AMS Allegro: Unraveling slow mode traveling and traffic

To make the city a more cyclist and pedestrian friendly place, it’s imperative that people like city planners are able to make well-informed decisions. The project ALLEGRO thoroughly tracks and researches the behaviour of cyclist and pedestrians and uses this knowledge to develop tools that give decision-makers insight into the behaviour of these ‘slow mode’ travellers. This helps plan, design and manage the urban environment whilst taking pedestrians and cyclist into account.

Amsterdam has been a hot spot for bikes for ages, how come we still know so little about their behaviour?
Getting to grips with the ‘behaviour’ of cyclists and pedestrians is notoriously difficult. They have a terrific amount of freedom in movement and choice compared to for instance cars or public transport who are bound be far more by rules and regulations. Also think about the wide range of things that can influence bikers and pedestrians to choose routes, change routes, slow down, speed up or react to on-the-spot situations… This creates a major amount of factors you have to take into account and measure when predicting their movements.

Up until recently, collecting any aspect of this data was a very pricey, time consuming activity that often delivered inaccurate or undetailed information. But new ways to gather a fast amount of information, made an abundance of information become available, opening up the possibilities to get to know more about cyclists flows. This research for instance will not only be using information from sensors but also data from social media platforms and augmented reality just to name a few.

image-4511248

Photo: Until recently, collecting data on bike and pedestrian flows was very hard and time consuming activity. New technologies however have given the possibility to collect accurate and detailed information on cyclist and pedestrian flows more abundantly.

So you’ll be gathering this information then predict their movements?
Ultimately yes, but collecting, fusing and actually making sense from and using the data are all very complex task in themselves. That’s one of the reasons why the research is split up into three parts: one focused on collecting and fusing data, one on interpreting it and one on using the information for tools and stimulation models.

More on the research:
With a team of consisting of 8 PhD students and 3 postdocs led by Professor Serge Hoogendoorn. Through the use of big data collection and experimentation, analysis and a fusion techniques that combine data from social media, augmented reality, remote and crowd sensing amongst others – the research group is aiming to achieve major scientific breakthroughs in terms of both theory and modeling.

Visit the research page.