Vision Zero – Transport Innovation Alliance

Tag Archive for: Vision Zero

The gaps we need to close in our mobility strategies

3 June 2026/in Rikesh Shah/by Transport Innovation

By Rikesh Shah, Chair of the Transport Innovation Alliance

In May, as Chair of the Transport Innovation Alliance, it was a genuine pleasure to lead our Leadership Forum in Barcelona — bringing together 20 cities from across Europe and some of the world’s leading mobility experts for two days of open, frank discussion. A particular thanks to Manuel Valdés and the team at ATM Àrea de Barcelona for being such generous and engaged hosts. What made Barcelona particularly striking was how closely it echoed what I heard at our North American session in Detroit last month — the same questions, the same tensions, the same urgency, just in a different context. These are not local challenges; they are global ones.

Rikesh Shah in conversation with Manuel Valdés, CEO of ATM Barcelona, at the TIA Leadership Forum

The agenda was deliberately broad reflecting the myriad challenges we see in our cities everyday: cycling networks and modal shift, fleet decarbonisation, autonomous vehicles across shared, bus, and private car applications, micromobility integration, public bus efficiency, and a site visit to the Glòries interchange. Yet three themes kept resurfacing across every session, every roundtable, every case study — Net Zero, Vision Zero, and the importance of data in understanding how to reach our mobility goals. These themes pose overlapping challenges that cities cannot solve in isolation.

On Net Zero, regional and city joint strategies will remain aspirational documents unless they grapple honestly with how change happens — not just what targets to set — and look beyond the city boundary. There was an honest acknowledgement that the car will co-exist with other modes for the foreseeable future, but its footprint must shrink while investment in alternatives grows.

A related area was EV infrastructure: we are deploying heavily without the data to know whether it is going in the right places. Closing the communication gap between transport agencies, stakeholders, and industry around what Net Zero actually requires — and what interventions work — demands that different perspectives are properly heard. It is something I saw first-hand at Transport for London, navigating boroughs, suppliers, and citizens who might have different motivations so communication and relationships are key.

On Vision Zero, the consistent thread was a systems approach — safety cannot be designed in isolation from the wider urban environment. Autonomous vehicles (buses, private and shared taxis) came up several times as a case in point: the potential to reduce human error and save lives is real, but only if the risks are properly understood and mitigations rigorously managed and we saw strong arguments of how safe AVs can be. The technology’s promise cannot be allowed to run ahead of the governance. For public buses in particular, the conversation around autonomy cannot be separated from total cost of ownership — the case for deployment has to stack up financially as well as operationally, and cities need robust frameworks to evaluate that.

Placemaking is equally central to this: streets built well for people are inherently safer, more accessible, and more likely to shift travel behaviour. Living in Watford and working in London, I have seen an excellent effort for better placemaking and more space for vulnerable road users. You notice the difference straight away. Road safety is not just a traffic engineering problem; it is a question of what kind of places we want to create. And that ambition cannot rest with cities alone — regional and local plans need to reflect it jointly, because the journeys people make do not stop at administrative boundaries.

On data — the connective tissue running through both — it must serve city goals and not become an end in itself. Cities consistently tracking modal shift are seeing results; those that are not, are flying blind. And data without narrative is just numbers on a slide.

The gaps are clear. That is why the Transport Innovation Alliance is now taking three working groups forward — on Net Zero, Vision Zero, and data and policy — to turn these conversations into structured, collaborative action. We are inviting cities to express their interest in joining. The work starts here.

Philadelphia unveils equity-driven Vision Zero overhaul

1 December 2025/in William Thorpe/by Transport Innovation

Philadelphia has put equity, vehicle technology and data integration at the forefront of its new Vision Zero Action Plan 2030, introducing a series of innovations that mark a shift in how the city intends to eliminate traffic deaths.

The plan debuts a new Underserved Communities metric to track racial disparities in fatalities, launches a pilot of Intelligent Speed Assistance (ISA) in the municipal fleet, and commits to delivering safety upgrades on every mile of the High Injury Network by 2030. It also updates the High Injury Network using post-pandemic crash data and sets out new efforts to link health and crash datasets to better understand injury patterns.

These measures form the backbone of the city’s latest strategy, released by the Office of Transportation and Infrastructure Systems (OTIS) and Vision Zero Philadelphia. The plan fulfils the mayor’s 2024 executive order and draws on input from nearly 3,000 residents through roundtables, surveys and market research. A mobile-optimised online version has also been published.

“This is a plan by and for the people of the City of Philadelphia,” said Cherelle Parker, Mayor of Philadelphia. “The voices of nearly 3,000 Philadelphians are reflected in this document and will help guide my administration’s work to make Philadelphia safe, clean and green with economic opportunity for all.”

Despite continued investment in safety programmes, the report notes that 2024 fatal crashes remained above pre-2020 levels. People walking, cycling, rolling or riding motorcycles–who make up fewer than 10 percent of all crashes–accounted for nearly two-thirds of fatalities. The Department of Public Health’s new equity metric shows that black and Hispanic residents experience disproportionately higher traffic-related deaths, a disparity the plan will track over time.

The updated High Injury Network, reflecting crash data from 2019 to 2023, reaffirms that 12 percent of streets account for 80 percent of serious injuries and fatalities. Residents identified speeding, running red lights and distracted driving as their top concerns, and emphasised that physical street design changes are most effective in reducing dangerous behaviours.

The plan is organised around the Safe System approach, outlining actions on safer streets and speeds, safer people, safer vehicles, data and policy. Recent progress includes expanded automated speed enforcement on major corridors, completion of the city’s fifth neighbourhood slow zone with a 20 mph (30 km/h) limit, and new pedestrian median islands on high-risk arteries.

Image: Philadelpia © | Dreamstime.com

New AI model helps cities analyse traffic risks at scale

25 November 2025/in William Thorpe/by Transport Innovation

Researchers at NYU Tandon School of Engineering have developed a multimodal AI system that analyses traffic-camera footage to detect collisions and near-misses, providing cities with a way to draw safety insights from existing video networks without extensive manual review.

The system, SeeUnsafe, has been recognised with New York City’s Vision Zero Research Award and is published in Accident Analysis and Prevention. It applies multimodal large language models (MLLMs) to long-form traffic footage, aiming to support more continuous analysis than traditional crash-based approaches.

Many cities now collect extensive traffic video but still rely on limited data sources because reviewing footage is labour-intensive. Speaking to Cities Today, Kaan Ozbay, Senior Author of the SeeUnsafe paper and Director of the C2SMART Transportation Research Center at NYU Tandon School of Engineering, said this has created a persistent gap.

Kaan Ozbay, Senior Author of the SeeUnsafe paper and Director of the C2SMART Transportation Research Center

“Cities have rapidly expanded their traffic-camera networks, but their ability to learn from all that video hasn’t kept up,” he said. “Manual video analysis is extremely time-consuming and expensive, and custom computer-vision pipelines require specialised engineering, site-specific tuning, and ongoing maintenance.”

Ozbay said this has limited the practical value of large video archives for day-to-day decision-making.

“This gap is why ‘more data leads to safer roads’ hasn’t become reality,” he added. “The advent of MLLMs brings about a paradigm shift, enabling the continuous video to be transformed into automated, scalable safety insights.”

The model combines object-level signals with contextual reasoning. Unlike traditional pipelines that separate tasks such as detection, tracking and speed estimation, it interprets traffic scenes as a whole.

“SeeUnsafe uses MLLMs to understand traffic scenes more like a human safety engineer, rather than as a collection of separate vision tasks,” Ozbay said. “This kind of scene-level understanding is essential for spotting rare but important events like collisions and near-misses that classical CCTV often struggles to capture.”

Testing on the Toyota Woven traffic-safety dataset showed accuracy levels above those of comparison models. However, Ozbay said results from controlled datasets do not automatically translate to the complexity of real-world urban environments.

“SeeUnsafe’s accuracy is already promising in controlled settings, but there is still a gap before it is ready for fully reliable citywide deployment in a place like New York,” he said. Factors such as lighting, weather, camera position and unusual behaviour can affect performance.

The system also produces natural-language summaries describing the conditions and movements associated with detected events. Ozbay said this format helps integrate the tool into existing public-sector workflows.

“This system lowers the barrier between users and analytical outcomes by translating huge volumes of complex, unstructured video into insights that non-technical stakeholders can immediately understand,” he said. “It fits existing workflows, reduces the learning curve, and helps agencies adopt AI-assisted safety analysis without having to change how they already review and justify decisions.”

Ozbay added that the same technology could be used in wider mobility-planning or operational contexts as cities strengthen data infrastructure.

“We see fixed traffic cameras as the ‘0 to 1’ step,” he explained. “Once that foundation is in place, the same core technology can naturally extend beyond fixed cameras.”

The long-term goal is to now support a clearer understanding of how risk develops across road networks.

“We’re already seeing parallel efforts in urban mobility and autonomous driving, and SeeUnsafe is positioned to plug into that ecosystem as the ‘traffic safety intelligence layer’ that connects real-world video, virtual models, and operational decisions,” he said.

Main image: Juliengrondin | Dreamstime.com