Supplier Soundbytes: What it takes to get AI results in automotive
In the next phase of automotive competition, the decisive breakthroughs may come not from the showroom or the software stack, but from the materials lab. Artificial intelligence is often discussed as if it were a software story. In automotive engineering, it is becoming something broader and more consequential. It is beginning to change how materials are discovered, how components are tested, how batteries are improved and how manufacturers make decisions under pressure.
The car, after all, is not a single invention but a stack of them: atoms, alloys, cells, packs, structures, systems and software, all required to work together at scale, safely and profitably. That multi-layer reality is where AI’s usefulness stops being theoretical. In practice, it is about finding better answers faster across the whole pipeline—turning data into decisions, and decisions into prototypes.
That makes vehicle development an unusually fertile ground for AI. Much of engineering still depends on slow cycles of trial, error and expert judgement: make a sample, run a test, interpret the result, adjust the design, and begin again. Simulations help, but they can be expensive and time-consuming. Data exists, but it is often messy, fragmented or collected too late to shape the most important decisions.
AI promises to compress some of those cycles. Used well, it can spot patterns in experimental data, suggest better materials, connect manufacturing conditions with performance, and help engineers make earlier, more confident choices. Used badly, it risks becoming another expensive black box. The difference lies less in fashionable algorithms than in disciplined engineering: good data, clear objectives, traceable results and adoption inside real workflows—so the gains show up where production and performance are decided.
That is the backdrop to the latest episode of Supplier Soundbytes from S&P Global Mobility, featuring Isaac Squires, founder and chief executive of Polaron. Spun out of Imperial College London, Polaron applies generative machine learning to accelerate the design and optimisation of advanced materials.
Isaac Squires
[Source: Polaron]
We’d love to hear your thoughts on this episode. Reach out to us at autology@spglobal.com, and discover more insights at autotechinsight.spglobal.com.
Don’t forget to hit the subscribe, follow, and like buttons to stay updated with the latest episodes of Autology.
Subscribe:
