TY  - JOUR
T1  - Inference on Driving Characteristic Based on Time-Series Partial Observation of Vehicle
AU  - Park, Sangeun 
AU  - Eom, Chanin 
AU  - Kwon, Minhae 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.6.858
KW  - Autonomous driving system
KW  - Driving characteristic inference
KW  - Partial observation
KW  - Transformer
KW  - Long short-term memory
KW  - Multi-layer perceptron
KW  - Trajectory data
AB  - With the commercialization of autonomous driving systems, inferring the driving characteristics of adjacent vehicles has become increasingly important for effective interaction between autonomous and non-autonomous vehicles. Driving information can be collected using roadside units or vehicles to infer these characteristics.
This study proposes a model that infers driving characteristics based on trajectory data collected within a limited observation range. Specifically, we confirm the practicality of the proposed system by considering noise that may occur during the sensing process and using real driving datasets. Simulation results demonstrate that the proposed model outperforms baselines and proves highly practical, even in environments with limited observation.