5 papers
Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study
Shichao Zhai, Shuhao Ye, Rong Xiong +1
Object-goal navigation (ObjectNav) in multi-floor scenarios presents a challenge due to sparse rewards caused by long-horizon decision-making. In this paper, we propose a diagnosti…
StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera Odometry
Yufei Wei, Shuhao Ye, Qi Wang +4
Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving efficient use of rig geometry a c…
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
Yufei Wei, Shuhao Ye, Chenxiao Hu +5
Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization and multi-camera rig odometry. Each group carries known intra-group geometry fro…
Fast-SegSim: Real-Time Open-Vocabulary Segmentation for Robotics in Simulation
Xuan Yu, Yuxuan Xie, Shichao Zhai +3
Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Gaussian Splatting variants, o…
ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
Shuhao Ye, Sitong Mao, Yuxiang Cui +6
Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate towards target in continuous environments, following natural language instruct…