AUTONEWS

How cities can make room for robotaxis

Driverless taxis are moving from pilot projects to real-world deployment. Researchers at EPFL are studying what cities must do it they want to integrate robotaxis without increasing congestion or weakening public transport.

Switzerland recently launched its first driverless taxi service in Furttal, near Zurich. As the so-called robotaxi services become a reality, researchers are increasingly focusing not just on their technical feasibility, but on how large fleets of autonomous vehicles can be integrated into transport systems, while also extending mobility options to currently underserved rural regions.

Kenan Zhang, professor at the EPFL Laboratory for Human-Oriented Mobility Eco-System (HOMES), studies how robotaxis can be integrated into transportation networks. She analyzes many factors, from fleet allocation to parking placement and social reception. “Robotaxis are technically feasible, but their future depends much more on regulation, public acceptance, economics, and integration with cities and public transport systems,” says Zhang.

In a series of studies published in Transportation Research, Zhang and her team present artificial intelligence methods that are able to coordinate large fleets of autonomous vehicles and optimize where those vehicles wait and park when not carrying passengers. The findings suggest that future robotaxi networks could be coordinated in ways that reduce waiting times, improve vehicle utilization, and expand service availability, including areas that are traditionally underserved by on-demand transport.

Serving remote areas...Certainly, taxi drivers naturally circulate around busy areas such as urban centers, airports, and train stations, leaving suburban and less densely populated areas with fewer transport options. A fleet of autonomous vehicles, on the other hand, could tackle this limitation by dispatching vehicles strategically, helping maintain service in suburban areas.

To this end, cities may need to coordinate thousands of autonomous vehicles, ensuring that enough vehicles are available where passengers need them. To study a centrally coordinated fleet management, Zhang and her colleagues developed reinforcement learning algorithms using real-world data from the city of Shenzhen, in China. In this centralized approach, rather than allowing each vehicle to make independent decisions, the system continuously redistributes vehicles across the city according to anticipated demand, helping maintain service quality and ensuring availability in neighborhoods that are often overlooked by conventional ride-hailing operators, such as Uber.

However, robotaxis could solve one urban headache while creating another. “As autonomous vehicles reduce the need for traditional parking, they may also spend more time circulating on the streets while waiting for passengers,” says Zhang. To address this issue, she suggests the introduction of new regulations, such as limiting driverless vehicles without passengers, charging fees for unnecessary circulation, or creating dedicated waiting areas.

Complementing public transport...Even if the technology is ready, one of the key factors for its successful deployment will depend on whether autonomous transport can complement, rather than undermine, sustainable mobility systems. In such a system, autonomous vehicles would become one component of a broader transport ecosystem, extending the reach of public transport instead of drawing passengers away from it.

However, the long-term cost of large-scale robotaxi services remains uncertain. If robotaxis become cheaper, more people may be willing to use them, increasing both their potential benefits and the risk of competition with public transport. “That would not be a good thing, because public transportation will always be more efficient in transporting travelers with limited vehicle space, road capacity, and energy consumption,” says Zhang.

Switzerland represents a particular case when it comes to adopting autonomous taxi services. The country already has a high-quality public transport network with extensive coverage across most urban areas. These factors can limit the demand for robotaxis, in particular in the city centres.

A cascading effect...“Considering all these technical and economical dimensions, at the beginning adoption of autonomous taxis will not be evenly spread,” believes Zhang. Major cities in countries such as the United States and China could undergo widespread deployment within the next decade. Then autonomous driving and robotaxis might benefit from a cascading adoption effect. “Once a city demonstrates that robotaxis can operate safely and efficiently, other cities with similar transport needs are likely to follow,” concludes Zhang.

The next challenge researchers need to address is ensuring that the computational models developed remain effective when deployed in real cities, where travel demand, infrastructure, and human behavior are far more complex than in simulations.

AV readiness is more than permitting...A city’s responsibilities do not disappear when vehicle regulation sits at the state or national level.

Cities still manage streets, traffic operations, emergency response, construction zones, special events, curbs, transit interfaces and much of the information needed to operate safely in a complex urban environment.

Austin therefore engages with AV operators on practical issues that directly affect operations.

One priority is first-responder preparedness.

Rather than having firefighters or police encounter an unfamiliar automated vehicle for the first time during an emergency, Austin organizes training where responders can see the vehicles, access them and understand how they should interact with them.

This seems operational, but it is also a governance principle: prepare institutions before deployment scales.

Digital information matters — but basic infrastructure still matters too...Automated vehicles depend on sophisticated sensing and mapping. Yet urban environments change constantly.

Roadworks appear. A street closes for an event. Emergency responders redirect traffic. A police officer gives instructions that conflict with a traffic signal.

Cities therefore have an important role as information providers.

Austin shares information on road closures, events and other changes in the right-of-way and is progressively improving how this information can be communicated digitally.

At the same time, the city’s experience provides an important reminder: preparing for AVs does not necessarily mean installing expensive AV-specific infrastructure everywhere.

Clear striping, understandable signs, well-designed intersections and visible restrictions help automated vehicles — but they also help human drivers, cyclists and pedestrians.

Investment in a clearer and safer right-of-way can therefore create benefits regardless of how quickly vehicle automation develops.

Robotaxis also change the curb...Pickup and drop-off is emerging as another important interface between cities and automated mobility.

When an AV repeatedly stops in an inappropriate location, the immediate issue may be vehicle behavior. But repeated conflicts may also reveal a deeper infrastructure problem: people are trying to access a destination for which the city has not provided an appropriate pickup or drop-off space.

That transforms an operational complaint into planning information.

As ride-hailing and robotaxis increase demand for short-duration curb access, cities may need to reconsider how much curb space is allocated to parking compared with passenger loading, deliveries, cycling infrastructure and other uses.

The arrival of automated vehicles therefore reinforces a trend that was already underway: the curb is becoming active mobility infrastructure rather than simply a place to store vehicles.

Incident reporting can support continuous improvement...Austin has also developed a public dashboard for autonomous vehicle incidents reported by residents, first responders and city staff.

Importantly, the objective is not simply to count incidents. Repeated reports can help determine whether a problem originates with vehicle behavior, infrastructure, temporary traffic control or another part of the transportation system.

That information can then be discussed with AV companies — and can also trigger changes on the city side.

This creates something cities will increasingly need as automated mobility scales: a structured feedback loop between technology providers, public agencies and road users.

Cities should define their expectations now...One of the most important lessons from Austin is therefore that cities do not need to wait for comprehensive AV regulatory authority before preparing.

They can already identify what they expect from operators.

They can prepare first responders.

They can improve road and curb infrastructure.

They can establish channels for incident reporting and learning.

They can determine what operational data would be useful.

And they can start asking how automated mobility should support existing public objectives — from Vision Zero and accessibility to transit integration and efficient use of public space.

The infrastructure decisions cities make today will remain long after today’s generation of autonomous vehicles has changed.

AV readiness should therefore not be about redesigning a city around a particular technology.

It should be about building a transportation system capable of accommodating new technologies while continuing to serve the public interest.

Cities can make room for robotaxis by implementing strategic urban planning, proactive regulatory frameworks, and infrastructural adjustments. Instead of letting autonomous vehicle (AV) companies dictate street design, cities can actively manage how robotaxis integrate into the existing transport ecosystem to prevent gridlock and complement public transit.

Here are the key strategies cities are using to make room for robotaxis safely and efficiently:

1. Smart curb management & dedicated hubs: To prevent robotaxis from blocking traffic during pickups and drop-offs, cities must rethink curb space.

• Designated pickup/drop-off points: Moving away from door-to-door service by establishing fixed, off-street pickup zones reduces sudden stops on busy roads.

• Dedicated waiting areas: Creating geofenced staging lots for empty robotaxis ensures they don't constantly idle or circle public streets while waiting for the next fare.

2. Upgrading digital and physical infrastructure...While AV companies train vehicles to navigate existing roads, physical and digital optimizations dramatically increase safety and efficiency.

• Enhanced lane visibility: Maintaining high-contrast lane markings and clear, standardized road signage helps vehicle cameras interpret the environment flawlessly.

• Live data sharing: Cities can feed real-time data regarding sudden road closures, construction zones, and special-event traffic directly to AV operators.

• Anti-degradation tech: Addressing "urban canyons" by mapping satellite signal degradation between skyscrapers helps maintain precise vehicle localization.

3. Reclaiming redundant parking space...As private car ownership drops and automated fleets use less stationary parking, massive amounts of urban real estate open up.

• Expanding active mobility: Cities can systematically convert redundant street parking into wider sidewalks, protected bike lanes, and green infrastructure.

• Low-traffic neighborhoods: Designating specific zones or school districts where robotaxis are strictly slowed down or entirely excluded prioritizes pedestrian safety.

4. Directing traffic with pricing and regulations...Without dynamic regulatory boundaries, cheap autonomous rides risk overwhelming roads and undercutting mass transit.

• Congestion and "empty mile" fees: Taxing operators for vehicles circulating without passengers discourages constant cruising.

• Prioritizing shared rides: Implementing road-pricing structures that favor pooled or high-occupancy AVs over single-passenger "driverless taxis" maximizes road capacity.

5. Integrating with public transit...The most successful integrations position robotaxis as a "first-mile, last-mile" extension of mass transit, rather than a competitor.

• Transit partnerships: Setting up service agreements where transit agencies dictate service boundaries, implement fare caps, and manage bookings within a unified public transit app (similar to pilots in Oslo and Dallas).

• Suburban coverage: Incentivizing fleets to service low-density outer suburbs helps connect isolated riders to central train or bus terminals