MMUSV-Sim: A Maritime Simulation Platform for Multi-USV Cooperative Perception
Overview
The paper presents MMUSV-Sim, a maritime simulation platform built on Unreal Engine 5 and Project AirSim designed to enable cooperative perception among multiple unmanned surface vehicles (USVs). The authors address challenges such as limited sensing range, occlusions, and the high cost of sea trials by providing a configurable environment for synchronized multimodal data acquisition. Using this平台
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Control: reported autonomous
“Maritime autonomous navigation enables unmanned surface vehicles to perform multiple tasks and can also serve as a driver-assistance system for manned vessels, improving safety and comfort. Compared with on-road scenes, maritime perception faces unique challenges: optical sensors degrade due to reflections and sea fog, while wind and waves cause large platform motions that disrupt perception stability. Therefore, hig”
Exact source · revision 1Source owner not reported
Artifact availability · dataset: available
“t detection, tracking, and odometry, and evaluate baseline methods, highlighting the need for improved maritime perception, multi-modal fusion, and adaptive 4D mmWave radar waveform design. The dataset can be downloaded from https://github.com/ORCAUBOAT/MariSense .”
Exact source · revision 1Source owner not reported
Environment: simulation
“dinated sea trials, the scarcity of multi-USV datasets, and the lack of integrated maritime simulation and evaluation tools. We present MMUSV-Sim, a perception-oriented maritime simulation and data-generation platform built on Unreal Engine 5 and Project AirSim. It supports configurable maritime scenarios, synchronized multimodal acquisition across multiple USVs, and consistent 3D annotations in a shared world frame.”
Exact source · revision 1Source owner not reported
Reported quantity · scene frames: 14385 other · Basis not reported
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Reported quantity · sequences: 341 other · Basis not reported
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Reported quantity · AP: 64.26 other · Basis not reported
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Reported quantity · LiDAR detection AP: 64.26 other · Basis not reported
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Dataset · modalities: RGB · Differing source assertions
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Dataset · modalities: LiDAR · Differing source assertions
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Dataset · tasks: vessel detection
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Dataset · embodiments: multi-USV
“Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB--LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB--LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate f”
Exact source · revision 1Source owner not reported
Developments
- 2026-11-05 05:00 UTC · 1 reportsMMUSV-Sim: A Maritime Simulation Platform for Multi-USV Cooperative PerceptionarXiv Robotics — research abstracts：MMUSV-Sim: A Maritime Simulation Platform for Multi-USV Cooperative Perception
- 2026-11-05 00:00 UTC · 1 reportsMariSense: A multi-modal dataset for environmental perception in maritimeInternational Journal of Robotics Research — Journal metadata：MariSense: A multi-modal dataset for environmental perception in maritime autonomy
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalMMUSV-Sim: A Maritime Simulation Platform for Multi-USV Cooperative Perception
This paper presents MMUSV-Sim, a maritime simulation platform built on Unreal Engine 5 and Project AirSim designed to enable cooperative perception among multiple unmanned surface vehicles (USVs). The authors address challenges such as limited sensing range, occlusions, and the high cost of sea trials by providing a configurable environment for synchronized multimodal data acquisition. Using this platform, they generated the MarU2U-200m dataset, comprising 341 sequences and 14,385 scene frames with consistent 3D annotations. The study establishes a cooperative bird's-eye-view vessel detection benchmark, demonstrating that Early Fusion improves LiDAR detection [email protected] from 64.26 to 81.46 compared to single-USV baselines, while RGB features provide further improvements. The work also evaluates the utility of generated data for pretraining real-world maritime detection models.
- International Journal of Robotics Research — Journal metadataSignalMariSense: A multi-modal dataset for environmental perception in maritime autonomy
This publication presents MariSense, the first multi-modal dataset for maritime autonomy perception that introduces dynamic waveform 4D mmWave radar alongside visible, thermal, LiDAR, marine radar, AIS, and navigation sensors. The dataset covers anchorages and fairways under varying weather, time, and sea conditions, with extrinsically calibrated sensors. It establishes benchmarks for object detection, tracking, and odometry and evaluates baseline methods to highlight needs in maritime perception, multi-modal fusion, and adaptive radar waveform design. The dataset is available at https://github.com/ORCAUBOAT/MariSense.
Event coverage history
Current attention 3·Peak within the comparable range 3（2026-11-07 02:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).