5 papers
Joint On-and-Off Policy Learning for Vision-and-Language Navigation
Qingrong He, Lin Zhao, Kevin Zheng +1
Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Recent advancements in Vision-La…
BAT-Nav: Belief-Based Arbitration and Termination via Remaining Discoverability in Multi-Goal Semantic Navigation
Xi Lin, Kangyi Wu, Jiayi Li +3
Multi-goal semantic navigation couples searches through a shrinking horizon: effort spent on one request can make another effectively undiscoverable. Discoverability therefore depe…
Think before Go: Hierarchical Reasoning for Image-goal Navigation
Pengna Li, Kangyi Wu, Shaoqing Xu +5
Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navig…
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Kangyi Wu, Pengna Li, Kailin Lyu +5
Vision-Language Navigation(VLN) requires an agent to navigate through 3D environments by following natural language instructions. While recent Video Large Language Models(Video-LLM…
Towards Learning a Generalist Model for Embodied Navigation
Duo Zheng, Shijia Huang, Lin Zhao +2
Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required…