A Novel Cooperative Design for USV–UAV Systems: 3-D Mapping Guidance and Adaptive Fuzzy Control

Li, Jiqiang; Zhang, Guoqing; Shan, Qihe; Zhang, Wensheng

doi:10.1109/tcns.2022.3220705

Cited by 58 publications

(27 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have used context-aware and depth-based fusion to improve object detection, and environment recognition [ 30 ]. Li et al [ 31 ] introduced an adaptive fuzzy control algorithm with a 3D mapping guidance system for the underactuated surface vehicle (USV) and unmanned aerial vehicle (UAV). Here, the 3D mapping guidance system provides the reference signals of the yaw degree of freedom for the USV and UAV, and the adaptive fuzzy control algorithm provides position and attitude information by fusing the dynamic surface control (DSC) and the backstepping techniques.…”

Section: Related Workmentioning

confidence: 99%

Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation

Yin

Ramalingam

Elara

et al. 2023

Sensors

View full text Add to dashboard Cite

Hazardous object detection (escalators, stairs, glass doors, etc.) and avoidance are critical functional safety modules for autonomous mobile cleaning robots. Conventional object detectors have less accuracy for detecting low-feature hazardous objects and have miss detection, and the false classification ratio is high when the object is under occlusion. Miss detection or false classification of hazardous objects poses an operational safety issue for mobile robots. This work presents a deep-learning-based context-aware multi-level information fusion framework for autonomous mobile cleaning robots to detect and avoid hazardous objects with a higher confidence level, even if the object is under occlusion. First, the image-level-contextual-encoding module was proposed and incorporated with the Faster RCNN ResNet 50 object detector model to improve the low-featured and occluded hazardous object detection in an indoor environment. Further, a safe-distance-estimation function was proposed to avoid hazardous objects. It computes the distance of the hazardous object from the robot’s position and steers the robot into a safer zone using detection results and object depth data. The proposed framework was trained with a custom image dataset using fine-tuning techniques and tested in real-time with an in-house-developed mobile cleaning robot, BELUGA. The experimental results show that the proposed algorithm detected the low-featured and occluded hazardous object with a higher confidence level than the conventional object detector and scored an average detection accuracy of 88.71%.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation

Yin

Ramalingam

Elara

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…where b = min½l min (K a ), 1=2k a and e = k p r e v max + 1=2k a (v max À v max (0)) 2 Then integrate equation ( 21), the following inequality (22) holds…”

Section: Double Layer Virtual Ship Guidancementioning

confidence: 99%

“…The robust neural damping technology with the compress ability for the network weights is proposed to stable the model perturbations and external disturbances. (2) The merit of the input-based ETM is only updating the control orders at the triggering instants. On the basis of the triggering rule, this leads to a lower activating frequency between the controllers and the actuators and effectively alleviates the communication burden.…”

Section: Control Designmentioning

confidence: 99%

“…In recent years, as intelligent vehicles have become a novel trend in the development of future vehicle field, intelligent control system has been developed rapidly in vehicle motion control. As one of the classical vehicle maneuvering scenarios, path-following has been widely used in marine engineering, 1,2 such as oceanic exploration, military reconnaissance, and natural resource detection. In the practical engineering applications, the occupation and security of communication channel have required more attentions to be attracted, which is of great significance in the field of intelligent vehicles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Event-triggered robust adaptive control for unmanned surface vehicle in presence of deception attacks

Zhang

Dong

Shan

2023

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

This article focuses on a double layer virtual ship guidance–based adaptive event–triggered path-following control for unmanned surface vehicle under the unknown actuator gain and deception attacks. In the guidance unit, the adaptive virtual ship is developed to derive the smooth reference paths for the controlled objective. That can effectively remove the abrupt phenomenon of actuators. Associated with the double layer virtual ship guidance strategy, a robust adaptive control algorithm is proposed for the unmanned surface vehicle by fusing the event-triggered rule and the adaptive compensated technique. In the algorithm, the deception attacks caused by the communication channel were compensated by constructing the attack adaptive parameters. That is critical to improve the accuracy and stabilize of the closed-loop control system. Besides, the transmission burden from the controller to the actuator was reduced for merits of the input-based event-triggered mechanism. Finally, the theoretical stability was proofed by the Lyapunov theorem, and the well performance was obtained through numerical simulation in presence of the time-varying disturbances.

show abstract

“…Thus, measuring the resulting impact generated by the towing cable and the flow would help assess the vehicle’s maneuvering behavior. 2 Many scientists are neglecting the impact of the towing cable since its effect would make the computational model quite complex and impossible to solve. Ergo, just a handful of researchers address these problems by including the consequences of the towing cable.…”

Section: Introductionmentioning

confidence: 99%

Modeling and analysis of static and dynamic behavior of marine towed cable-array system based on the vessel motion

Gharib,

Heydari,

Salehi Kolahi

2024

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Towing cables are playing a key role in maneuverability of moving or submerged vessels and the supporting vehicles in the ocean. This investigation evaluates the tension strength of the various parts of the marine towing cable and its geometric form under various operating conditions. Thus, the governing equations of the problem are introduced and analyzed first, followed by an examination of the method of solving the problem. We evaluate the cable’s static and dynamic behavior under different operating conditions using a continuous cable method. Then, we introduce and analyze the governing equations of the problem. The static mode comprises three operating conditions: a two-dimensional mode for constant vessel length, a two-dimensional mode for constant hydrophone depth, and a three-dimensional mode for different vessel motion and seawater directions. Dynamic mode operating conditions include vessel acceleration, vessel rotation, and cable tightening. The results show that, if the velocity of the seawater flow is zero, changing the angle of the vessel motion has little effect on the tension force of the cable-array and the length of the cable in the steady-state. It is also found that assuming a constant depth of the cable-array, the maximum tension force of the cable will increase to almost 35 times. However, if the length of the cable-array remains constant, the maximum tension force of the cable increases by around 13 times as the vessel’s speed increases by 5 times.

show abstract

A Novel Cooperative Design for USV–UAV Systems: 3-D Mapping Guidance and Adaptive Fuzzy Control

Cited by 58 publications

References 44 publications

Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation

Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation

Event-triggered robust adaptive control for unmanned surface vehicle in presence of deception attacks

Modeling and analysis of static and dynamic behavior of marine towed cable-array system based on the vessel motion

Contact Info

Product

Resources

About