Knowledge Distillation Neural Network for Predicting Car-following Behaviour of Human-driven and Autonomous Vehicles
On the map: Knowledge distillation → Multimodal distillation
Abstract (arXiv)
As we move towards a mixed-traffic scenario of Autonomous vehicles (AVs) and Human-driven vehicles (HDVs), understanding the car-following behaviour is important to improve traffic efficiency and road safety. Using a real-world trajectory dataset, this study uses descriptive and statistical analysis to investigate the car-following behaviours of three vehicle pairs: HDV-AV, AV-HDV and HDV-HDV in mixed traffic. The ANOVA test showed that car-following behaviours across different vehicle pairs are statistically significant (p-value < 0.05). We also introduce a data-driven Knowledge Distillation Neural Network (KDNN) model for predicting car-following behaviour in terms of speed. The KDNN model demonstrates comparable predictive accuracy to its teacher network, a Long Short-Term Memory (LSTM) network, and outperforms both the standalone student network, a Multilayer Perceptron (MLP), and traditional physics-based models like the Gipps model. Notably, the KDNN model better prevents collisions, measured by minimum Time-to-Collision (TTC), and operates with lower computational power, making it ideal for AVs or driving simulators requiring efficient computing.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal distillation, one of 12 directions in Knowledge distillation. Builds on 3 of its 18 references that are in the map. First posted on arXiv 8 Nov 2024.
Builds on
3 of 18 references.
References · 3
- 2020Knowledge Distillation: A Surveycited by 1,603
- 2021Does Knowledge Distillation Really Work?cited by 190
- 2020Deep Learning in the Era of Edge Computing: Challenges and Opportunitiescited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024CAV-AHDV-CAV: Mitigating Traffic Oscillations for CAVs through a Novel Car-Following Structure and Reinforcement Learning
- 2025A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models
- 2026Macroscopic Characteristics of Mixed Traffic Flow with Deep Reinforcement Learning Based Automated and Human-Driven Vehicles
- 2024A Cognitive-Based Trajectory Prediction Approach for Autonomous Driving
- 2024Towards Selection and Transition Between Behavior-Based Neural Networks for Automated Driving
- 2022Adaptive Instance Distillation for Object Detection in Autonomous Driving
- 2018An LSTM Network for Highway Trajectory Prediction
- 2018Naturalistic Driver Intention and Path Prediction using Recurrent Neural Networks