arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Georgia Institute of Technology(佐治亚理工学院)

2026-06-19 至 2026-06-19 共收录 3
2606.19920 2026-06-19 cs.RO cs.LG cs.MA 新提交

Deep-Unfolded Coordination

深度展开协调

Hunter Kuperman, Minchan Jung, Rahul V. Ghosh, Alex Oshin, Evangelos A. Theodorou

机构 * Autonomous Control and Decision Systems Laboratory Georgia Institute of Technology United States(佐治亚理工学院自主控制与决策系统实验室)

AI总结 提出Deep Coordinator框架,通过深度展开ADMM-DDP迭代学习动态调整超参数,实现非凸优化器求解时自适应惩罚参数,在车队和四旋翼仿真中速度提升6.18-9.44倍且可扩展至8倍规模。

Comments The second and third authors contributed equally (equal second authorship). 35 pages (10 pages main text), 17 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19590 2026-06-19 cs.RO cs.SY eess.SY 新提交

Safe, Real-Time Active Model Discrimination and Fault Diagnosis for Nonlinear Systems via Differentiable Reachability

通过可微可达性实现非线性系统的安全、实时主动模型辨识与故障诊断

Xinpei Ni, Melkior Ornik, Glen Chou, Samuel Coogan

机构 * Institute of Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology(佐治亚理工学院机器人与智能机器研究所) Department of Aerospace Engineering, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校航空航天工程系)

AI总结 针对不确定非线性系统,提出一种基于可微可达性近似的实时主动故障诊断算法,通过优化控制输入使输出集分离,在保证安全的同时实现快速模型辨识。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20437 2026-06-19 hep-ex cs.LG 新提交

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

HEPTv2:用于带电粒子重建的端到端高效点变换器

Siqi Miao, Shitij Govil, Jack P. Rodgers, Mia Liu, Javier Duarte, Shih-Chieh Hsu, Yuan-Tang Chou, Pan Li

机构 * School of Electrical and Computer Engineering, Georgia Institute of Technology(佐治亚理工学院电气与计算机工程学院) Department of Physics and Astronomy, Purdue University(普渡大学物理与天文学系) Department of Physics, University of California San Diego(加州大学圣地亚哥分校物理系) Department of Physics, University of Washington(华盛顿大学物理系)

AI总结 提出HEPTv2,一种端到端点变换器架构,通过局部敏感哈希编码和扇区化解码,无需图构建即可从探测器击中点直接重建粒子轨迹,在TrackML上以0.8%假率实现98.6%追踪效率,延迟仅15ms。

详情

展开后加载摘要…

URL PDF HTML 收藏