A Semantic Topology Graph to Detect Re-Localization and Loop Closure of the Visual Simultaneous Localization and Mapping System in a Dynamic Environment

Wang, Yang; Zhang, Yi; Hu, Lihe; Wang, Wei; Ge, Gengyu; Tan, Shuyi

doi:10.3390/s23208445

Cited by 3 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VSLAM, in theory, is defined as follows: A mobile robot, equipped with visual sensors, constructs a model of the surrounding environment and concurrently estimates its own motion while in motion, without any prior knowledge of the environment [11]. In their study, Wang et al [12] introduced a technique that utilizes a semantic topological map and ORB-SLAM2 for relocalization and loop closure detection. This strategy significantly enhances the precision of relocalization and loop closure detection in dynamic situations.…”

Section: Introductionmentioning

confidence: 99%

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning

Wang,

Zhao

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Precision control of multiple robotic fish visual navigation in complex underwater environments has long been a challenging issue in the field of underwater robotics. To address this problem, this paper proposes a multi-robot fish obstacle traversal technique based on the combination of cross-modal variational autoencoder (CM-VAE) and imitation learning. Firstly, the overall framework of the robotic fish control system is introduced, where the first-person view of the robotic fish is encoded into a low-dimensional latent space using CM-VAE, and then different latent features in the space are mapped to the velocity commands of the robotic fish through imitation learning. Finally, to validate the effectiveness of the proposed method, experiments are conducted on linear, S-shaped, and circular gate frame trajectories with both single and multiple robotic fish. Analysis reveals that the visual navigation method proposed in this paper can stably traverse various types of gate frame trajectories. Compared to end-to-end learning and purely unsupervised image reconstruction, the proposed control strategy demonstrates superior performance, offering a new solution for the intelligent navigation of robotic fish in complex environments.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning

Wang,

Zhao

et al. 2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…This approach explicitly represented the environment rather than just depicting surfaces or geometric primitives, leading to a more comprehensive understanding of the environment and enhancing several aspects. Ultimately, this method improved the intelligent interaction and decision-making ability of environment mapping [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Review on Enhancing Visual Simultaneous Localization and Mapping with Deep Semantic Segmentation

Liu,

He,

et al. 2024

Sensors

View full text Add to dashboard Cite

Visual simultaneous localization and mapping (VSLAM) enhances the navigation of autonomous agents in unfamiliar environments by progressively constructing maps and estimating poses. However, conventional VSLAM pipelines often exhibited degraded performance in dynamic environments featuring mobile objects. Recent research in deep learning led to notable progress in semantic segmentation, which involves assigning semantic labels to image pixels. The integration of semantic segmentation into VSLAM can effectively differentiate between static and dynamic elements in intricate scenes. This paper provided a comprehensive comparative review on leveraging semantic segmentation to improve major components of VSLAM, including visual odometry, loop closure detection, and environmental mapping. Key principles and methods for both traditional VSLAM and deep semantic segmentation were introduced. This paper presented an overview and comparative analysis of the technical implementations of semantic integration across various modules of the VSLAM pipeline. Furthermore, it examined the features and potential use cases associated with the fusion of VSLAM and semantics. It was found that the existing VSLAM model continued to face challenges related to computational complexity. Promising future research directions were identified, including efficient model design, multimodal fusion, online adaptation, dynamic scene reconstruction, and end-to-end joint optimization. This review shed light on the emerging paradigm of semantic VSLAM and how deep learning-enabled semantic reasoning could unlock new capabilities for autonomous intelligent systems to operate reliably in the real world.

show abstract

A comprehensive overview of core modules in visual SLAM framework

Cai,

Li,

et al. 2024

Neurocomputing

View full text Add to dashboard Cite

A Semantic Topology Graph to Detect Re-Localization and Loop Closure of the Visual Simultaneous Localization and Mapping System in a Dynamic Environment

Cited by 3 publications

References 38 publications

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning

A Comparative Review on Enhancing Visual Simultaneous Localization and Mapping with Deep Semantic Segmentation

A comprehensive overview of core modules in visual SLAM framework

Contact Info

Product

Resources

About