Embedded Files
9:00 - 9:15
Welcome and introduction to the workshop
Welcome and introduction to the workshop
Session 1
9:15 - 9:40
Maurice Fallon, University of Oxford, UK
Maurice Fallon, University of Oxford, UK
Where's my glasses: Identifying change in scene graphs over time
9:40 - 10:05
Jen Jen Chung, The University of Queensland, Australia
Jen Jen Chung, The University of Queensland, Australia
Exploring interactions with object-level maps
Coffee Break 10:05 - 10:15
Session 2
10:15 - 10:40
Abinav Valada, University of Freiburg, Germany
Abinav Valada, University of Freiburg, Germany
Open-World Autonomy: Representations, Mapping, Interaction
10:40 - 11:05
Luca Carlone, MIT, USA
Luca Carlone, MIT, USA
From Map to Memories: Present and Future of Spatial AI for Robotics
11:05 - 11:30
David Hsu, National University of Singapore, Singapore
David Hsu, National University of Singapore, Singapore
Open Scene Graphs for Open World Navigation
Interactive Poster 11:30 - 12:00
1. MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
1. MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
2. Object Pose and Shape Estimation for Grasping: Does it Work?
2. Object Pose and Shape Estimation for Grasping: Does it Work?
3. CorseBIMLoc: BIM-Integrated Coarse Global Localization via Open-Set Scene Graphs
4. Common Prior Maps for Industrial Manipulation via VQ Motion Codebooks
5. osmAG-LLM: Zero-Shot Open-Vocabulary Object Navigation via Semantic Maps and Large Language Models Reasoning
6. CAD Assemblies as Object-Level Priors for Robotic Operations Planning
7. Rail-Constrained Train Localization Using Multilayer Map
8. Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation
9. Towards Robust Cross-Seasonal Image-to-Map Matching against Publicly Available Prior Maps
Lunch Break 12:00 - 13:10
Session 3
13:10 - 13:35
Jose Luis Sanchez Lopez, University of Luxembourg, Luxembourg
Jose Luis Sanchez Lopez, University of Luxembourg, Luxembourg
Tightly Integrating Semantic-Relational Priors into SLAM for Indoor Environments
13:35 - 14:00
Huan Yin (On Line), Hunan University, China
Huan Yin (On Line), Hunan University, China
BIM as a Prior Semantic Map: Localization and Dataset
Coffe Break 14:00 - 14:20
Paper Presentation 14:20 - 14:45
1. NeMo-map: Neural Implicit Motion Fields as Spatio-Temporal Prior Map for Shared Human-Robot Environments
1. NeMo-map: Neural Implicit Motion Fields as Spatio-Temporal Prior Map for Shared Human-Robot Environments
2. Wall-Based BIM Constraints for Drift Reduction in Indoor RGB-D SLAM
3. Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignment
4. COMPASS: COmpact Multi-channel Prior-map And Scene Signature for Floor-Plan-Based Visual Localization
5. Plantar Force Prior-Guided Parameter Optimization for Adaptive Control of Wearable Knee Exoskeletons
14:45 - 15:10
Javier Civera, University of Zaragoza, Spain
Javier Civera, University of Zaragoza, Spain
Geometric and Open-Vocabulary Priors for Visual SLAM
Session 4
Paper Presentation 15:10 - 15:40
1. Learning-Based Hierarchical Scene Graph Matching for Robot Localization Leveraging Prior Maps
1. Learning-Based Hierarchical Scene Graph Matching for Robot Localization Leveraging Prior Maps
2. ActLoc: Learning to Localize on the Move via Active Viewpoint Selection
2. ActLoc: Learning to Localize on the Move via Active Viewpoint Selection
3. Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition
4. Experience-Based Map Building Re-Exploration of Quasi-Dynamic Indoor Environments
5. RoboBIM: Scaling Robot Semantic Foundations through Agentic Extraction of BIM Priors
15:40- 16:05
Ji Zhang (Haokun Zhu Substitute), CMU, USA
Ji Zhang (Haokun Zhu Substitute), CMU, USA
A Full-Stack System for Real-Time Semantic Mapping and Object Navigation
Paper Presentation 16:05 - 16:25
1. Towards Zero-Shot Global Localization via Dense Embedding Maps Based on Satellite Priors
2. OSM-BKI: OpenStreetMap-Guided Bayesian Kernel Inference for Domain-Robust LiDAR Semantic Mapping
3. INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval
4. IFG: Internet-Scale Guidance for Functional Grasping Generation
Interactive Poster 16:25 - 16:50
1. Swept-Volume-Aware Planning and Control for Multi-Axle Swerve-Drive AMRs
1. Swept-Volume-Aware Planning and Control for Multi-Axle Swerve-Drive AMRs
2. Passage-Aware Structural Mapping for RGB-D Visual SLAM
2. Passage-Aware Structural Mapping for RGB-D Visual SLAM
3. Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation
4. Towards Platform-Agnostic Geospatial Awareness: Fusing Satellite Priors with LiDAR Laser Point Cloud for Seamless Indoor-Outdoor Navigation
5. Rethink Semantic Maps as Living Priors: A Lifecycle Framework for Semantic-Aware Navigation in Dynamic Urban Environments
6. Where Am I? Semantic Map Grounding via Vision-Language Models for Multi-Modal Localization
16:50- 17:15
Xiaolong Wang (On Line), UCSD, USA
Xiaolong Wang (On Line), UCSD, USA
17:15 – 17:30
Closing Remarks and Award Ceremony
Page updated
Google Sites
Report abuse