“In terms of congestion, Bangalore is one of the worst cities in India,” says Dr. Raghuram Krishnapuram, a senior scientist at the Centre of Data for Public Good (CDPG), Foundation for Science Innovation and Development (FSID), in Bengaluru’s Indian Institute of Science (IISc).
That traffic is as ubiquitous to the city as its pleasant weather, start-up ecosystem and green spaces is nothing new. In 2022, according to the TomTom Traffic Index, Bengaluru was ranked the world’s second-most congested city, only beaten by London for this dubious position. And while this has improved – Bengaluru dropped to 6th on this list in 2024 – it continues to be one of the country’s most congested cities, something any Bengalurean will attest to.
To address the problem, CDPG and the Bengaluru Traffic Police (BTP) have come together to organise a hackathon called The Bengaluru Mobility Challenge. The hackathon aims to provide innovative solutions to the city’s traffic woes using AI and geospatial technologies. “There is a huge potential to make a difference to Bangalore,” says Krishnapuram.
Data-driven solutions
FSID, previously called SID (Society for Innovation and Development), is IISc’s incubation centre, harnessing the scientific knowledge available at IISc to help society and industry. Among the initiatives that were seeded here was the India Urban Data Exchange (IUDX). The open-source platform was born out of the need to facilitate data exchange between various city departments, government agencies, citizens and the private sector, and to eventually help cities use this data to address complex urban challenges.
On November 24, 2023, when CDPG was created within FSID, IUDX became part of the new centre. Krishnapuram spells out the rationale behind CDPG: “The idea is that cities in India can leverage the data that they have to do impactful things.” “You can derive a lot of insights from the data and enable an entire ecosystem of start-ups that can use that data to build useful applications that will benefit society,” he adds.
Krishnapuram explains the mechanics behind how data could be used for public welfare using an example from Tripura’s capital, Agartala, which has partnered with IUDX. In late 2022, video data from various intersections in the city was collected to help monitor and regulate traffic. “For example, if there are a lot of vehicles accumulating in one direction, you can increase the duration of the green light, etc.,” he says, adding that since the roads are all interconnected, a lot of coordination is needed to ensure that traffic flows smoothly.
Although this particular traffic project did not go beyond the pilot stage, many more such projects are underway. Already, the platform has been installed in nearly 50 Indian cities and is being leveraged for various purposes. In Surat, for instance, IUDX is being used to monitor the bus transit system while in Chennai it is helping the city keep an eye on water levels in its reservoirs and predict floods. “It is also being used to set up green corridors and solid waste disposal schedules… those kinds of things,” he says.
The origin of the hackathon
At a symposium to mark the launch of CDPG back in November 2023, one of the speakers M.N. Anucheth, the Joint Commissioner of Police, Traffic, Bengaluru City, spoke about the traffic situation in the city and urged the city’s entrepreneurs to help address the problem. “So, we thought that maybe this would be a good problem to work on,” recalls Krishnapuram.
This led to the conceptualisation of The Bengaluru Mobility Challenge, which was announced earlier this month. The participants will rely on camera data provided by BTP. “Instead of just using the BTP cameras which are limited in number, we are leveraging the Safe City cameras to look at how many vehicles are passing in large parts of the city,” he says. If one can do AI-based analytics, this data can be used to model the city traffic, he adds. “Bangalore is a large city but it does not have a traffic model. No one knows the commuting patterns of people right now.”
Krishnapuram believes that insights from the data can help city planning and decision-making, whether it is about expanding the public transport system, designing alternative routes, deciding which roads should be one-way or putting in a metro line. “If you have this information, you can do a lot of things that make it easier for people to commute.”
Two phases
The hackathon, open to all residents of India, will consist of two phases, each of which will focus on different aspects of urban mobility management. The first phase will involve using data from Safe City cameras installed around IISc to predict vehicle counts and generate traffic patterns. Understanding these patterns can help predict traffic, which in turn can help police take action, he says. “This could help them regulate the traffic differently. For instance, close certain roads to divert the traffic.”
In Phase Two, on the other hand, participants will re-identify vehicles across different network locations and estimate origin-destination flows. This will help understand the behaviour of motorists in the city. Krishnapuram recognises that this is not an easy task given the number of vehicles that are similar to each other. However, he hopes that the data from this phase will help them test their hypotheses about driving behaviours.
Teams registering for the hackathon can have up to five members and choose to participate in either or both phases. “People don’t have to participate in the first phase to participate in the second phase,” he says. Alternatively, if a team wants to stop after the first phase, it can do so, but it needs to make its code public, putting it up in open source. “People that are participating in Phase Two, can make use of those results if they want to. But if they are continuing in Phase Two, they don’t have to do this.”
Feasibility and beyond
If the challenge is successful, they hope to scale it up to the entire city, but currently, the focus is on the feasibility aspect, he says. “We want to see if this data is useful…if you can do something with it, using AI and machine learning.” Existing AI algorithms for traffic developed using data from other countries, don’t necessarily work in Indian traffic, which he describes as “a different beast that is completely chaotic”. For instance, algorithms that do vehicle counts fail in India because we have rickshaws and bullock carts on the road, merrily trundling along buses, cars and motorbikes. “They are not recognised and end up not being counted. That is a challenge,” he says.
Krishnapuram believes that traffic solutions specific to Indian conditions could emerge out of this hackathon. “When you open the problem to so many people, everyone comes up with different ideas,” he says. Also, since the solutions are open source, he hopes that potential solutions that may emerge from the hackathon could well be replicated for the benefit of the entire city or even the country. “Traffic is a huge problem in India, and we have to find sustainable solutions,” he says.
Beyond traffic issues
And yes, using data meaningfully to address civic issues doesn’t just stop with traffic issues. “Traffic and transportation is one area, pollution and flooding are other problems. We are hoping that hackathons can help create awareness and good solutions.”
To know more or register, log into dataforpublicgood.org.in/bengaluru-mobility-challenge-2024
