Industry 4

Mobility & automotive

ADAS and autonomy safety and validation, traffic operations, fleet and logistics planning, materials for batteries and lightweighting.

Written for

ADAS and autonomy safety and validation, traffic operations, fleet and logistics planning, materials for batteries and lightweighting.

The decision

Can this controller be released; how to time signals across a city; how to route a fleet.

How it is done today

Safety sign-off rests on simulated disturbance models; signals and routes are tuned junction by junction and depot by depot.

When it goes wrong A disturbance model that is too clean passes controllers that fail on the road.

Applications

ApplicationYou giveYou getStatus
Autonomous-driving safety validation

Proof: 95.6% safe episodes against 39.5% with the white-noise model

The controller and its operating envelopeThe safe-episode rate under a measured disturbance modelLive on quantum hardware
Traffic-signal coordination

Proof: About 20% less waiting, proof of concept

The junction network and flowsCoordinated timingsDeployed through the platform network
Vehicle routing and fleet assignment, including drone deliveryVehicles, depots, orders and windowsThe routes and the assignmentDeployed through the platform network
Rail timetable recovery and rolling-stock rotationThe timetable, the fleet and the disruptionA recovered planDeployed through the platform network
Battery and lightweight-materials candidate ranking

Proof: Materials lane: four of four formulations ranked correctly on IBM Heron

Candidate materialsA ranking with the smallest difference it resolvesLive on quantum hardware
CFD acceleration for aerodynamics

Proof: Crossover projected at about 93 logical qubits

A flow problemThe crossover point and the route to itRoadmap

What changes for you

  • The disturbance model is measured on hardware instead of assumed.
  • The sign-off evidence names its baseline.
  • Routing and signal work ships through the platform network today.

First engagement

You send One controller and its operating point.

You get back The safe-episode comparison against your current model. Two weeks.

Proof · Autonomous-driving safety validation · traffic signal coordination

Hardware result · customer proof of concept

95.6%

safe episodes with the measured disturbance model, against 39.5% with the white-noise model, same controller

Measured on quantum hardwareClassical computationPlatform a 128-qubit processor; closed-loop evaluation in simulation

Decision

Can the autonomy controller be released

What is modelled

The disturbance the controller faces, as a 128-qubit model; the controller evaluated in closed-loop simulation.

Operational outcome

  • +56 points in safe-episode rate at the same operating point
  • Evidence a safety reviewer can sign off
  • City signal coordination: 20% less waiting time (proof of concept, simulation)
Problem size
128-qubit disturbance model · one controller · city-scale signal network
Scope
The controller was evaluated in simulation; no on-road result is claimed.

Results, each with its baseline

  • 95.6% safe episodes with the disturbance model measured on a 128-qubit processor, against 39.5% with the white-noise model, same controller, same operating point.Measured on quantum hardwareClassical computationWhere 128-qubit processor; evaluation in simulation
  • City traffic-signal coordination: about 20% less vehicle waiting time in simulation (2020), against conventional signal timing (platform network, quantum-inspired).Platform networkWhere simulation, 2020
  • CFD acceleration: crossover projected at about 93 logical qubits from a measured cost law (projection).ProjectionWhere projection

Benchmark

Mobility & automotiveAutonomous-driving safety validation · traffic signal coordination

Published reference

Nonlinear flow on superconducting hardware reaches 15 time steps; vehicle routing on device reaches 3 nodes.

Sources: IBM Heron R3, 2026 · arXiv:2504.01567 · arXiv:2509.11469

Merlin

95.6% vs 39.5% safe episodes · 20% less waiting at signals (proof of concept)

Measured on quantum hardwareClassical computationPlatform network

Baseline

White-noise disturbance model; conventional signal timing

Read the story

Through our platform network

Client anonymised to its sector; partner not named; metric quoted with its published baseline, compute type and status. Not our own measurement.

Automotive / materials

Automotive materials discovery (transparent conductors)

Score 123.5 vs 100.5 (NSGA-II) and 76.2 (TPE) in a 60-second run; reached NSGA-II's 60-second score in about 10 s

Condition
One public dataset; computational only. Any percentage is derived from the paper's table, not stated by its authors.
Compute
Quantum-inspired, on classical hardware
Status
Preprint

Does not show that quantum beats classical.

Through our platform network · partner and client not named

Mobility / smart city

Urban traffic-signal timing

−20% vehicle waiting time vs the conventional method

Condition
Simulation in a virtual environment, June 2020. Not a field trial.
Compute
Quantum-inspired optimisation
Status
Simulation, 2020

Does not show that quantum beats classical.

Through our platform network · partner and client not named

Your industry, next

Bring us the decision your industry has to make next.

A resist, a grid plan, a controller, a cipher: you get the answer, the method it was checked against, and its status. The free check runs in your browser.

No keyNo cardAn answer in about a second