Safe and Defensive Autonomous Driving Workshop

About

SDAD (Safe and Defensive Autonomous Driving) is an ECCV 2026 full-day workshop in Malmö on September 9, 2026. We organize around three core problems:

What dangers appear in driving scenes—including latent hazards that are difficult to observe?
How can autonomous vehicles learn defensive driving under uncertainty and long-tail situations?
How can we evaluate defensive driving behaviors beyond trajectory-centric benchmarks?

Program

September 9, 2026 · Full-day workshop, 09:00–17:35. 6 keynote talks, oral sessions with 4 papers, poster sessions, a panel discussion, and the best paper awards.

$300 Best Paper Award
$200 Best Paper Honorable Mention ×2

Morning

09:00–09:15 Welcome Speech
09:15–09:45 Keynote Talk 1 Chong Ruan
AI Safety in DeepRoute: System and Methods
09:45–10:15 Keynote Talk 2 Dan Levi
Foundation Models for General Full Autonomy
10:15–10:30 Coffee break
10:30–11:00 Oral Session (2 × 15 min)
1. Seeing the Evidence, Not Just the Answer: Training-Free SalMask Evidence Routing for Traffic Accident Video Understanding
2. RoCA: Robust Cross-Domain End-to-End Autonomous Driving
11:00–12:15 Poster Session
12:15–14:00 Lunch Break

Afternoon

14:00–14:30 Keynote Talk 3 Jun Gao
Closed-Loop Simulation for Autonomous Vehicle
14:30–15:00 Oral Session (2 × 15 min)
1. Worst-Case Hidden-Vehicle Trajectory Search in Spatiotemporal Occlusion Regions
2. RareOcc: Controllable 4D Occupancy and LiDAR Generation for Long-Tail Driving Scenes
15:00–15:30 Coffee break
15:30–16:00 Keynote Talk 4 Andreas Geiger
Learning and Evaluating Defensive Driving Honestly
16:00–16:30 Keynote Talk 5 Boyi Li
Teaching Robots from Videos with Generative Signals
16:30–17:00 Keynote Talk 6 Dragomir Anguelov
Expressive World Models for Closed Loop Evaluation and Model Training
17:00–17:30 Panel Discussion Host: Qifeng Chen
17:30–17:35 Award and Closing

Keynote Speakers

Andreas Geiger

Professor of Computer Science

University of Tübingen

Learning and Evaluating Defensive Driving Honestly

Dragomir Anguelov

VP and Head of Research

Waymo

Expressive World Models for Closed Loop Evaluation and Model Training

Jun Gao

Assistant Professor

University of Michigan

Closed-Loop Simulation for Autonomous Vehicle

Chong Ruan

Chief Scientist

DeepRoute.Ai

AI Safety in DeepRoute: System and Methods

Boyi Li

Postdoctoral Researcher

UC Berkeley

Research Scientist

NVIDIA Research

Teaching Robots from Videos with Generative Signals

Dan Levi

Foundational AI Research Group Lead

General Motors - Autonomous Vehicles

Foundation Models for General Full Autonomy

Call for Papers

We invite non-archival submissions on defensive driving, latent hazards, learning under uncertainty, and evaluation beyond trajectory-centric benchmarks. Reviews run on OpenReview; accepted work is presented as posters, with oral presentations and best-paper awards ($300 Best Paper; two $200 Honorable Mentions).

Submission deadline: July 15, 2026

Submit to OpenReview Dates, rules & review

Accepted Papers

Eighteen papers were accepted to SDAD 2026, four of them selected for oral presentations. Together they span latent hazard anticipation, planning under occlusion and uncertainty, critical scenario generation, and evaluation protocols that go beyond trajectory-centric benchmarks.

Abstracts and camera-ready PDFs for each accepted paper.

Browse accepted papers

Organizers

Qifeng Chen

Associate Professor

HKUST

Alexandre Alahi

Associate Professor

EPFL

Bo Li

Associate Professor

UIUC

Yiyi Liao

Assistant Professor

Zhejiang University

Li Erran Li

Head of Science

AWS AI

Tongyi Cao

CTO

DeepRoute.Ai

Student Co-Organizers

Zhili Chen PhD Student HKUST
Qiang Wen Researcher DeepRoute.Ai
Jiaqi Tang PhD Student HKUST
I Chieh Chen PhD Student HKUST

Safe and Defensive Autonomous Driving Workshop on ECCV 2026

About

Program

Morning

Afternoon

Keynote Speakers

Andreas Geiger

Dragomir Anguelov

Jun Gao

Chong Ruan

Boyi Li

Dan Levi

Call for Papers

Accepted Papers

Organizers

Qifeng Chen

Alexandre Alahi

Bo Li

Yiyi Liao

Li Erran Li

Tongyi Cao

Student Co-Organizers

Sponsors