TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

GPUDrive: Data-driven, multi-agent driving simulation at 1M FPS

98 点作者 jonbaer10 个月前

4 条评论

cs70210 个月前
Unless I'm missing something big, this looks like a significant deal for independent developers of self-driving AI software: GPUDrive enables them to run driving simulations with hundreds of AI agents on consumer-grade GPUs at 1M FPS, and it comes with Python bindings, wrappers for Pytorch and Jax, and a friendly standard MIT license. Thank you for sharing this on HN!
评论 #41199576 未加载
评论 #41199064 未加载
foota10 个月前
Is this just the location data being trained on, or is there image and sensor input data too? It looks like it&#x27;s just location, which seems like it limits the applicability, but I&#x27;m not sur<p>Edit: reading a bit more it&#x27;s somewhere in between. Afaict no raw sensor data etc.,. but different &quot;parsed&quot; sensor inputs are supported. I&#x27;m not sure whether this is synthetic or not? E.g., is the LIDAR view real LIDAR data from some system or a processed result of what the system thinks LIDAR would be able to see? I can&#x27;t tell.
BetterWhisper10 个月前
<a href="https:&#x2F;&#x2F;github.com&#x2F;Emerge-Lab&#x2F;gpudrive">https:&#x2F;&#x2F;github.com&#x2F;Emerge-Lab&#x2F;gpudrive</a> - the repo
toppy10 个月前
I don&#x27;t know this field of research thus my question: why such a high framerate is consider as a feature at all? Does it help with learning rate?
评论 #41200509 未加载