How Singapore is testing autonomous vehicles for a driverless future 

Niels de Boer, Programme Director of the Centre of Excellence for Testing & Research of Autonomous Vehicles NTU, shares how the organisation is supporting Singapore’s autonomous vehicle vision.

In the “Avengers: Age of Ultron”, Iron Man’s Audi R8 flagrantly flaunts its self-driving capabilities, recklessly steering itself out of harm’s way as it cruises along the villain-ridden streets. But in reality, autonomous vehicles are a lot more conservative.
Self-driving vehicles have the potential to reduce the occurrence of traffic accidents and keep the roads safer for all. Helping Singapore achieve this is the Centre of Excellence for Testing & Research of Autonomous Vehicles NTU (CETRAN).
Niels De Boer, Programme Director of CETRAN, highlights how the organisation supports Singapore’s Land Transport Authority in developing test requirements and standards for autonomous vehicles.

Singapore’s autonomous vehicle vision

Autonomous vehicles (AVs) are part of the vision of a car-lite Singapore. That is, to reduce people’s reliance on cars and promote the use of alternative transportation.
AV fleets could function as on-demand shuttle services between homes and workplaces, as well as public transport nodes to help improve first-and-last-mile connectivity.
Although bus and train services might cover the main part of a trip, people still need to walk, cycle, or use another method to get to and from the nearest station or stop. This is a gap that AVs hope to fill.
“Moreover, given the manpower constraints in the transportation sector, we can harness AVs to alleviate labour shortages,” Boer says.

CETRAN test centre

To support the development of AVs, CETRAN performs physical testing of the vehicles in its test centre as part of the approval process for on-road trials. The test centre is built to mimic Singapore’s public roads and contains typical urban environment features such as zebra crossings, speed humps, and parking lots.

CETRAN test centre. 
It also uses a digital twin of the test track to create virtual obstacle courses.
“We can stimulate digital road hazards, such as vehicles emerging from junctions and children running onto the roads without having to coordinate real-life logistics,” Boer says. This not only helps to save costs but also expands the type of testing CETRAN can perform without any actual risk. The centre has tested over 50 AV projects so far.
In 2020, Nanyang Technological University and Volvo Buses launched the world’s first full-size, autonomous electric bus. At 12 metres long and with a full capacity of close to 80 passengers, this project stands out in Boers’ memory. “It is impressive that a vehicle this big can run autonomously on the tight corners in our test track,” he highlights.
Unlike regular buses, this particular electric vehicle produces zero emissions and uses 80 per cent less energy than a diesel bus of the equivalent size.
The bus is also equipped with a global navigation satellite system that runs in parallel with an inertial management unit that measures speed and movement. This improves the bus' navigation when going over uneven terrain and around sharp bends, ensuring a smoother ride for passengers.

The world’s first full-size, autonomous electric bus launched by Nanyang Technological University and Volvo Buses. 
Another notable project is autonomous road sweepers. Most vehicles are designed to drive in the middle of the lane. But road sweepers are meant to follow the curb and move dynamically from one area to another, so the organisation had to reframe its testing approach.
This piece of technology could change the future of road sweeping as autonomous road sweepers can be used during the wee hours of the morning or late into the night. Street sweeper personnel need not inconvenience themselves during these hours.

Addressing the blindspots of autonomous vehicles

CETRAN has also collaborated with automation company Siemens to develop a vehicle-to-infrastructure communication system. This is a model that allows road components such as traffic cameras, traffic lights, and parking meters to share information with vehicles.
“For example, we can place sensors at the top of a lamppost to monitor road conditions and wirelessly send this information to AVs nearby,” Boers says. This allows self-driving vehicles to make better decisions as they receive data on potential hazards they would not have been able to capture otherwise.

Developing autonomous vehicle requirements

The bulk of CETRAN’s work lies in developing AV requirements, which is a challenge because the driving scene in Singapore is tightly regulated.
"The process of getting a driving license is tedious, regular inspections on vehicles are mandatory, and the Land Transport Authority watches over the car modification scene like a hawk," Boer explains.
But AVs are a whole other ballgame.
For example, mirrors are a very important part of any vehicle, but with the human driver out of the picture, they are no longer essential. “Instead, what we need are better cameras as driverless cars have computer vision and their field of sight is more comprehensive,” Boer says.
In addition, traffic conditions are ever-changing. Trying to govern every aspect of road user interactions is nearly impossible.
For instance, Singapore drivers learn that they have to turn on their headlights after 7 pm for better road visibility. But what should AVs do if it is already dark before 7 pm, or still bright after 7 pm? Strictly adhering to a manuscript is not always ideal because traffic is not prescriptive.
Then comes the duty of care expected of all road users. Motorists are obliged to ensure that any action they take does not cause injury to others or damage to property. “A driver can complain about an illegal pedestrian crossing but that still doesn’t give them the right to hit a person,” Boer shares.
Similarly, AVs need to know the distinction and not just stick to black and white traffic rules.
To navigate these vague traffic boundaries, CETRAN adopts a watch-and-learn approach. As they conduct safety checks, they learn what is important to regulate and control.
One example of this is the quality of sensors, which have to detect pedestrians and other vehicles from certain distances. “They also have to be adequately responsive to lane markings, traffic signs, and traffic lights,” Boer says.
CETRAN is at the forefront of supporting AV testing and deployment. Iron Man may own the flashiest self-driving cars, but the nation triumphs in the safety of AVs.