Why these Challenges?

Autonomous driving is developing fast. Although still deemed important, the requirement for cutting-edge algorithms is no longer to achieve as high as mAP for object detectors, or to recognize lanes as conventional segmentation. We believe the future of autonomous driving algorithms is to bond perception closely with planning. As such, we introduce four curated, brand-new challenges following such a philosophy.

  • OpenLane Topology Challenge. Go beyond conventional lane line detection as segmentation. Recognizing lanes as an abstraction of the scene - centerline, and building the topology between lanes and traffic elements. Such a topology is to facilitate planning and routing.

  • Online HD Map Construction Challenge. Traditional mapping pipelines require a vast amount of human effort to maintain, which limits their scalability. This task aims to dynamically construct local maps with rich semantics based on onboard sensors. The vectorized map can be further utilized by downstream tasks.

  • 3D Occupancy Prediction Challenge. The representation of 3D bounding boxes is not enough to describe general objects (obstacles). Instead, inspired by the concept in Robotics, we deem general object detection as an occupancy representation to cover more irregularly shaped objects (e.g., protruding). The output could also be fed as cost volume for planning. This idea is also endorsed by Mobileye at CES 2023 and Tesla AI Day 2022.

  • nuPlan Planning Challenge. To verify the effectiveness of the newly-designed modules in perception, we need an ultimate planning framework with a closed-loop setting. Previous motion planning benchmarks focus on short-term motion forecasting and are limited to open-loop evaluation. nuPlan introduces long-term planning of the ego vehicle and corresponding metrics.

  • motivation
    Motivation of the Challenges: bond perception more closely with planning.


    Send E-mail Contact us via workshop-e2e-ad@googlegroups.com with the prefix [CVPR 2023 E2EAD].

    Join Slack Join Slack to chat with Challenge organizers. Please follow the guidelines in #general and join the track-specific channels.

    Join Wechat Join WeChat group to chat with Challenge organizers.


    Filling out this form for sign-up or feedback.


    For participation, you can create a team at EvalAI, and then make a submission. A valid submission would be automatically viewed as a successful participation. No more than ten individuals are allowed in a team. For more details please refer to FAQ and description in each track.


    The year 2023's edition of the Challenge is hosted by:

    Track 1
    OpenLane Topology

    GitHub GitHub GitHub EvalAI

    Task Description

    The OpenLane-V2 dataset* is the perception and reasoning benchmark for scene structure in autonomous driving. Given multi-view images covering the whole panoramic field of view, participants are required to deliver not only perception results of lanes and traffic elements but also topology relationships among lanes and between lanes and traffic elements simultaneously.