TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for Autonomy
This work addresses the problem of building generalist agents with enhanced embodied reasoning for autonomy applications, though it appears incremental as it builds on existing world model and transformer frameworks.
The authors tackled the challenge of modeling real-world environments that change across space and time by introducing a spatio-temporal road image dataset (STRIDE) and a transformer-based generative world model (TARDIS), achieving robust performance in tasks like photorealistic image synthesis and georeferencing.
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.