical AI is the next great wave: robots, humanoids, drones, autonomous vehicles and energy systems that act in the physical world rather than merely describe it. Whether these systems work safely and reliably will not be decided by the large model on top, but by the embedded intelligence inside each component, sensing, estimating and acting in real time.
Physical AI is the term everyone is now using, and the excitement is justified. After a decade in which AI mostly read, wrote and recognised, the frontier is shifting to machines that act: robots that manipulate, drones that fly, vehicles that drive, energy systems that manage themselves. But the attention is landing in the wrong place. The future of Physical AI will require not only capable large models, but also intelligence that can operate reliably at the edge, on the hardware itself. And it is the layer the industry talks about least.
This is the final article in a series about embedded AI. We began by separating edge AI, which is only a deployment choice, from embedded AI, which is an engineering requirement. We looked at why intelligence in the physical world has to respect physics rather than just recognise patterns, why the data behind it takes years to build and cannot be copied, how the architecture is designed so the model can be trusted in real time, and what it actually takes to deploy that intelligence inside a real product, from the silicon up. I want to close by connecting all of it to where the industry is now heading, because Physical AI is where these threads converge.
Physical AI is built from the bottom up
A Physical AI system is a stack. At the top sits a coordinating layer, the model that plans, perceives the wider scene and decides what the system should do next. Underneath it sits everything that actually touches the physical world: actuators, motors, power electronics, sensors and batteries, each with its own real-time job to do. The top layer, the high-level planner, gets the attention because it is visible and easy to demonstrate. The bottom layer decides whether any of it works as intended and safely.
The reason is simple. A humanoid robot is only as capable as its joint control, and only as safe as its power system is predictable. A drone is only as reliable as its flight controller and its battery the moment a gust hits. No coordinating model, however large, can rescue a component whose local state estimate is wrong, nor can it wait for a round-trip to the cloud when a decision has to be made in milliseconds. Safety and real-time control live at the component level, not at the top of the stack. So Physical AI succeeds or fails where the intelligence meets the hardware, and that intelligence has to be embedded, built for constrained silicon, real-time operation and the physics of the system it runs inside. This is exactly the distinction we drew at the start of this series. It matters more here than anywhere.
The battery is the common component of Physical AI
Many Physical AI systems, from humanoids and drones to autonomous vehicles and grid-scale storage systems, share a common component: the battery. It is one of the foundations of the electrified world and an important application of embedded intelligence.
A battery’s true state cannot be measured directly. State of charge, state of health and early signs of degradation or fault must be inferred from voltage, current and temperature, under sensor noise and drift, across changing operating conditions and as the cell ages. Those estimates have to run in real time on a cost-constrained processor. Getting them wrong affects safety, reliability, performance and lifetime. That makes the battery a good example of why Physical AI depends on robust, physics-informed embedded intelligence.
A battery cannot be managed from the cloud alone. Critical battery states must be estimated in real time by embedded intelligence running directly on the hardware.
What makes embedded intelligence trustworthy
Trustworthy embedded AI depends on four things: physics, real-world data, real-time architecture and full-stack integration.
Physics sets the boundaries. Data provides experience built over years in the lab and the field. Architecture enables intelligence to run in milliseconds on constrained hardware. Full-stack integration turns a model into a product that remains reliable for years in operation.
A physics-informed model can infer what sensors cannot directly measure and remain robust beyond the precise conditions represented in its training data.
The same principles apply across motors, power electronics, actuators and flight controllers. But in the electrified world, the battery remains a critical component because the performance, availability, safety and lifetime depend on accurate state estimation and control.
Where this leaves us
Physical AI is not AI that observes the world. It is AI that operates within it. It will not be built solely from the top down by increasingly capable coordinating models. It will be built from the bottom up through trusted, real-time intelligence running directly on the hardware. High-level models will get the headlines. But whether Physical AI actually works will be decided at the edge, where estimation and control meet physics inside the component itself. In the electrified world, that mastery starts with the battery.
Dr Umut Genc is CEO of Eatron Technologies, a UK-based deep-tech company specialising in AI-powered Battery Optimisation Software for mobility and energy applications. Eatron’s Battery Optimisation Software is production-validated across automotive OEMs, two-wheeler platforms, and grid-scale energy storage systems.
