Navigating dynamic urban environments presents significant challenges for embodied agents, requiring advanced spatial reasoning and adherence to common-sense norms. Despite progress, existing visual navigation methods struggle in map-free or off-street settings, limiting the deployment of autonomous agents like last-mile delivery robots. To overcome these obstacles, we propose a scalable, data-driven approach for human-like urban navigation by training agents on thousands of hours of in-the-wild city walking and driving videos sourced from the web. We introduce a simple and scalable data processing pipeline that extracts action supervision from these videos, enabling large-scale imitation learning without costly annotations. Our model learns sophisticated navigation policies to handle diverse challenges and critical scenarios. Experimental results show that training on large-scale, diverse datasets significantly enhances navigation performance, surpassing current methods. This work shows the potential of using abundant online video data to develop robust navigation policies for embodied agents in dynamic urban settings.

Objectives: To better explore the valuable experience and knowledge in traditional Chinese medicine (TCM) literature and promote the academic heritage and innovation of TCM, this paper tries to provide methods and a system of word segmentation and POS tagging for ancient Chinese medicine literature. Method: Based on HMM and Java language for POS tagging, this paper develops a word segmentation system of Chinese ancient books by constructing a Thesaurus of Chinese medicine terminology and a special POS tagging method for Chinese medicine, and adopting Ansj open source code as the core word segmentation algorithm. Results: Thesaurus of Chinese medicine terminology involving 155,343 Chinese medicine words are constructed. These words were divided into 14 categories and 7 levels of 891 parts of speech (POS). Online website of Chinese word segmentation and POS tagging proprietary system were established (http://www.zhongyifenci.org). And the F measure reaches 90.65%, which is much higher than the system of Ansj. Clinical or Biological Impact: This system, with high precision and recall rate, will be very helpful to knowledge discovery of Chinese medicine and be beneficial to giving full play to the original advantages of Chinese medicine.