Autonomous Understanding Through Open-world Perception and Intigrated Language Models for On-road Tasks

In conjunction with The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

Wed June 3 - Sun June 7, 2026 | Denver, Colorado, USA

About AUTOPILOT

AUTOPILOT is a workshop on safety-critical autonomous driving, spotlighting robust perception and trajectory forecasting that support reliable decision-making and motion planning. It emphasizes the practical use of foundation models, vision-language and generative, through efficient distillation for on-vehicle deployment. A core theme is open-world learning, addressing Out-of-Distribution (OOD) and known hazards by detecting, predicting, and mitigating novel objects, agents, and events beyond standard taxonomies. AUTOPILOT features invited talks from leading industry experts, an open challenge, and archival proceedings, bringing academia and practitioners together to develop real-world solutions with explicit attention to societal impact, ethics, and reproducible evaluation.

Invited Speakers

Jose M. Alvarez

Nvidia

Dragomir Anguelov

Waymo

Manmohan Chandraker

NEC

Aniruddha Kembhavi

Wayve

Bat-El Shlomo

ZOOX

Nemanja Djuric

Aurora

Submission

The AUTOPILOT workshop invites full paper submissions (up to 8 pages, including figures and tables but excluding references), as well as abstracts and position papers of up to 4 pages (excluding references).

Submission Guidelines

All papers must be submitted via the ICCV 2025 OpenReview workshop website.
Submission should be PDF format and follow the official CVPR 2026 template and guidelines.
Submissions must be original, unpublished work (no concurrent submissions).
Authors may upload optional supplementary materials, containing additional details, videos, images, etc.
Papers should follow the ICCV author guidelines and be anonymized for double-blind review.
The accepted papers will be presented as oral, spotlight, or poster presentations.
Accepted papers will be published in the official ICCV workshop proceedings.
The presentation of accepted papers at our workshop will follow the same policy as that for the accepted papers at the ICCV 2025 leading conference.

We invite the submission of original, high-quality research papers on topics related to advancing the next frontier of safe autonomous driving to the AUTOPILOT workshop.

Topics

Topics of interest include, but are not limited to:

Foundational models for autonomous driving systems.
Detection, recognition, prediction, and mitigation of novel or out-of-label hazards in autonomous driving.
Risky event understanding, including accident anticipation and risk assessment.
Human activity recognition, psychological understanding, such as pedestrian behavior, group crossing dynamics, trajectory, or intent prediction.
Novel datasets, benchmarks, and evaluation protocols, especially for out-of-distribution or rare hazard scenarios.
Vision-based perception and scene understanding include recognition of traffic signals, road signs, markings, and dynamic agents.
Vision-Language and multimodal learning models for enhanced situational awareness and decision-making.
Human factors and human-robot interaction (HRI) in autonomous driving, including trust, interface design, and driver/passenger behavior.
Explainable and interpretable AI (XAI) techniques to improve transparency, accountability, and user trust in autonomous systems.

Submission Portal