Abstract
The aim of this research is to work towards building an open-source, platform-independent algorithm capable of predicting driver workload in real-time and in a non-intrusive way. To work towards a system that can also be implemented in on-road settings, we aimed at using off-the-shelf, non-intrusive sensors that could be implemented into the steering wheel and dashboard of current and future generations of cars, making them non-intrusive.
In order to build the initial predictive model, a driving simulator experiment was performed. Nineteen participants were required to drive a virtual replication of the Dutch A67 C-ITS corridor between Eindhoven and Venlo. We attempted to induce driver workload by varying weather, traffic composition, traffic density and by asking participants to perform various manoeuvres such as lane changing, merging and exiting. We measured heart rate, skin response, blink and performance measures.
Results show that within individuals and within the experimental group, workload was predictable with a high correct rate in both individual models as well as group models. We also evaluated how well the models would generalise when used outside of the experimental setting. Preliminary results for this generalisation are poor. We discuss possible reasons for this and next steps we are planning to take to increase this performance.
In order to build the initial predictive model, a driving simulator experiment was performed. Nineteen participants were required to drive a virtual replication of the Dutch A67 C-ITS corridor between Eindhoven and Venlo. We attempted to induce driver workload by varying weather, traffic composition, traffic density and by asking participants to perform various manoeuvres such as lane changing, merging and exiting. We measured heart rate, skin response, blink and performance measures.
Results show that within individuals and within the experimental group, workload was predictable with a high correct rate in both individual models as well as group models. We also evaluated how well the models would generalise when used outside of the experimental setting. Preliminary results for this generalisation are poor. We discuss possible reasons for this and next steps we are planning to take to increase this performance.
Original language | English |
---|---|
Title of host publication | Proceedings of the 6th International Conference on Road Safety & Simulation (RSS) |
Subtitle of host publication | 17-19 October 2017, The Hague, Netherlands |
Number of pages | 10 |
Publication status | Published - 2017 |
Event | RSS2017: Road Safety and Simulation International Conference 2017 - Grand Hotel Amrâth Kurhaus, The Hague, Netherlands Duration: 17 Oct 2017 → 19 Oct 2017 http://rss2017.org/ |
Conference
Conference | RSS2017: Road Safety and Simulation International Conference 2017 |
---|---|
Abbreviated title | RSS 2017 |
Country/Territory | Netherlands |
City | The Hague |
Period | 17/10/17 → 19/10/17 |
Other | The Road Safety and Simulation conference series was established in Rome in 2007, and has since then provided a bi-annual platform for researchers and professionals from various disciplines to share their expertise and latest insights in the field of road safety and simulation. Delft University of Technology (TU Delft) is delighted to host the 2017 Road Safety and Simulation (RSS) international conference. RSS2017 will be organised in collaboration with the Dutch Institute for Road Safety Research (SWOV). The RSS2017 conference covers a wide area of topics. Furthermore we introduce a special theme focusing on advancing the safety of all road users with special attention for vulnerable road users. Especially, in the upcoming era of advanced technologies and vehicle automation new safety challenges have emerged. The road infrastructure design plays a critical role in accommodating these challenges. |
Internet address |
Keywords
- driver workload
- Machine Learning
- workload prediction
- Driving simulator