analiza aiqbench
This paper introduces the PDB dataset and Gate-SP baseline to advance personalized trajectory prediction by explicitly modeling individual driver identities using multimodal sensor data. The work demonstrates that incorporating driver-specific information can selectively improve motion forecasting accuracy, addressing a key limitation in existing autonomous driving benchmarks where driver identity is typically ignored.
PDB: Not All Drivers Are the Same -- A Personalized Dataset for Understanding Driving Behavior
arXiv:2503.06477v2 Announce Type: replace-cross Abstract: Driving behavior varies across individuals, yet most existing driving datasets do not preserve driver identity or control for factors that may affect driving style. We introduce the Personalized Driving Behavior (PDB) dataset, a multimodal dataset collected from 9 drivers using the same vehicle and route under comparable conditions. PDB includes data from a 128-line LiDAR, external and driver-facing cameras, GNSS, IMU, CAN-bus signals, and heart-rate measurements, with 111,060 frames of LiDAR point cloud data and more than 1.33 million images. Based on these recordings, we construct PDB-Traj, a personalized trajectory prediction benchmark with 1,309 10-second trajectory segments sampled at 10 Hz. Each segment includes the ego trajectory, surrounding-agent trajectories, and driver identity. We further introduce Gated Selective Personalization (Gate-SP), a driver-aware baseline that selectively incorporates driver identity into trajectory prediction. Experiments on PDB-Traj provide reference results for personalized motion forecasting and show that driver information can improve prediction when applied selectively. PDB and PDB-Traj provide a benchmark for studying driver-specific behavior and personalized trajectory prediction.
Authors:Chuheng Wei, Ziye Qin, Siyan Li, Ziyan Zhang, Xuanpeng Zhao, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Ziran Wang, Matthew J. Barth, Guoyuan Wu
Abstract:Driving behavior varies across individuals, yet most existing driving datasets do not preserve driver identity or control for factors that may affect driving style. We introduce the Personalized Driving Behavior (PDB) dataset, a multimodal dataset collected from 9 drivers using the same vehicle and route under comparable conditions. PDB includes data from a 128-line LiDAR, external and driver-facing cameras, GNSS, IMU, CAN-bus signals, and heart-rate measurements, with 111,060 frames of LiDAR point cloud data and more than 1.33 million images. Based on these recordings, we construct PDB-Traj, a personalized trajectory prediction benchmark with 1,309 10-second trajectory segments sampled at 10 Hz. Each segment includes the ego trajectory, surrounding-agent trajectories, and driver identity. We further introduce Gated Selective Personalization (Gate-SP), a driver-aware baseline that selectively incorporates driver identity into trajectory prediction. Experiments on PDB-Traj provide reference results for personalized motion forecasting and show that driver information can improve prediction when applied selectively. PDB and PDB-Traj provide a benchmark for studying driver-specific behavior and personalized trajectory prediction.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2503.06477 [cs.CV]
(or arXiv:2503.06477v2 [cs.CV] for this version)
Text integral sub licența deschisă a publicației · 205 cuvinte
Subiecte conexe
Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
arXiv · 31 iul. 2026
A class of statement between conjecture and theorem
LessWrong · 21 sept. 2026
PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
arXiv · 4 iun. 2026
Consumer Appetite for Personal AI Goes Mainstream
IEEE Spectrum · 29 oct. 2026