A Survey on Visual Navigation and Positioning for Autonomous UUVs

Qin, Jiangying; Li, Ming; Li, Deren; Zhong, Jiageng; Yang, Ke

doi:10.3390/rs14153794

Cited by 30 publications

(16 citation statements)

References 114 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2022 Spacecraft Navigation Deep learning for spacecraft dynamics control, guidance and navigation [40]. 2022 Visual Navigation Unmanned underwater vehicles [41]. 2022 Unmanned Aerial Vehicle Reinforcement Learning for UAVs [14].…”

Section: Year Topic Highlightmentioning

confidence: 99%

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Golroudbari¹,

Sabour²

2023

Preprint

View full text Add to dashboard Cite

This review paper presents a comprehensive overview of end-to-end deep learning frameworks used in the context of autonomous navigation, including obstacle detection, scene perception, path planning, and control. The paper aims to bridge the gap between autonomous navigation and deep learning by analyzing recent research studies and evaluating the implementation and testing of deep learning methods. It emphasizes the importance of navigation for mobile robots, autonomous vehicles, and unmanned aerial vehicles, while also acknowledging the challenges due to environmental complexity, uncertainty, obstacles, dynamic environments, and the need to plan paths for multiple agents. The review highlights the rapid growth of deep learning in engineering data science and its development of innovative navigation methods. It discusses recent interdisciplinary work related to this field and provides a brief perspective on the limitations, challenges, and potential areas of growth for deep learning methods in autonomous navigation. Finally, the paper summarizes the findings and practices at different stages, correlating existing and future methods, their applicability, scalability, and limitations. The review provides a valuable resource for researchers and practitioners working in the field of autonomous navigation and deep learning.

show abstract

Section: Year Topic Highlightmentioning

confidence: 99%

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Golroudbari¹,

Sabour²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, autonomous underwater vehicles (AUVs) have found extensive application in several domains including maritime survey, underwater search and rescue, marine [8,9]. Vision-based techniques depend on the establishment of image libraries and the precision of image processing [10][11][12]. The inertial navigation system (INS) is typically integrated with several auxiliary methods, however, over time, the positioning inaccuracies build [3,13].…”

Section: Introductionmentioning

confidence: 99%

High frame rate acoustic navigation of AUV based on range ambiguity suppression

Li,

Fu,

Zou

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Underwater acoustic navigation is extensively utilized across many industries due to its exceptional dependability and continuous real-time functionality. Due to the swift advancement of technology in recent years, the velocity of autonomous underwater vehicles (AUVs) has progressively increased. A high frame rate is required for the underwater acoustic navigation system in order to precisely obtain the trajectory of the AUV. Nevertheless, the discrepancy lies in the fact that the high frame rate and the unambiguous measurement could be seen as contradictory. Higher frame rates greatly raise the probability of range ambiguity, leading to various potential pseudo solutions that exacerbate the difficulty of accurate positioning and noticeably impact navigation performance. To address the aforementioned issue, a high frame rate acoustic navigation technique that relies on the suppression of range ambiguity has been studied in this paper. Initially, the relationship between measurements were investigated, specifically the time delay and Doppler shift, and the confusing periodic leap. Subsequently, the coupling model was employed to develop a high-precision acoustic navigation model, taking into account the statistical characteristics of measurements. We also examined a high-precision solving approach. Ultimately, the proposed method was validated through both simulation analysis and field testing to confirm its practicality and efficiency. The results demonstrate that it can attain a high level of accuracy in resolving the ambiguous problem and achieve high-precise acoustic navigation.

show abstract

“…This research demonstrates that uncalibrated visual perception, guided by reinforcement learning, can direct the robot to perform repeatable actions. Visual perception, when used for control feedback, requires high frequency and low latency, and hence, in underwater robots, it is more commonly employed for target identification and tracking, navigation, and positioning [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

A Fish-like Binocular Vision System for Underwater Perception of Robotic Fish

Tong,

Wu,

Wang

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Biological fish exhibit a remarkably broad-spectrum visual perception capability. Inspired by the eye arrangement of biological fish, we design a fish-like binocular vision system, thereby endowing underwater bionic robots with an exceptionally broad visual perception capacity. Firstly, based on the design principles of binocular visual field overlap and tangency to streamlined shapes, a fish-like vision system is developed for underwater robots, enabling wide-field underwater perception without a waterproof cover. Secondly, addressing the significant distortion and parallax of the vision system, a visual field stitching algorithm is proposed to merge the binocular fields of view and obtain a complete perception image. Thirdly, an orientation alignment method is proposed that draws scales for yaw and pitch angles in the stitched images to provide a reference for the orientation of objects of interest within the field of view. Finally, underwater experiments evaluate the perception capabilities of the fish-like vision system, confirming the effectiveness of the visual field stitching algorithm and the orientation alignment method. The results show that the constructed vision system, when used underwater, achieves a horizontal field of view of 306.56°. The conducted work advances the visual perception capabilities of underwater robots and presents a novel approach to and insight for fish-inspired visual systems.

show abstract

A Survey on Visual Navigation and Positioning for Autonomous UUVs

Cited by 30 publications

References 114 publications

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

High frame rate acoustic navigation of AUV based on range ambiguity suppression

A Fish-like Binocular Vision System for Underwater Perception of Robotic Fish

Contact Info

Product

Resources

About