ICRA

MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM

MotionGS-SLAM：面向运动模糊鲁棒SLAM的事件调制高斯溅射

Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa

机构 * Research Institute for Science & Technology, Tokyo University of Science（东京理科大学科学技术研究所） 纠错

AI总结 MotionGS-SLAM通过事件调制高斯核与双调制机制，在渲染流水线中建模运动模糊形成，实现相机轨迹与场景几何联合优化，显著提升高运动下SLAM的轨迹与地图精度。

Comments 8 pages, 5 figures. Published in the 2026 IEEE International Conference on Robotics and Automation

Seeing the Bigger Picture: 3D Latent Mapping for Mobile Manipulation Policy Learning

看见更大的图景：用于移动操作策略学习的3D潜在映射

Sunghwan Kim, Woojeh Chung, Zhirui Dai, Dwait Bhatt, Arth Shukla, Hao Su, Yulun Tian, Nikolay Atanasov

AI总结 本文提出SBP方法，通过3D潜在映射提升移动操作策略的学习性能，实现更强的空间和时间推理能力。

Comments ICRA 2026, project page: this https URL (https://existentialrobotics.org/sbp_page/)