Drone Dataset for Complex Vehicle-VRU Interactions

VRUD

A vehicle-VRU interaction dataset with 13,418 trajectories, 87% VRU proportion, and 4,000+ interaction scenarios — built to study how cars, pedestrians, and cyclists actually negotiate shared space.

Raw drone footage
Standardized trajectories + HD map --
Loading video…
Loading map…
00:00 / 00:00

Drag the slider to compare raw drone video with standardized trajectories on the HD map — vehicle ↔ VRU interactions at an urban intersection (site 22).

Dataset Overview

VRUD inverts the typical vehicle-centric ratio of autonomous-driving datasets, providing a dense statistical basis for vulnerable road user safety research.

VRU-First

Of 13,418 trajectories, 87% are VRUs — pedestrians, cyclists, and e-bike riders. The dataset is dimensioned for VRU-focused research, not as a side-effect of vehicle recordings.

Interaction Scenarios

4,000+ tagged interaction scenarios where a vehicle and at least one VRU influence each other's path or speed — gap acceptance, crossing, conflict, and yielding behaviors.

Unobstructed View

Top-down drone capture eliminates ego-vehicle occlusion — the bias that distorts ground-level VRU datasets. Clean trajectories at high temporal resolution.

Key Numbers

Headline metrics from the VRUD release.

13,418
Trajectories
87%
VRU Proportion
4,000+
Interaction Scenarios
4K
Aerial Resolution

What's Included

Each release ships with rich kinematic, contextual, and interaction-level fields, ready for direct scenario analysis.

Per-Trajectory Fields

  • Position (x, y) & velocity (vx, vy)
  • Longitudinal & lateral acceleration
  • Heading angle
  • Agent type (car / pedestrian / cyclist / e-bike)
  • Persistent track ID across frames
  • Per-frame timestamps
  • Lane / sidewalk / crosswalk reference
  • Surrounding agent IDs by class

Interactions & Safety

  • Vehicle ↔ VRU pair conflict tagging
  • Distance to VRU (DTV)
  • Time-to-collision (TTC) & minTTC
  • Post-encroachment time (PET)
  • Yielding / gap-acceptance flags
  • Crossing trajectory segmentation
  • Per-recording metadata file
  • Zone tagging (school / market / community exit)

How to Cite

Please cite the VRUD paper in any publication that uses this dataset.

"VRUD: A Drone Dataset for Complex Vehicle-VRU Interactions within Mixed Traffic"

Jilin University AD Safety Joint Lab · DRIVEResearch

Application for Access

Free for non-commercial academic research. We review every request manually and typically respond within 5 business days.

Application is submitted via our Feishu form. We typically respond within 5 business days.
No Feishu account required — choose "Fill in as guest" on the login screen if you don't have one.

Open Application Form →

Other Open Datasets

Companion open datasets from the lab and partner institutions, covering different road types and traffic agents.