Waymo Motion Dataset for Autonomous Vehicle Prediction

Waymo Open Dataset Motion V 1.3.0 provides data for predicting the movement of road users. It is released by Waymo and was updated on HuggingFace in September 2025. The dataset is designed for tasks like motion forecasting and trajectory modeling.

Use Cases

• Predict future trajectories of vehicles and pedestrians using historical object tracks.
• Train multimodal prediction models to generate multiple plausible future paths for each agent.
• Develop sensor fusion algorithms using combined LiDAR and camera data for scene understanding.
• Benchmark motion forecasting models on real-world, large-scale driving scenarios.

Strengths

• Based on the established Waymo Open Dataset, known for its scale and realism.
• Version 1.3.0 indicates iterative improvements and updates over previous releases.

Limitations

• Specific row counts, column details, and data size are not provided in the metadata.
• The geographic and temporal coverage of the specific data split is unknown.

Provenance

Source

Waymo

Collection Method

Collected using Waymo's autonomous vehicle sensors in real-world driving environments.

Freshness

Last updated on the platform in September 2025.