Unmanned Surface Vessels (USVs) require robust navigation strategies for tasks like reaching specific targets autonomously in adverse weather conditions. Typically, the target position is well-defined, and USV localization is performed using Global Navigation Satellite Systems (GNSS) sensors. However, GNSS-denied environments, uncertain target locations, and harsh weather conditions make it difficult for traditional navigation approaches to work properly. This paper presents a novel control-based framework for robust autonomous navigation of a USV in GNSS-denied maritime environments with uncertain target locations. The framework employs a heterogeneous robotic system consisting of an Unmanned Aerial Vehicle (UAV) and a USV. It uses a multi-stage heading control approach with autonomous mode switching based on target proximity. Initially, UAV provides localization and guidance for the USV. As the target enters the USV's camera field-of-view, navigation modes switch to visual servoing. Finally, upon target acquisition within the LiDARs range, the LiDAR-based navigation stage recalculates the precise position of the target vessel to minimize the uncertainty of the target pose for precise maneuvering.The framework's effectiveness was validated in real-world sea conditions during the Muhammad Bin Zayed International Robotic Competition. The results demonstrate the proposed framework's potential for robust USV navigation in extreme weather conditions.
Abstract Tomatoes are a major crop worldwide, and accurately classifying their maturity is essential for many agricultural applications, such as harvesting, grading, and quality control. In this paper, the authors propose a novel method for tomato maturity classification using a convolutional transformer. Additionally, this study introduces a new tomato dataset named KUTomaData, explicitly designed to train deep-learning models for tomato segmentation and classification. KUTomaData is a compilation of images sourced from a greenhouse in the UAE, with approximately 1939 images available for training and testing. The dataset is prepared under various lighting conditions, viewing perspectives and employs different mobile camera sensors, thus distinguishing it from existing datasets.The contributions of this paper are threefold:Firstly, the authors propose a novel method for tomato maturity classification using a modular convolutional transformer. Secondly, the authors introduce a new tomato image dataset that contains images of tomatoes at different maturity levels. Lastly, the authors show that the convolutional transformer outperforms state-of-the-art methods for tomato maturity classification.The effectiveness of the proposed framework in handling cluttered and occluded tomato instances was evaluated using two additional public datasets, Laboro Tomato and Rob2Pheno Annotated Tomato, as benchmarks. The evaluation results across these three datasets demonstrate the exceptional performance of our proposed framework, surpassing the state-of-the-art by 58.14%, 65.42%, and 66.39% in terms of mean average precision scores for KUTomaData, Laboro Tomato, and Rob2Pheno Annotated Tomato, respectively.This work can improve tomato harvesting, grading, and quality control efficiency and accuracy.
World Elderly population is rising day by day, which increases demand for healthcare and number of caregivers.Ambient assisted livings is an emerging field(AAL) aimed at making Elderly and physically challenged people's life selfsufficient, safe and independent.Due to progresses in technology our surroundings are being automated.These may include homes, hospitals, factories and transportation.Ambient Assisted Environments for elder people monitor their daily activities to detect any abnormal or abrupt behavior.Any anomaly detected can be then sent to the concerned person who can be physician or family member of the elderly.As Ambient is a diverse field having a lot of technologies and application areas.Activity monitoring can be specified to a certain specific activity e.g.Fall detection and monitoring Vital Signs.This paper specifically focuses on smart home projects of Ambient Assisted Livings for elderly people monitoring overall daily activities.Out of two Ambient Technologies aspects providing support for indoor and outdoor activities of aged people this paper is focused on indoor smart environments.The prime objective of this paper is to analyze different researches being done in Ambient Assisted Livings (AAL) used for home automation or building smart homes.A comparative study of various AAL environments is followed by a discussion on issues linked with AAL.Along with the analysis of issues and challenges associated with these, a roadmap is also provided for the researchers for knowledge acquisition bout AAL systems.
Objectives: This paper presents the overview of five different tools and techniques for visually impaired, namely Braille Touch, Online Multi language Word Processor, Helping Hand, Sound Game and Readable Image. Methods: This is not a comparison of the tools, so each of the tool or technology was studied separately in terms of its design and working, merits and de-merits the experiments and evaluation etc. Findings: Braille Touch is a software-based technology and is very cheap and user friendly as compared to other available Braille Technologies. But, it can’t be implemented on Ordinary cell phones and needs touch devices. The Sound Game works automatically so it can be used by single user without any assistance. It can be used at home or small space because of compact size. Online Multi language Word ProcessorInterface was very simple and light colors were used to assist the color blinds but Translation and Transliteration were done using Google API that doesn’t provide accurate results. System is not evaluated to check the performance and popularity. Readable Image provides accessibility and readability of images at different levels of detail to the persons having visual impairments while previous tools could only read the image by its caption and tags.Helping Hand device is portable and very easy to use. The device was tested on a small group so the results cannot be considered satisfactory. Improvements: The Braille Touch device needs to be evaluated. More functions can be added in Sound Game and Online Multi language Word Processor. The approach for the Readable Image will be implemented.Keywords: Braille, Tools, Technologies, Visually Handicap, Visually Impaired
Accurate knee joint angle prediction is crucial for biomechanical analysis and rehabilitation. In this study, we introduce FocalGatedNet, a novel deep learning model that incorporates Dynamic Contextual Focus (DCF) Attention and Gated Linear Units (GLU) to enhance feature dependencies and interactions. Our model is evaluated on a large-scale dataset and compared to established models in multi-step gait trajectory prediction.Our results reveal that FocalGatedNet outperforms existing models for long-term prediction lengths (20 ms, 60 ms, 80 ms, and 100 ms), demonstrating significant improvements in Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Specifically for the case of 80 ms, FocalGatedNet achieves a notable MAE reduction of up to 24\%, RMSE reduction of up to 14\%, and MAPE reduction of up to 36\% when compared to Transformer, highlighting its effectiveness in capturing complex knee joint angle patterns.Moreover, FocalGatedNet maintains a lower computational load than most equivalent deep learning models, making it an efficient choice for real-time biomechanical analysis and rehabilitation applications. Code implementation for the FocalGatedNet model can be found in the GitHub repository: https://github.com/LyesSaadSaoud/FocalGatedNet
Stroke survivors who experience severe hemiparesis often cannot completely recover the use of their hand and arm. Many of the rehabilitation devices currently available are designed to increase the functional recovery right after the stroke when, in some cases, biological restoring and plastic reorganization of the central nervous system can take place. However, this is not always the case. Even after extensive therapeutic interventions, the probability of regaining functional use of the impaired hand is low. In this respect, we present a novel robotic system composed of a supernumerary robotic finger and a wearable cutaneous finger interface. The supernumerary finger is used to help grasping objects while the wearable interface provides information about the forces exerted by the robotic finger on the object being held. We carried out two experiments, enrolling 16 healthy subjects and 2 chronic stroke patients. Results showed that using the supernumerary finger greatly improved the grasping capabilities of the subjects. Moreover, providing cutaneous feedback significantly improved the performance of the considered task and was preferred by all subjects.
A branch of robotics, variable impedance actuation, along with one of its subfields variable stiffness actuation (VSA) targets the realization of complaint robotic manipulators. In this paper, we present the modeling, identification, and control of a discrete variable stiffness actuator (DVSA), which will be developed for complaint manipulators in the future. The working principle of the actuator depends on the involvement of series and parallel springs. We firstly report the conceptual design of a stiffness varying mechanism, and later the details of the dynamic model, system identification, and control techniques are presented. The dynamic parameters of the system are identified by using the logarithmic decrement algorithm, while the control schemes are based on linear quadratic control (LQR) and computed torque control (CTC), respectively. The numerical simulations are performed for the evaluation of each method, and results showed the good potentialities for the system. Future work includes the implementation of the presented approach on the hardware.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cpath fill='%23fff' d='m8.751-17.959 10.11 11.373L3.997-9.844l13.94-6.1-7.692 13.129z'/%3e%3c/svg%3e)
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)