Jens-Patrick Andre Bjerk Langstrand

Contact

Academic interests

Applied Machine Learning
Sensor Fusion
Vehicle Safety

Background

Jens-Patrick Langstrand received his master's degree in applied computer science from Østfold University College in 2016. He has been working as a researcher at the Institute for Energy Technology since. His research focus has been on applied Machine Learning for Human Factors research. He started his Doctorate Degree study in 2020 on sensing, control and testing in a warning system for slippery road conditions. The goal is to improve tyre-road friction estimation through physical modelling and sensor fusion. The project is part of the CRItical SPeed function and Automatic speed control function ahead of a dangerous road section (CRiSp) project.

Research Groups

Cyber-physical systems

Research groups

Cyber-physical systems

Langstrand, Jens-Patrick Andre Bjerk & Rabi, Maben (2023). Estimating road friction from kinematic summaries at curved sections. In Mastellone, Silvia (Eds.), Proceedings of the 2023 IEEE Conference on Control Technology and Applications (CCTA). IEEE conference proceedings. ISSN 979-8-3503-3544-6. p. 307–314. doi: 10.1109/CCTA54093.2023.10253194. Show summary
We present a system for estimating the friction of the pavement surface at any curved road section, by arriving at a consensus estimate, based on data from vehicles that have recently passed through that section. This estimate can help following vehicles. To keep costs down, we depend only on standard automotive sensors, such as the IMU, and sensors for the steering angle and wheel speeds. Our system’s workflow consists of: (i) processing measurements from vehicular sensors, (ii) transmitting short kinematic summaries from vehicles to a road side unit (RSU), using V2X communication, and (iii) estimating the friction coefficients, by running a machine learning regressor at the RSU, on summaries from individual vehicles, and then combining several such estimates.We study two key questions: (i) should each individual road section have a local friction coefficient regressor, or can we use a global regressor that covers all the possible road sections? and (ii) how accurate are the resulting regressor estimates? We test the performance of design variations of our system, using simulations of normal driving scenarios at curved road sections, using the commercial package Dyna4. We consider a single vehicle type with varying levels of tyre wear, and a range of road friction coefficients. We find that: (a) only a marginal loss of accuracy is incurred in using a global regressor as compared to local regressors, (b) the consensus estimate at the RSU has a worst case error of about ten percent, if the combination is based on at least fifty recently passed vehicles, and (c) our regressors have root mean square (RMS) errors that are less than five percent. The RMS error rate of our system is half as that of a commercial friction estimation service [7].But when tested with data from extreme driving manoeuvres that were unseen in the training data, our regressor performs an order of magnitude worse than on data from normal driving runs on curved road sections. Still our regressor’s RMS errors on such test data are no worse than the state of the art Artificial Neural Network regressors [18], [30].
Langstrand, Jens-Patrick Andre Bjerk; Randem, Hans Olav; Thunem, Harald & Hoffmann, Mario (2023). Using Deep Learning to classify road surface conditions and to estimate the coefficient of friction. In X, X (Eds.), 2023 IEEE Intelligent Vehicles Symposium (IV). IEEE (Institute of Electrical and Electronics Engineers). ISSN 979-8-3503-4691-6. doi: 10.1109/IV55152.2023.10186717.
Randem, Hans Olav; Langstrand, Jens-Patrick Andre Bjerk; Nguyen, Hoa Thi & Thunem, Harald P-J (2021). Detecting Overlapping Pharmaceutical Infusion Bags using Convolutional Neural Network. In Colomo-Palacios, Ricardo & Ripon, Kazi Shah Nawaz (Ed.), Proceedings of the International Conference on Applied Artificial Intelligence (ICAPAI) 2021. IEEE conference proceedings. ISSN 978-1-7281-5934-8. p. 1–6. doi: 10.1109/ICAPAI49758.2021.9462053.
Langstrand, Jens-Patrick Andre Bjerk; Nguyen, Hoa Thi & McDonald, Robert (2020). Applying Deep Learning to Solve Alarm Flooding in Digital Nuclear Power Plant Control Rooms. In Ahram, Tareq (Eds.), Advances in Artificial Intelligence, Software and Systems Engineering: Proceedings of the AHFE 2020 Virtual Conferences on Software and Systems Engineering, and Artificial Intelligence and Social Computing, July 16-20, 2020, USA. Springer. ISSN 978-3-030-51327-6. p. 521–527. doi: 10.1007/978-3-030-51328-3_71.
Hildebrandt, Michael; Nguyen, Hoa Thi & Langstrand, Jens-Patrick (2019). Synquesticon: An Environment for Authoring and Conducting Micro Task Studies. Proceedings of the Human Factors and Ergonomics Society Annual Meeting.. ISSN 1071-1813. p. 475–478. doi: 10.1177/1071181319631471.
Hildebrandt, Michael; Langstrand, Jens-Patrick & Nguyen, Hoa Thi (2019). Synopticon: A real-time data fusion platform for behavioral research. In x, x (Eds.), AutomotiveUI'19 Proceedings of the 11th International Conference on Automotive User Interfaces and Interactive Vehicular Applications:Adjunct Proceedings. Association for Computing Machinery (ACM). ISSN 978-1-4503-6920-6. p. 494–497. doi: 10.1145/3349263.3349597. Show summary
AutomotiveUI is the premier forum for user interface (UI) research in the automotive domain, bringing together researchers from both academia and industry. As in previous years, the papers and presentations of AutomotiveUI '19 target the development of novel vehicle technologies based on principled models and concepts that seek to enhance driver experience, safety, and performance; the development of semi and fully autonomous driving; and the needs of different user groups, including passengers and pedestrians.
Langstrand, Jens-Patrick; Nguyen, Hoa Thi & Hildebrandt, Michael (2018). Synopticon: Sensor fusion for real-time gaze detection and analysis. Proceedings of the Human Factors and Ergonomics Society Annual Meeting.. ISSN 1071-1813. 62(1), p. 311–315. doi: 10.1177/1541931218621072.
Nguyen, Hoa Thi; Langstrand, Jens-Patrick & Hildebrandt, Michael (2018). ReClass: An Application of Deep Learning for Real-time Reading Detection Using and Eye Tracking Device. Proceedings of the Human Factors and Ergonomics Society Annual Meeting.. ISSN 1071-1813. 62(1), p. 307–310. doi: 10.1177/1541931218621071.
Fernandes, Alexandra; Danielsen, Brit-Eli; Nguyen, Hoa Thi & Langstrand, Jens-Patrick (2018). Assessing human performance and fatigue in a control room during ISS operations. In NN, NN (Eds.), Proceedings of the 2018 SpaceOps Conference, (AIAA 2018-2543). American Institute of Aeronautics and Astronautics (AIAA). ISSN 978-1-62410-562-3. p. 1–11. doi: 10.2514/6.2018-2543. Full text in Research Archive

View all works in Cristin

Hildebrandt, Michael; Langstrand, Jens-Patrick & Nguyen, Hoa Thi (2020). Lessons Learned from Developing Gaze Tracking Tools for ATM and Flight Deck Training. Full text in Research Archive
Langstrand, Jens-Patrick; Nguyen, Hoa Thi & Michael, Hildebrandt (2018). Synopticon: Sensor Fusion for Real-Time Gaze Detection and Analysis.
Nguyen, Hoa Thi; Langstrand, Jens-Patrick & Hildebrandt, Michael (2018). ReClass: An Application of Deep Learning for Real-time Reading Detection Using and Eye Tracking Device.
Fernandes, Alexandra; Danielsen, Brit-Eli; Langstrand, Jens-Patrick & Nguyen, Hoa Thi (2018). Assessing Human Performance and Fatigue in a Control Room during ISS Operations.

View all works in Cristin

Published May 18, 2020 7:00 AM - Last modified Oct. 11, 2021 1:55 PM