Path Coverage Optimization for USV with Side Scan Sonar for Victim Recovery

Este documento muestra un análisis de los resultados de búsqueda de literatura sobre sistemas tecnológicos de apoyo a personas víctimas de diversos eventos que implican perdida de movilidad en algún grado, requiriendo de desarrollos como la robótica asistencial. Se usa la guía PRISMA 2020 como referente de la revisión sistemática. Se consultó en la base de datos Scopus publicaciones sobre robótica y víctimas de la violencia de los últimos tres años, se construyeron redes bibliométricas con Vosviewer, se filtraron los resultados, se caracterizaron y se agruparon por la atención a víctimas tras desastres y enfermedades. Se concluye, es necesario encaminar los esfuerzos en robótica hacia la atención de víctimas de la violencia en Colombia apoyado en los avances identificados documentados a nivel científico dada la ausencia de evidencia al respecto.

show abstract

Collaborative Obstacle Detection for Dual USVs Using MGNN-DANet with Movable Virtual Nodes and Double Attention

He,

Li,

et al. 2024

Drones

View full text Add to dashboard Cite

To reduce missed detections in LiDAR-based obstacle detection, this paper proposes a dual unmanned surface vessels (USVs) obstacle detection method using the MGNN-DANet template matching framework. Firstly, point cloud templates for each USV are created, and a clustering algorithm extracts suspected targets from the point clouds captured by a single USV. Secondly, a graph neural network model based on the movable virtual nodes is designed, introducing a neighborhood distribution uniformity metric. This model enhances the local point cloud distribution features of the templates and suspected targets through a local sampling strategy. Furthermore, a feature matching model based on double attention is developed, employing self-attention to aggregate the features of the templates and cross-attention to evaluate the similarity between suspected targets and aggregated templates, thereby identifying and locating another USV within the targets detected by each USV. Finally, the deviation between the measured and true positions of one USV is used to correct the point clouds obtained by the other USV, and obstacle positions are annotated through dual-view point cloud clustering. Experimental results show that, compared to single USV detection methods, the proposed method reduces the missed detection rate of maritime obstacles by 7.88% to 14.69%.

show abstract

Path Coverage Optimization for USV with Side Scan Sonar for Victim Recovery

Cited by 3 publications

References 5 publications

Differentiable Boustrophedon Paths That Enable Optimization Via Gradient Descent

Differentiable Boustrophedon Paths That Enable Optimization Via Gradient Descent

Revisión sistemática de aplicaciones de robótica para atención de víctimas

Collaborative Obstacle Detection for Dual USVs Using MGNN-DANet with Movable Virtual Nodes and Double Attention

Contact Info

Product

Resources

About