论文概要
研究领域: CV 作者: Huaide Jiang, Yash Chaudhary, Yuping Wang 发布时间: 2026-03-19 arXiv: 2503.16908
中文摘要
我们提出NavTrust，一个统一基准测试，在真实场景中系统性地对输入模态（包括RGB、深度和指令）进行损坏，并评估其对导航性能的影响。NavTrust是首个将具身导航智能体暴露于统一框架下多样化RGB-深度损坏和指令变体的基准。
原文摘要
We present NavTrust, a unified benchmark that systematically corrupts input modalities, including RGB, depth, and instructions, in realistic scenarios and evaluates their impact on navigation performance. NavTrust is the first benchmark that exposes embodied navigation agents to diverse RGB-Depth corruptions and instruction variations.
--- *自动采集于 2026-03-22*
#论文 #arXiv #CV #小凯