arXiv subjects

Di Meng

Publications and source records attributed to Di Meng.

3 recordsLinked to original sources

arXiv2025

A Hierarchical Region-Based Approach for Efficient Multi-Robot Exploration

Multi-robot autonomous exploration in an unknown environment is an important application in robotics.Traditional exploration methods only use information around frontier points or viewpoints, ignoring spatial information of unknown areas. Moreover, finding the exact optimal solution for multi-robot task allocation is NP-hard, resulting in significant computational time consumption. To address these issues, we present a hierarchical multi-robot exploration framework using a new modeling method called RegionGraph. The proposed approach makes two main contributions: 1) A new modeling method for unexplored areas that preserves their spatial information across the entire space in a weighted graph called RegionGraph. 2) A hierarchical multi-robot exploration framework that decomposes the global exploration task into smaller subtasks, reducing the frequency of global planning and enabling asynchronous exploration. The proposed method is validated through both simulation and real-world experiments, demonstrating a 20% improvement in efficiency compared to existing methods.

cs.RO↗

arXiv2022

A Machine Learning Approach to Digital Contact Tracing: TC4TL Challenge

Contact tracing is a method used by public health organisations to try prevent the spread of infectious diseases in the community. Traditionally performed by manual contact tracers, more recently the use of apps have been considered utilising phone sensor data to determine the distance between two phones. In this paper, we investigate the development of machine learning approaches to determine the distance between two mobile phone devices using Bluetooth Low Energy, sensory data and meta data. We use TableNet architecture and feature engineering to improve on the existing state of the art (total nDCF 0.21 vs 2.08), significantly outperforming existing models.

cs.LG↗

arXiv2021

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Vertebrae localization, segmentation and identification in CT images is key to numerous clinical applications. While deep learning strategies have brought to this field significant improvements over recent years, transitional and pathological vertebrae are still plaguing most existing approaches as a consequence of their poor representation in training datasets. Alternatively, proposed non-learning based methods take benefit of prior knowledge to handle such particular cases. In this work we propose to combine both strategies. To this purpose we introduce an iterative cycle in which individual vertebrae are recursively localized, segmented and identified using deep-networks, while anatomic consistency is enforced using statistical priors. In this strategy, the transitional vertebrae identification is handled by encoding their configurations in a graphical model that aggregates local deep-network predictions into an anatomically consistent final result. Our approach achieves state-of-the-art results on the VerSe20 challenge benchmark, and outperforms all methods on transitional vertebrae as well as the generalization to the VerSe19 challenge benchmark. Furthermore, our method can detect and report inconsistent spine regions that do not satisfy the anatomic consistency priors. Our code and model are openly available for research purposes.

eess.IV↗