9 papers
KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies
Yihan Zeng, Minghao Ye, Yiyuan Chen +4
Long-horizon robot manipulation remains challenging because similar observations may occur at different execution stages, while the appropriate action depends on previously complet…
CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM
Kangjie Zhou, Zhejia Wen, Zhiyong Zhuo +9
Recent Vision-Language Models (VLMs) have demonstrated significant potential in robotic planning. However, they typically function as semantic reasoners, lacking an intrinsic under…
DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
Yufei Jia, Guangyu Wang, Yuhang Dong +17
We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper…
ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting
Yuetao Li, Zijia Kuang, Ting Li +4
We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establish…
COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation
Siqi Zhang, Yanyuan Qiao, Qunbo Wang +4
Vision-and-Language Navigation (VLN) tasks have gained prominence within artificial intelligence research due to their potential application in fields like home assistants. Many co…
An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation
Lu Shi, Yuxuan Xu, Shiyu Wang +6
The sim-to-real gap remains a critical challenge in robotics, hindering the deployment of algorithms trained in simulation to real-world systems. This paper introduces a novel Real…