English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

End-to-end autonomous driving recently emerged as a promising researchdirection to target autonomy from a full-stack perspective. Along this line,many of the latest works follow an open-loop evaluation setting on nuScenes tostudy the planning behavior. In this paper, we delve deeper into the problem byconducting thorough analyses and demystifying more devils in the details. Weinitially observed that the nuScenes dataset, characterized by relativelysimple driving scenarios, leads to an under-utilization of perceptioninformation in end-to-end models incorporating ego status, such as the egovehicle's velocity. These models tend to rely predominantly on the egovehicle's status for future path planning. Beyond the limitations of thedataset, we also note that current metrics do not comprehensively assess theplanning quality, leading to potentially biased conclusions drawn from existingbenchmarks. To address this issue, we introduce a new metric to evaluatewhether the predicted trajectories adhere to the road. We further propose asimple baseline able to achieve competitive results without relying onperception annotations. Given the current limitations on the benchmark andmetrics, we suggest the community reassess relevant prevailing research and becautious whether the continued pursuit of state-of-the-art would yieldconvincing and universal conclusions. Code and models are available at\url{https://github.com/NVlabs/BEV-Planner}

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?