Building object-level maps can facilitate robot-environment interactions (e.g. planning and manipulation), but objects could often have multiple probable poses when viewed from a single vantage point, due to symmetry, occlusion or perceptual failures. A robust object-level simultaneous localization and mapping (object SLAM) algorithm needs to be aware of this pose ambiguity. We propose to maintain and subsequently disambiguate the multiple pose interpretations to gradually recover a globally consistent world representation. The max-mixtures model is applied to implicitly and efficiently track all pose hypotheses, but the resulting formulation is non-convex, and therefore subject to local optima. To mitigate this problem, temporally consistent hypotheses are extracted, guiding the optimization into the global optimum. This consensus-informed inference method is applied online via landmark variable re-initialization within an incremental SLAM framework, iSAM2, for robust real-time performance. We demonstrate that this approach improves SLAM performance on both simulated and real object SLAM problems with pose ambiguity.
MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction
ETH Zurich（苏黎世联邦理工学院）；Harbin Engineering University（哈尔滨工程大学）；University of Liverpool（利物浦大学）；University of Macau（澳门大学）；University of Ottawa（多伦多大学）；Wuhan University（武汉大学）；Imperial College London（伦敦帝国学院）
人形机器人在现实生活中扮演着越来越重要的角色，特别是在室内应用方面。为室内环境测绘、自定位和物体识别等任务提供强大的解决方案，对于使机器人更加自主，从而更加人性化至关重要。著名的毕宿五服务机器人Pepper是实现这些目标的合适人选。在本文中，同时定位和映射（SLAM）算法与对象识别相结合的混合系统的开发和测试与胡椒机器人在现实世界的条件下第一次。ORB SLAM 2算法是本课题的一项重要研究工作.然后，基于尺度不变特征变换（SIFT）和随机采样一致性（RANSAC）的对象识别技术与SLAM相结合，识别和定位映射的室内环境中的对象。我们的实验结果表明，该系统的适用性，在现实世界的场景中的胡椒机器人。此外，我们在https://github.com/PaolaArdon/Salt-Pepper上向社区提供了我们的源代码。
Range-based 6-DoF Monte Carlo SLAM with Gradient-guided Particle Filter on GPU
Graduate School of Science and Technology, University of Tsukuba（筑波大学科学技术研究生院）；National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究院）；Institute of Systems and Information Engineering, University of Tsukuba（筑波大学系统与信息工程研究所）
GeVI-SLAM: Gravity-Enhanced Stereo Visua Inertial SLAM for Underwater Robots
School of Data Science, Chinese University of Hong Kong, Shenzhen, China（数据科学学院，香港中文大学（深圳））；School of Life Sciences, Chinese University of Hong Kong, China（生命科学学院，香港中文大学）
NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting
Department of Mechanical and Automation Engineering and T Stone Robotics Institute, The Chinese University of Hong Kong（机械与自动化工程系和T Stone机器人研究所，香港中文大学）；School of Automation and Intelligent Sensing, the State Key Laboratory of Avionics Integration and Aviation System of-Systems Synthesis, and Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University（自动化与智能感知学院、航空系统集成与航空系统综合国家重点实验室、上海导航与定位服务重点实验室，上海交通大学）
DynoSAM: Open-Source Smoothing and Mapping Framework for Dynamic SLAM
Australian Centre For Robotics (ACFR)（澳大利亚机器人中心）；School of Aerospace, Mechanical and Mechatronic Engineering (AMME)（航空航天、机械与机电工程学院）；University of Sydney（悉尼大学）
MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM
HFIPS, Chinese Academy of Sciences（中国科学院合肥智能机械研究所）；University of Science and Technology of China（中国科学技术大学）；Tohoku University（东北大学）；University of Zaragoza（阿斯图里亚大学）；University of Tokyo（东京大学）；Dalian University of Technology（大连理工大学）
BPDA-GMM: Bayesian Probabilistic Data Association via Gaussian Mixture Models for Semantic SLAM
School of Information Science, Japan Advanced Institute of Science and Technology（信息科学学系，日本科学技术大学）；University of Engineering and Technology, Vietnam National University（工程技术大学，越南国家大学）
Robust Graph Matching through Semantic Relationship Generation for SLAM
Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg（卢森堡大学自动化与机器人研究组，安全、可靠与信任跨学科研究中心）；Computer Vision and Aerial Robotics Group at Universidad Politécnica de Madrid（马德里理工大学计算机视觉与空中机器人研究组）
Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM
College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海智能自主系统研究院）；Division of Decision and Control Systems, School of EECS, KTH Royal Institute of Technology（瑞典皇家理工学院电气工程与计算机科学学院决策与控制系统系）
HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fields
University of Stuttgart（斯图加特大学）；Huawei Munich Research Center（华为慕尼黑研究中心）；Central Media Technology Institute, Huawei 2012 Laboratories（华为2012实验室中央媒体技术研究院）；Technical University of Munich（慕尼黑工业大学）
Simultaneous Localization and 3D-Semi Dense Mapping for Micro Drones Using Monocular Camera and Inertial Sensors
The Hatter Department of Marine Technologies, University of Haifa, 3498838, Israel（海洋技术系，海法大学）；Computer Science, University of Haifa, 3498838, Israel（计算机科学，海法大学）
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
School of Automation and Intelligent Sensing, and Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University（自动化与智能感知学院，导航与位置服务上海市重点实验室，上海交通大学）；School of Electrical Engineering and Computer Science, The University of Queensland（电气工程与计算机科学学院，昆士兰大学）；School of Computer Science and Technology, Tongji University（计算机科学与技术学院，同济大学）
TomoSLAM: factor graph optimization for rotation angle refinement in microtomography
Institute for Information Transmission Problems – IITP RAS（信息传输问题研究所（俄罗斯科学院））；Evocargo（Evocargo 公司）；Smart Engines Service LLC（Smart Engines Service 有限责任公司）
DOA: A Degeneracy Optimization Agent with Adaptive Pose Compensation Capability based on Deep Reinforcement Learning
School of Electronics Engineering, Beijing University of Posts and Telecommunications（北京邮电大学电子工程学院）；Xiangjiang Laboratory（湘江实验室）；Signal and Information Processing (SIP) Lab, Department of Computer Science, University of Warwick（战争科大学计算机科学系信号与信息处理实验室）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）；Department of Statistics and Probability, National University of Singapore（新加坡国立大学统计与概率系）；Robotics and Microsystems Center, School of Mechanical and Electric Engineering, Soochow University（苏州大学机械与电子工程学院机器人与微系统中心）
Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition
School of Electronics and Computer Science, University of Southampton（索姆塞特大学电子与计算机科学学院）；School of Electronics and Computer Science, Queensland University of Technology（昆士兰科技大学电子与计算机科学学院）；School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
从单目视觉系统估计相机的运动以及场景的3D结构是一项复杂的任务，其通常依赖于所谓的场景刚性假设。当观察动态环境时，这一假设被违反，这导致相机的自我运动和对象的运动之间的模糊性。为了解决这个问题，我们提出了一个自监督学习的框架，从单目视频的三维物体运动场估计。我们的贡献是双重的。首先，我们提出了一个两阶段的投影流水线，明确地解开相机自我运动和物体运动与动态注意模块，称为DAM。具体而言，我们设计了一个综合的运动模型，估计在第一和第二翘曲阶段，分别由注意力模块通过共享的运动编码器控制的相机和对象的运动。其次，我们提出了一个对象运动场估计通过对比样本共识，称为CSAC，利用弱语义先验（限界框从对象检测器）和几何约束（每个对象尊重刚体运动模型）。在KITTI，Cityscapes和Waymo Open Dataset上的实验证明了我们方法的相关性，并表明我们的方法在自监督单目深度估计，对象运动分割，单目场景流估计和视觉里程计等任务中优于最先进的算法。
Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimation
School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（人工智能与机器人学院和机器人视觉感知与控制技术国家工程研究中心，湖南大学）；State Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University（自主智能无人系统国家重点实验室，同济大学）；School of Computer Science and Engineering, Hunan University of Science and Technology（计算机科学与工程学院，湖南科技大学）
