SaferTramDriving – SaferTramDriving

Since the 2000s, tramways have become established in many cities as the main mode of public transport. Tramways are an attractive form of surface mass transit (high passenger flow, safe solution, clean energy) for local authorities. Furthermore, its cost is also lower than that of the other mass transit system: the metro. Indeed, the installation of a tramway generally generates fewer infrastructure-related constraints, as it integrates into an existing environment with other road users (cars, motorized and non-motorized two-wheelers, etc.) and pedestrians. However, this multiplicity of players in the tramway's traffic zone makes driver’s task very demanding. Anticipation is the key to safety in urban visual driving, as the stopping distances of railway equipment are very long and avoidance maneuvers are impossible. This makes the driver state at the core of the safety of the tramway, as he/she must be constantly attentive to prevent any risk of collision with third parties, whether moving or stationary, in a context where the field of view is sometimes severely reduced (masking by buildings, street furniture, signs, etc.).
In this context, the perceptual and cognitive workload of tramway drivers can be high, which in fine can affect driver performance. Since the 1950s, research has demonstrated the causal link between workload and performance. A human operator with a low workload will see his/her level of attention decrease, and therefore his/her performance. In the same way, an operator with a heavy workload will experience increased fatigue and, ultimately, reduced performance. In performing the driving task, there is therefore an optimal workload range within which the driver can maintain good performance over a longer period of time. With this in mind, the goal of the project is to keep the driver’s workload in an optimal range, using an advanced driving assistance system (ADAS) that self-adapts in real-time. Doing so requires upstream to estimate the driver state and to estimate the task demands to cope with the situation in the current driving environment. Considering these two estimates, the best way to assist the driver can be determined in modulating the requirements of the driving task (reducing the driver's load or increasing it if necessary) in order to keep the driver in the optimum performance zone.
The project approach relies on a consortium with expertise in:
- tramway operation, safety and regulations (operator, public authority);
- knowledge of the mechanisms involved in the evolution of human vigilance/attention (expert company in human factors);
- design of virtual sensors based on these mechanisms, and of driver assistance systems (transport research laboratory with an automatic control department);
- virtual tramway simulation (company specialized in simulation).
This approach will take into account the “GAME” principle (“Globalement Au Moins Équivalent” / “Globally At Least Equivalent”) defined by transport regulations and aimed at maintaining an overall level of safety.
In fine, the SaferTramDriving project aims to develop a system providing:
1. An estimate of the driver's actual state, notably his/her level of attention, without disturbing the driving task, i.e. without adding a new task to the driver;
2. An estimate of the driving task demands, based on the state of the current driving environment (obstacles detection, speed profile, etc.);
3. An advanced driving assistance, which can adapt in real-time using the previous information, allowing the driver's load to be modulated to better control his/her vigilance and attention.
To ensure the efficiency of the system elaborated regarding the need of safety improvement, a part of the project will be dedicated to prototype and evaluate this system. The evaluation will be carried out with professional tramway drivers coming from several French networks, using a demonstrator developed as part of the project and based on a full-scale tramway simulator.