At this year’s Autonomous Vehicle Technology Expo Europe 2026, Mircea Gradu will present “Advanced connected and automated vehicle (CAV) AI research platform – deployment and results” within the Simulation and Testing, Scenarios & Virtual Validation conference session.

Deployed across 25 live public intersections in Orange County, California, the platform combines infrastructure based LiDAR sensing, AI powered traffic intelligence, eco driving control systems and real world deployment to create one of the most ambitious connected mobility research initiatives currently operating on public roads.

We caught up with Mircea ahead of the event to learn more about the project and why its findings could have major implications for the future of connected and automated mobility worldwide.

To begin, could you give us an overview of the advanced connected and automated vehicle AI research platform deployed in Orange County? What problem was it designed to address?

The platform was created to tackle several major urban mobility challenges simultaneously, particularly around traffic inefficiency, vulnerable road user safety, infrastructure intelligence and vehicle energy consumption.

Conventional traffic signal systems still rely heavily on static timing plans and outdated loop detector technology, which creates unnecessary stopping, queueing and wasted energy at intersections. At the same time, pedestrians and cyclists remain especially vulnerable in these environments, with many near miss incidents never being captured by traditional monitoring systems.Municipalities also lack the continuous, real time, multi modal traffic data needed to properly optimise signal operations or make informed infrastructure decisions. Vehicle classification, speed, trajectory and behavioural data are often fragmented or unavailable.

 The energy implications are equally significant. Stop start driving dramatically increases energy consumption and emissions, particularly for electric vehicles where efficiency and range remain critical concerns.

What makes this platform unique compared with other connected and automated vehicle research initiatives globally?

There are three core differentiators. First is the fact that the platform operates on live public roads rather than within a controlled proving ground or isolated test environment. Second is the use of infrastructure side LiDAR sensing rather than relying entirely on vehicle based intelligence. Third is the project’s strong energy efficiency focus, mandated through US Department of Energy objectives. Many global testbeds focus purely on autonomy or connectivity. This platform combines safety, sustainability and infrastructure intelligence into one fully integrated deployment.

What were the main objectives of the research, and how do the findings relate to improving safety for cyclists, pedestrians and other vulnerable road users?

One of the project’s most important breakthroughs is its ability to shift safety analysis from reactive to proactive.Historically, safety improvements have relied on analysing crashes after they occur, often years later. This platform instead identifies near miss events and behavioural risk patterns in real time, fundamentally changing how intersections can be  monitored and improved. Crucially, the intelligence sits within the infrastructure itself rather than inside the vehicle. That means every road user benefits equally at equipped intersections, whether they are driving a connected vehicle, riding a bicycle or simply crossing the road.

This infrastructure centred approach delivers a level of equitable protection that vehicle only systems cannot achieve alone.

You’ve analysed mixed traffic, vehicle speeds and non university road users. What early insights or behavioural patterns have emerged from the data?

Several fascinating findings have already emerged from the deployment.

For the first time, pass through traffic across the UCI network can now be accurately quantified, giving transportation planners robust evidence to justify signal timing and infrastructure changes.

The platform has also confirmed that both energy savings and traffic flow improvements are real, although highly dependent on traffic density. The strongest performance gains appear in low to moderate traffic conditions, highlighting an important challenge for scaling during peak congestion.

Another major shift is the move away from crash based safety analysis toward real time near miss intelligence. Rather than waiting years for accident data, transportation teams can now identify high risk behaviours almost instantly and map them with precision.

Interestingly, the findings also show that energy efficiency and vulnerable road user safety naturally reinforce one another. Smoother traffic flow reduces vehicle energy consumption while simultaneously reducing the stop start conditions most commonly associated with pedestrian and cyclist conflicts.

The use of privacy preserving LiDAR sensing also avoids much of the regulatory friction faced by camera heavy monitoring systems, making continuous public road deployment far more politically viable in many Western cities.

Could you walk us through the analysis framework behind the project? How do microsimulation, model based engineering and X in the loop testing contribute to it?

The project combines simulation, model based engineering and physical vehicle validation into one tightly integrated development framework. One standout result was that the combined vehicle and signal controller delivered a 44% improvement in average vehicle speed while also producing the largest energy savings. The correlation between simulation and X in the loop testing results was also remarkably strong, validating the real world applicability of the modelling approach.

Performance again proved density dependent, with the most significant gains achieved under lighter traffic conditions. Sensor capability also played a critical role. Greater LiDAR detection distance directly improved controller performance, strengthening the case for next generation sensing technologies in future connected infrastructure systems.

Ultimately, the research demonstrates that energy efficiency and safety are not competing priorities. The same eco driving strategies that reduce energy consumption also reduce the stop and go traffic conditions where vulnerable road user conflicts most commonly occur.

How do you balance simulation and virtual validation with real world scenario testing, and what advantages does this hybrid approach provide?

The platform follows a carefully structured progression from simulation to X in the loop validation and finally to live road deployment. The first phase uses simulation to model eco driving behaviour at signalised intersections under varying traffic conditions and sensing ranges. The second phase introduces a real Scion iQ battery electric vehicle at Argonne National Laboratory into the loop, allowing researchers to measure real vehicle energy behaviour while keeping the surrounding traffic environment simulated. The final phase moves into live deployment across 25 public intersections with real traffic, real signal hardware and real vulnerable road user interactions. This progression is what makes the platform particularly compelling. Rather than treating simulation and real world testing as separate workstreams, each phase directly informs and validates the next.

The agreement between simulation and physical testing was especially impressive. For example, simulation predicted a 31.6% reduction in fuel consumption for the vehicle controller alone, while X in the loop testing measured 26.4%. For the combined vehicle and signal controller, simulation predicted 38.4% savings and testing confirmed 36.1%.

That level of consistency strongly suggests the simulation models accurately capture real world vehicle dynamics.

What has been your involvement, and FISITA’s wider role, in developing or coordinating this research platform?

Together with Professor Samuelsen and Dr Lane, I helped initiate the project several years ago, particularly supporting the sensing and signal processing elements. Alongside my role within FISITA, I also serve as Vice President of Vehicle Engineering at Karma Automotive, the American luxury EV manufacturer headquartered in Irvine. Looking ahead, Karma Automotive will support the platform’s next development stages around V2X connectivity, V2I integration and AI based data management systems.

Why did you choose to present these findings at Autonomous Vehicle Technology Expo Europe?

After first introducing the project at the event in 2022, we felt this year presented the ideal opportunity to share a comprehensive update on the platform’s deployment, validation and real world results. The conference consistently attracts an exceptionally knowledgeable audience and creates the perfect environment for deeper technical discussions around connected and autonomous vehicle deployment.

Finally, what are you hoping to explore, learn or connect with at the show this year?

The conference always offers excellent opportunities for networking across highly specialised areas of interest, while also providing direct access to the latest developments shaping the rapidly evolving AI driven connected and autonomous vehicle landscape. For anyone working within the sector, it remains one of the most valuable opportunities to exchange ideas, challenge assumptions and explore what comes next for the future of mobility.