Learning to Car-Follow Using an Inertia-Oriented Driving Technique: A Before-and-After Study on a Closed Circuit
November 01, 2025 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Kostantinos Mattas, Antonio Lucas-Alba, Tomer Toledo, Oscar M. Melchor, Shlomo Bekhor, Biagio Ciuffo
arXiv ID
2512.13694
Category
cs.HC: Human-Computer Interaction
Cross-listed
cs.CY,
cs.RO
Citations
0
Venue
arXiv.org
Last Checked
4 months ago
Abstract
For decades, car following and traffic flow models have assumed that drivers default driving strategy is to maintain a safe distance. Several previous studies have questioned whether the Driving to Keep Distance is a traffic invariant. Therefore, the acceleration deceleration torque asymmetry of drivers must necessarily determine the observed patterns of traffic oscillations. Those studies indicate that drivers can adopt alternative CF strategies, such as Driving to Keep Inertia, by following basic instructions. The present work extends the evidence from previous research by showing the effectiveness of a DI course that immediately translates into practice on a closed circuit. Twelve drivers were invited to follow a lead car that varied its speed on a real circuit. Then, the driver took a DI course and returned to the same real car following scenario. Drivers generally adopted DD as the default CF mode in the pretest, both in field and simulated PC conditions, yielding very similar results. After taking the full DI course, drivers showed significantly less acceleration, deceleration, and speed variability than did the pretest, both in the field and in the simulated conditions, which indicates that drivers adopted the DI strategy. This study is the first to show the potential of adopting a DI strategy in a real circuit.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted