Static HTML snapshot of the model record for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Model | MILE |
| Lab / Organization | Wayve |
| Category | Foundation World Model |
| Subtype | Driving World Model |
| World Model Type | Model-based imitation learning for driving |
| Primary Domain | Autonomous Driving |
| Architecture | Variational autoencoder with spatial-temporal transformer for dynamics prediction |
| Modality | Visual (Multi-camera) + Ego-state |
| Training Method | Model-based imitation learning with future imagination rollouts |
| Status | active |
| Year | 2022 |
| Performance Index | 63/100 (medium confidence, v1.1) |
Main editorial body preserved directly in static HTML.
MILE (Model-based Imitation LEarning) is a world model for autonomous driving that learns a joint representation of scene dynamics, semantic segmentation, and ego-vehicle planning from camera-only input. Unlike modular driving stacks, MILE uses a learned world model to imagine future driving scenarios and optimize planning within that imagination, achieving state-of-the-art performance on the CARLA benchmark. It pioneered the concept of world-model-based end-to-end driving.
MILE is a model-based imitation learning for driving developed by Wayve in 2022 for autonomous driving.
Short extractable facts for answer engines and no-JS readers.
| Signal | Value |
|---|---|
| Definition | MILE is a model-based imitation learning for driving developed by Wayve in 2022 for autonomous driving. |
| Short Description | A world model for autonomous driving that jointly learns dynamics, perception, and planning through model-based imitation learning. |
| Benchmark Rows | 1 |
| FAQ Entries | 2 |
| Related Models | 3 |
| Related Guides | 0 |
| Related Research Topics | 0 |
| Last Updated | 2026-04-07 |
Key capabilities associated with this model.
Representative applications attached to this model record.
Balanced assessment surfaced in static HTML.
Published benchmark evidence attached to this model record.
| Benchmark | Metric | Result | Source |
|---|---|---|---|
| CARLA Benchmark | Driving Score 81 DS | State-of-the-art | Source |
Primary references preserved in static HTML for citation extraction.
| Reference | Link |
|---|---|
| Hu et al., 2022. Model-Based Imitation Learning for Urban Driving. NeurIPS 2022. arXiv:2210.07729 | Open source |
Nearby models linked from the current editorial record.
| Model | Category | World Model Type | Index v1.1 |
|---|---|---|---|
| GAIA-1 | Foundation World Model | Generative driving world model | 61/100 |
| Copilot4D | Foundation World Model | Spatiotemporal LiDAR world model | 57/100 |
| NVIDIA Cosmos | Foundation World Model | Video world foundation model | 87/100 |
Side-by-side comparisons already connected to this model.
| Comparison | Matchup | Summary |
|---|---|---|
| MILE vs GAIA-1 | MILE vs GAIA-1 | Both from Wayve, these models represent two generations of driving world models. MILE focuses on actionable imagination for planning, while GAIA-1 scales to photorealistic scenario generation. |
FAQ answers rendered directly into static HTML for extractable responses.
MILE uses a VAE-based world model for imagination-based planning and focuses on decision-making. GAIA-1 is a larger generative model that produces high-fidelity video predictions but doesn't directly plan actions.
MILE was primarily evaluated in the CARLA simulator. Wayve has since developed real-world driving systems inspired by MILE's world-model approach.
Short extractable summary preserved directly in static HTML.
Editorial provenance and refresh policy preserved directly in static HTML.
Published by world-models.io editorial board.
Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.
This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.
Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-04-07.
Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.
Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.
Primary model and lab sources embedded in static HTML.