Researchers from Zhejiang University, the Chinese University of Hong Kong, and Zhejiang University have developed a new model called RAM for 3D spatial understanding and manipulation in robots. This model addresses limitations in current vision-language models by creating an external 3D knowledge base, enabling better object pose comprehension and long-range task planning. Practical tests showed high success rates for both language-driven and image-guided operations, and RAM is compatible with various large models and robotic platforms. AI
Summary written by gemini-2.5-flash-lite from 3 sources. How we write summaries →
IMPACT Introduces a novel approach to 3D spatial understanding for robots, potentially improving their ability to perform complex tasks based on natural language or visual cues.
RANK_REASON Academic paper published in a top journal detailing a new model for robotics.