SciTransfer
TrustVehicle · Project

Making Self-Driving Cars Safer in Bad Weather and Unpredictable Traffic

transportTestedTRL 6
trustvehicle.eu

Imagine your car can drive itself on the highway, but it gets confused when it rains or when a cyclist suddenly swerves in front of it. TrustVehicle worked on making that handoff between you and the car much smoother and safer — especially when the weather is bad or traffic is chaotic. They built smarter sensors and better warning systems so the car knows its own limits, and tested everything on 4 different types of vehicles in real roads and proving grounds. Think of it as teaching a self-driving car to say "I'm not sure, you take over" before things go wrong, not after.

By the numbers
4
vehicle class demonstrators tested in real-world conditions
13
consortium partners across the vehicle value chain
7
countries represented in the consortium
77%
industry participation rate in the consortium
Level 3
SAE conditional automation targeted
16
total project deliverables produced
The business problem

What needed solving

Automakers developing Level 3 self-driving features face a critical trust and safety gap: their systems fail or behave unpredictably in bad weather, complex traffic, and during the handover moment when the car asks the human driver to take back control. Testing these scenarios is extremely expensive and time-consuming, and there is no standardized way to validate that the system will behave safely across all conditions.

The solution

What was built

The project built fault-tolerant automated driving controllers with sensor fusion for uncertain conditions, intuitive human-machine interfaces for safe driver takeover, and an adaptive validation system using self-diagnostics and data logging. These were demonstrated across 4 vehicle classes in proving grounds and real urban environments, with 16 deliverables produced in total.

Audience

Who needs this

Automotive OEMs developing Level 3 ADAS featuresTier-1 suppliers building sensor fusion and perception systemsCommercial vehicle manufacturers (trucks, buses) adding automationVehicle testing and homologation companiesAutomotive software companies specializing in driving algorithms
Business applications

Who can put this to work

Automotive OEMs & Tier-1 Suppliers
enterprise
Target: Vehicle manufacturers and Tier-1 suppliers developing ADAS and Level 3 automation

If you are an automotive OEM or Tier-1 supplier struggling with the reliability of your Level 3 automated driving system in rain, fog, or mixed traffic — this project developed fault-tolerant controllers and sensor fusion systems tested across 4 vehicle classes in real-world conditions. Their adaptive validation approach using self-diagnostics and data logging can help you systematically extend your approved driving scenarios without starting from scratch each time.

Commercial Vehicle & Fleet Operators
mid-size
Target: Truck and bus fleet operators investing in driver-assist automation

If you are a fleet operator looking to adopt conditional automation for long-haul trucks or urban buses — this project built and tested human-machine interfaces designed for safe driver takeover in 4 different vehicle classes. The tools for assessing driver-in-the-loop and driver-off-the-loop situations can reduce the cost and time of certifying your automated fleet for mixed traffic conditions.

Automotive Testing & Validation
any
Target: Vehicle testing companies and certification bodies

If you are a testing and validation company that needs to assess automated driving systems more efficiently — this project created new tools for cost- and time-effective assessment of driver handover situations. Their agile validation method based on self-diagnostics and data logging was demonstrated in proving grounds and real urban environments, offering a replicable testing approach for Level 3 systems.

Frequently asked

Quick answers

What would it cost to license or integrate this technology?

The project did not publish pricing or licensing terms. As a publicly funded RIA project with 13 partners across 7 countries, results are likely available through collaboration agreements with consortium members. Contact the coordinator for specific licensing discussions.

Has this been tested at industrial scale?

Yes — the project demonstrated its systems on 4 demonstrators representing 4 different vehicle classes, tested in both proving grounds and real-life urban environments. The consortium included 10 industry partners, indicating strong industrial involvement in validation.

What is the IP situation — can we license this?

With 13 partners from 7 countries and 77% industry participation, IP is likely shared among consortium members. The coordinator, Virtual Vehicle Research GmbH (Austria), is the primary contact point for IP discussions. Specific licensing terms would need to be negotiated directly.

How mature is this technology — can we deploy it now?

The technology was demonstrated in real-world conditions but remains at the research-to-prototype stage for most components. SAE Level 3 automation is still subject to evolving regulations across European markets. The validation tools and sensor fusion methods are closest to near-term adoption.

Can this integrate with our existing ADAS systems?

The project specifically designed controllers and sensor fusion systems to work in mixed traffic with varying levels of automation. Based on available project data, the human-machine interfaces were built with user acceptance in mind, suggesting compatibility considerations were part of the design process.

What regulations does this help us meet?

The project directly addresses challenges of SAE Level 3 conditional automation compliance, including fault-tolerant and fail-operational system behavior requirements. The systematic scenario identification and adaptive validation methods can support type-approval processes for automated driving functions.

Is there ongoing support or follow-up work?

The project ended in October 2020. Virtual Vehicle Research GmbH continues active research in automated driving. Based on available project data, the 16 deliverables produced provide a substantial knowledge base, and consortium partners remain active in the European automotive R&D ecosystem.

Consortium

Who built it

The TrustVehicle consortium is heavily industry-driven: 10 out of 13 partners come from industry, giving it a 77% industry ratio — well above average for EU research projects. The 7-country spread across AT, FI, FR, IT, SE, TR, and UK covers major European automotive markets and supply chain hubs. The coordinator, Virtual Vehicle Research GmbH from Austria, is classified as an SME and a research center, suggesting strong applied-research focus. With 4 SMEs in the mix alongside larger industry players, the consortium spans the full vehicle value chain from component suppliers to OEMs. For a business looking to adopt these results, this means the technology was shaped by companies that understand commercial constraints, not just academic ideals.

How to reach the team

Virtual Vehicle Research GmbH (Austria) — search for their automated driving research team leads on LinkedIn or their institutional website

Order a report on this consortiumSee VIRTUAL VEHICLE RESEARCH GMBH profile →
Next steps

Talk to the team behind this work.

Want an introduction to the TrustVehicle team? SciTransfer can connect you with the right consortium partner for your specific use case — whether that's sensor fusion, HMI design, or validation tools.

Order a report on this topicMore in Transport & Mobility
More in Transport & Mobility
See all Transport & Mobility projects →
Modular Rail Wagons That Cut Steel Industry Raw Material Transport Costs
ITECCO Demo
Open →
Dual-Line Road Marking Inspection Device That Cuts Survey Costs in Half
DuaLine
Open →
Ready-to-Buy Electric In-Wheel Motor That Cuts Weight 25% and Fits Any Vehicle
GEM in-wheel
Open →