TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for Autonomy

TL;DR

This paper introduces STRIDE, a comprehensive spatio-temporal road image dataset, and TARDIS, a transformer-based world model that effectively captures environment dynamics for autonomous agent tasks.

Contribution

It presents a novel dataset and a unified autoregressive transformer model for modeling complex spatio-temporal environment dynamics in autonomous systems.

Findings

Robust performance in image synthesis and instruction following.

State-of-the-art results in georeferencing tasks.

Demonstrates potential for generalist autonomous agents.

Abstract

World models aim to simulate environments and enable effective agent behavior. However, modeling real-world environments presents unique challenges as they dynamically change across both space and, crucially, time. To capture these composed dynamics, we introduce a Spatio-Temporal Road Image Dataset for Exploration (STRIDE) permuting 360-degree panoramic imagery into rich interconnected observation, state and action nodes. Leveraging this structure, we can simultaneously model the relationship between egocentric views, positional coordinates, and movement commands across both space and time. We benchmark this dataset via TARDIS, a transformer-based generative world model that integrates spatial and temporal dynamics through a unified autoregressive framework trained on STRIDE. We demonstrate robust performance across a range of agentic tasks such as controllable photorealistic image synthesis, instruction following, autonomous self-control, and state-of-the-art georeferencing. These results suggest a promising direction towards sophisticated generalist agents--capable of understanding and manipulating the spatial and temporal aspects of their material environments--with enhanced embodied reasoning capabilities. Training code, datasets, and model checkpoints are made available at https://huggingface.co/datasets/Tera-AI/STRIDE.