Human Trajectory Prediction Benchmark

We propose a comprehensive trajectory prediction dataset A-to-X that consists of a representative set of trajectories, which will enable better generalization under realistic circumstances that are either complex or unsafe and out-of-distribution (OOD) with respect to current datasets.

Entire Dataset (Agent-to-Agent Interactions + Agent-to-Environment Interactions)


A2X

DatasetA2X
Description
Samples
Train/Test Ratio

Agent-to-Agent Interactions


A2A (Complete)

DatasetA2A (Complete)
Description
Samples
Train/Test Ratio

CFF

DatasetCFF
Description
Samples
Train/Test Ratio

LCAS

DatasetLCAS
Description
Samples
Train/Test Ratio

ORCA

DatasetORCA
Description
Samples
Train/Test Ratio

TrajNet

DatasetTrajNet
Description
Samples
Train/Test Ratio

Wildtrack

DatasetWildtrack
Description
Samples
Train/Test Ratio

Agent-to-Environment Interactions


A2E (Complete)

DatasetA2E (Complete)
Description
Samples
Train/Test Ratio

Bottleneck

DatasetBottleneck
Description
Samples
Train/Test Ratio

Pathfinding

DatasetPathfinding
Description
Samples
Train/Test Ratio