Latest Spatial AI & SLAM Research Papers

The newest Spatial AI & SLAM papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Spatial AI & SLAM so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• RAVEN: A Unified Active SLAM System for Rapid Autonomous Visual Exploration with Aerial Robots under Localization Uncertainty
  Xinyi Chen, Yichen Zhang, Chenxing Jiang, Shaojie Shen · arXiv · Oct 27, 2026

  Active simultaneous localization and mapping (SLAM) addresses the problem of planning robot motion to build complete and accurate maps of unknown environments through efficient exploration while maintaining high localization accuracy. This …

• VPR-Space: A Benchmark for Visual Place Recognition in Space Analog Domains
  Richard Fechner, Peer Neubert · arXiv · Oct 26, 2026

  Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the…

• SCOPE: Scene-graph Construction Optimized by Plan Error-correction for Robot Long-term Planning Datasets
  Chaoyue Li, Zeyu Gao, Yanfeng Lu, Fan Luo · arXiv · Oct 22, 2026

  Task and Motion Planning (TAMP) stands as a fundamental challenge in robotics, essential for enabling autonomous agents to execute complex, long-horizon tasks in diverse environments. While Large Language Models (LLMs) introduce a new parad…

• Consistent Distributed Invariant EKF SLAM with Point and Object Features
  Mengya Xu, Xianjia Yu, Ha Sier, Shoudong Huang et al. · arXiv · Oct 22, 2026

  Multi-robot SLAM allows robots to improve their estimates by exchanging map information, but repeated exchanges create unknown correlations between local estimators. Covariance intersection (CI) can fuse estimates without tracking these cor…

• RGraph-Eval: Task-Grounded Scene Graphs for Evaluating Robot Video Generation
  Aleksandr Lazarev, Sofia Zimina, Roman Kuznetsov, Tatiana Zemskova et al. · arXiv · Oct 22, 2026

  Generated robot videos can look convincing while depicting the wrong interac- tion: a different object is moved, a grasp disappears, or a placement ends out- side its destination. We introduce RGraph-Eval, a reference-based framework that m…

• Failure Modes of Vision-Language Models for Human Activity Understanding in Thermal HRI
  Han Hu, He Chen · arXiv · Oct 21, 2026

  Thermal cameras enable robots to perceive human activities in darkness while revealing less personally identifiable appearance information and fewer details of the surrounding environment than RGB cameras. As vision-language models (VLMs), …

• CoGaussian: Open-Vocabulary Gaussian-based Collaborative 3D Scene Understanding
  Om Shivam Verma, Shaya Farahmand, Lingjun Zhao, Lu Gan · arXiv · Oct 20, 2026

  Collaborative perception enables agents to retrieve the scene semantics and geometry beyond the field of view of any individual agent. This broader scene understanding enhances transportation safety and improves efficiency in multi-robot sy…

• PanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian Splatting
  Jinghan Gao, Siyu Wang, Dongyu Feng, Yiyuan Pan et al. · arXiv · Oct 20, 2026

  3D scene graphs support language-guided navigation by organizing physical entities and their containment and spatial relations into hierarchical maps. Building such structured maps requires a scene representation that consistently distingui…

• CAOS-SLAM: Class-Agnostic Object-Aware Real-Time vSLAM for Dynamic Environments
  Gaia Borghi, João Carlos Virgolino Soares, Angelo Bratta, Shahab Heshmati-Alamdari et al. · arXiv · Oct 19, 2026

  Robust visual Simultaneous Localization and Mapping (vSLAM) in dynamic environments faces challenges due to the presence of moving objects that may introduce erroneous observations, corrupt the map reconstruction and overall degrade localiz…

• Foundation-Model-Driven 3D Scene Graphs for Mobile Manipulation
  Dominic Maggio, Lorenzo Shaikewitz, Aryan Naveen, Kris Hauser et al. · arXiv · Oct 16, 2026

  Geometric and Semantic Foundation models are becoming increasingly popular tools for generating spatial maps for robots. Recent work (e.g., FOUND-IT) has leveraged these tools to construct real-time, task-driven, and open-set 3D scene graph…

• FLoTS-SLAM: Optical Flow-Derived Uncertainty for Monocular Dynamic SLAM with Two-Stage Optimization
  Haorui Du, Lipu Zhou · arXiv · Oct 16, 2026

  Monocular simultaneous localization and mapping (SLAM) remains challenging in dynamic environments. Real-time dynamic object identification in such environments is a critical problem. Recent approaches estimate per-pixel uncertainty from re…

• HyperLoop: Hyperspectral-Assisted Loop Closure Detection in 3D-SLAM for Planetary Exploration
  Annie Bhalla, Dennis Rotondi, Riccardo Giubilato, Kai O. Arras et al. · arXiv · Oct 14, 2026

  Autonomous navigation of planetary rovers is challenged by visually repetitive, featureless terrain. SLAM systems based on 3D Gaussian Splatting (3DGS) offer dense mapping but rely on RGB appearance descriptors that degrade under perceptual…

• Perception Beyond the Visible: Incompleteness-Aware Scene Understanding for Robot Autonomy
  Rohit Mohan · arXiv · Oct 13, 2026

  Reliable robot autonomy requires reasoning about the world from partial and noisy observations. However, many perception systems model only visible scene regions, rely on fixed semantic categories, and assume reliable sensor measurements. T…

• RTISSLAM: In-air Imaging Sonar SLAM using a Robust Pose Graph and Occupancy Grid Mapping
  Jan Steckel · arXiv · Oct 13, 2026

  Sonar was one of the first sensors with which mobile robots built maps, and in-air sonar keeps working where cameras and lidar fail, in darkness, smoke, dust and next to glass. Classical sonar SLAM, however, relied on geometric features or …

• Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving
  Yuechen Luo, He Chong, Fang Li, Shaoqing Xu et al. · arXiv · Oct 9, 2026

  Reinforcement Learning (RL) substantially improves planning performance in autonomous-driving Vision-Language-Action (VLA) models. However, existing RL methods rely on scalar trajectory rewards that measure overall quality but fail to ident…

• A spatial AI-based biomarker with independent prognostic value in early low- and intermediate- risk breast cancer
  C. Boissin, Y. Xiang, B. Liu, J. Vallon-Christersson et al. · medRxiv · Oct 9, 2026

  Background: Patients with ER-positive/HER2-negative early breast cancer of low or intermediate grade are generally considered to have a favourable prognosis, yet a number will recur. This risk is poorly captured by standard clinicopathologi…

• Towards Accurate End-Effector Localization for UMI-Style Robotic Manipulation Teaching
  Junjie Zhang, Deteng Zhang, Zhisong Xu, Bo Sun et al. · arXiv · Oct 7, 2026

  Robot demonstration learning requires accurate and temporally complete end-effector localization during close-range manipulation and camera occlusion. Existing SLAM benchmarks emphasize navigation motions, whereas manipulation datasets prio…

• CORNAV: Construction-Aware Reasoning for Robot Navigation on Active Worksites
  Parastoo Ali Pour, Deepak Prakash Kumar, Tommy Zhou, Pramod Khargonekar et al. · arXiv · Oct 2, 2026

  The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the highest injury rates among major industries. These factors motivate the use of autonomous…

• EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation
  Pujun Guo, Yuanfan Zheng, Fei Teng, Mengfei Duan et al. · arXiv · Oct 2, 2026

  Panoramic images provide a complete 360-degree field of view, enabling comprehensive scene understanding for embodied perception. However, heterogeneous embodied platforms exhibit substantial differences in observation viewpoints and spatia…

• GlassGuard: Verified Glass Plane Mapping for Robot Navigation
  Hanwen Guo, Zhengzhi Lin, Yusen Xie, Ji Zhang · arXiv · Oct 1, 2026

  Transparent and specular surfaces pose a serious challenge to LiDAR-based SLAM and navigation because laser returns may pass through glass, leaving collision boundaries absent from the map. Prior work attempts to reconstruct the missing sur…

• STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction
  Nathan Tsoi, Michael J. Munje, Tejas Oberoi, Rishab Maheshwari et al. · arXiv · Sep 30, 2026

  Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition, common-se…

• GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
  Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang et al. · arXiv · Sep 30, 2026

  Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action model…

• MVP-SLAM: Multi-Camera Visual-Inertial Floorplan-Prior SLAM
  Asier Bikandi-Noya, Miguel Fernandez-Cortizas, Muhammad Shaheer, Holger Voos et al. · arXiv · Sep 30, 2026

  Indoor building construction sites are demanding environments for visual SLAM, where variable lighting and repetitive, low-textured structures make the system drift over long trajectories, though structural elements such as walls remain dis…

• Pow3R-SLAM: Real-Time RGB-D SLAM with 3D Reconstruction Priors
  Christopher Kolios, Ishaan Mehta, Sasa Janjic, Yeganeh Bahoo et al. · arXiv · Sep 29, 2026

  We present Pow3R-SLAM, a real-time RGB-D simultaneous localization and mapping (SLAM) system that uses Pow3R for tracking and mapping. Inspired by MASt3R-SLAM, a recent work on monocular SLAM using two-view 3D reconstruction priors, we exte…

• Towards Spatial Perception for Heterogeneous Robot Collaboration in Subterranean Mining Environments
  Mario Alberto Valdes Saucedo, Akash Patel, Christoforos Kanellakis, George Nikolakopoulos · arXiv · Sep 29, 2026

  The autonomous extraction of deep mineral deposits in abandoned underground mines is fundamentally a multi-agent integration problem. No single platform simultaneously offers the mobility to traverse kilometers of degraded drifts and the se…

• ForVis: An In-Field Dataset and Benchmark for VIO Using Under-Canopy UAV Flights in Forests
  Arman Kiani, Masoud Ataei, Elvis Gyaase, Jeffrey Eiyike et al. · arXiv · Sep 28, 2026

  Visual-inertial Simultaneous Localization and Mapping (VI-SLAM) for UAVs remains difficult to evaluate in real forest environments, where motion, illumination changes, repetitive vegetation, and vibration can all affect estimation. We prese…

• Action Sequence Transfer via LLMs for Heterogeneous Environments
  Choongho Chung, DongHwan Shin, Sung-Hee Lee · arXiv · Sep 28, 2026

  We present an action sequence transfer system that adaptively transfers user action sequences across different target spaces. Given an input action sequence from a source space and scene graph representations of both the source and target e…

• Augmented Reality Interfaces for Human-Robot Collaboration: Development of a ROS 2-Based Sensor Streaming Framework and Validation via SLAM Algorithms
  Alessandro Rubert, Stefano Ghidoni, Matteo Terreran · arXiv · Sep 25, 2026

  In recent years, Human-Robot Collaboration (HRC) has taken on a central role in Industry 4.0 and collaborative robotics, demanding communication channels that are increasingly bidirectional, intuitive, and efficient. In this context, Augmen…

• TRACKGRAPH: Online Open-Vocabulary 3D Scene Graphs via Image-Space Tracking
  Peder Borge Hellesylt, Albert Gassol Puigjaner, Kostas Alexis, Annette Stahl · arXiv · Sep 25, 2026

  Open-vocabulary 3D maps enable robots to reason about previously unknown environments using natural language. However, existing systems typically segment every incoming image, associate detections with persistent 3D segments, and frequently…

• FMCW-LIO: A Doppler LiDAR-Inertial Odometry
  Mingle Zhao, Jiahao Wang, Tianxiao Gao, Chengzhong Xu et al. · arXiv · Sep 24, 2026

  Conventional LiDAR-inertial odometry (LIO) or simultaneous localization and mapping (SLAM) methods heavily rely on geometric features of environments, as LiDARs primarily provide range measurements instead of motion measurements. From now o…