3 papers
cs.CV2026
Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning
Sixian Zhang, Yiyao Wang, Xinhang Song +3
Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit…
cs.CV2026
TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation
Yiyao Wang, Sixian Zhang, Keming Zhang +3
Existing zero-shot Object Goal Navigation (ObjectNav) methods often exploit commonsense knowledge from large language or vision-language models to guide navigation. However, such k…
cs.RO2024
DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model
Yang Jin, Jun Lv, Shuqiang Jiang +1
Generating robot demonstrations through simulation is widely recognized as an effective way to scale up robot data. Previous work often trained reinforcement learning agents to gen…