COMMOTIONS: Computational Models of Traffic Interactions for Testing of Automated Vehicles

As automated vehicles (AVs) are being developed for driving in increasingly complex and diverse traffic environments, it becomes increasingly difficult to comprehensively test that the AVs always behave in ways that are safe and acceptable to human road users. There is wide consensus that a key part of the solution to this problem will be the use of virtual traffic simulations, where simulated versions of an AV under development can meet simulated surrounding traffic. Such simulations could in theory cover vast ranges of possible scenarios, including both routine and more safety-critical interactions. However, the current understanding and models of human road user behaviour is not good enough to permit realistic simulations of traffic interactions at the level of detail needed for such testing to be meaningful. This fellowship aims to develop the missing simulation models of human behaviour, to ensure that development of the future automated transport system can be carried out in a responsible, human-centric way.

Behaviour of car drivers and pedestrians will be observed both in real traffic as well as in controlled studies in driving and pedestrian simulators, in some cases complementing behavioural data with neurophysiological (EEG) data, since several candidate component models make specific predictions about brain activity. The fellowship will then build on existing models of driver and pedestrian behaviour in routine and safety-critical situations, and extend these with state of the art neuroscientific models of specific phenomena like perceptual judgments, beliefs about others' intentions, and communication, to create an integrated cognitive modelling framework allowing simulations of traffic interactions across a variety of targeted scenarios.

Such cognitive interaction models, based on well-understood underlying mechanisms, will be one main contribution from the fellowship. Some researchers have suggested the use of another type of model altogether, instead obtained directly by applying machine learning (ML) methods to large data sets of human road user behaviour, i.e., without an ambition to correctly model underlying mechanisms. This fellowship hypothesises that to achieve reliable virtual testing of AVs, both types of modelling approaches will be needed, and methods for combining them will be researched. Not least, due to their "black box" nature, ML models need to be investigated and benchmarked, to for example determine their ability to generalise to rare, safety-critical events.

The multi-disciplinary research, building on and extending on the fellow's past experience in vehicle engineering, cognitive neuroscience, and machine learning, will be carried out at the Institute for Transport Studies, University of Leeds, with support also from the Schools of Psychology and Computing. The fellowship has direct support from industry, both in advisory capacities and as project partners actively sharing data and methods as well as providing first proof-of-concept uptake of the developed models into industrial environments for simulated testing.

The primary, long-term impact that the project envisions, and which it will actively work towards, is the development and successful deployment of safe and acceptable automated vehicles (AVs). There are large hoped-for economical and societal benefits from transport automation. Long-term, the global economy for AVs and AV-enabled services is projected to be worth trillions of pounds per year, and the UK government is targeting a leading role for the UK in this economy, with an estimated £51 billion annual benefit for the UK economy and 300,000 new jobs by 2030, as well as reductions in road traffic injuries and death, improved inclusive mobility, reduced congestion, and increased productivity.

However, a primarily technology-driven approach to automation, without proper consideration of human behaviour, risks resulting in AVs that behave in ways that are unappreciated by, and potentially unsafe to human road users. If AVs for example cause traffic jams because they are overly cautious, or misinterpret human road user behaviour in ways that lead to crashes, public acceptance and market penetration will suffer, which could in turn severely limit the abovementioned potential benefits. The human behaviour models and virtual testing simulations developed by this project will help mitigate against these risks, by providing a direct means of supporting human-centred, responsible innovation on vehicle automation, to develop AV technology that puts human behaviour, capabilities and well-being first. The project therefore holds promise of impact both at the level of the individual UK citizen, in terms of a safer and more desirable urban road traffic environment, as well as on the national level, giving the UK industry (vehicle manufacturers, suppliers, simulation tool developers, ...) and economy an edge over competitors, and as a result a greater share for the UK of the global market for automation.

Early impacts are expected already while the fellowship is active (2019-2023), in terms of first proofs of concept of the developed models in industrial simulation tools, as well as a raised awareness of the need for proper consideration of human road user behaviours in testing of AVs, among industry, general public, and policy makers. In the first years after the fellowship, this can in turn help drive policy-making on AV testing requirements, while in parallel the models should start to see actual use as part of industrial development processes. This will in turn support larger-scale deployment of safe and acceptable AVs in urban traffic in the UK and elsewhere, by current estimates circa 2025-2035.

Given that the project touches on a wide range of applied disciplines beyond just road vehicle automation, there are many more potential industrial and societal impacts. For example, transport planners can make use of improved traffic simulation tools to make better decisions on public spending on road traffic infrastructure. Furthermore, better models of human interactive locomotion and human situational awareness can be useful also outside the road traffic context, for example in the design of robots locomoting among humans, and of safety-critical environments like aircraft or nuclear power plants.