Navigation Capabilities Research Articles

Hybrid Machine Learning and Reinforcement Learning Framework for Adaptive UAV Obstacle Avoidance

This review explores the integration of machine learning (ML) and reinforcement learning (RL) techniques in enhancing the navigation and obstacle avoidance capabilities of Unmanned Aerial Vehicles (UAVs). Various RL algorithms are assessed for their effectiveness in teaching UAVs autonomous navigation, with a focus on state representation from UAV sensors and real-time environmental interaction. The review identifies the strengths and limitations of current methodologies and highlights gaps in the literature, proposing future research directions to advance UAV technology. Interdisciplinary approaches combining robotics, AI, and aeronautics are suggested to improve UAV performance in complex environments.

Biohybrid Micro/Nanorobots: Pioneering the Next Generation of Medical Technology.

Biohybrid micro/nanorobots hold a great potential for advancing biomedical research. These tiny structures, designed to mimic biological organisms, offer a promising method for targeted drug delivery, tissue engineering, biosensing/imaging, and cancer therapy, among other applications. The integration of biology and robotics opens new possibilities for minimally invasive surgeries and personalized healthcare solutions. The key challenges in the development of biohybrid micro/nanorobots include ensuring biocompatibility, addressing manufacturing scalability, enhancing navigation and localization capabilities, maintaining stability in dynamic biological environments, navigating regulatory hurdles, and successfully translating these innovative technologies into clinical applications. Herein, the recent advancements, challenges, and future perspectives related to the biomedical applications of biohybrid micro/nanorobots are described. Indeed, this review sheds light on the cutting-edge developments in this field, providing researchers with an updated overview of the current potential of biohybrid micro/nanorobots in the realm of biomedical applications, and offering insights into their practical applications. Furthermore, it delves into recent advancements in the field of biohybrid micro/nanorobotics, providing a comprehensive analysis of the current state-of-the-art technologies and their future applications in the biomedical field.

Software Architecture Design of ASV Rybitwa: Development of an Autonomous Surface Vehicle for Dynamic Navigation and Task Execution

Abstract This paper introduces the software design of an Autonomous Surface Vehicle (ASV) named ASV Rybitwa. It was designed as an easily transportable platform capable of autonomous navigation and performing tasks during the RoboBoat 2024 competition, with emphasis on its modularity, generality and extendibility. The paper presents a software architecture for a small autonomous surface vehicle using novel tools that provide easy system integration and expansion. To meet such requirements, a generic control box connecting an autopilot (PX4) and a onboard computer (NVIDIA Jetson Nano) was developed so as to host the Robot Operating System 2 (ROS2) and to interact with sensors and actuators. Computer vision from three Oak-D cameras, equipped with AI algorithm support (YOLOv8), was used for navigation and obstacle avoidance. The decision-making system was designed using behavioural trees and computer vision, allowing the vehicle’s capabilities to be adapted to the needs of the current tasks and mission. In addition, an Omni X propulsion system was proposed, providing full holonomy and enhancing dynamic positioning and navigation capabilities in complex navigational conditions. In addition this paper describes lessons learned from ASV Rybitwa’s real-world testing during the aforementioned competition.

Multi-agent long-distance end-to-end indoor navigation: using imitation learning pre-training and global map

Abstract To address the navigation challenges of mobile robot swarm coordination in complex environments, this paper presents a distributed navigation approach for mobile robot swarm. The study initially formulates the problem of robot swarm navigation as a partially observable Markov decision process, employing a distributed proximal policy optimization algorithm to train decision models mapping observations to actions directly. Furthermore, it adopts imitation learning pre-training to maximize expert decisions in the initial training phase, thereby reducing exploration space. Lastly, an improved path point generation algorithm along with a spatiotemporal reachability calculation method is proposed to guide the Deep Reinforcement Learning policy in accomplishing long-distance indoor navigation. Comprehensive performance evaluations are conducted in simulated environments to compare the proposed method with existing approaches. Results demonstrate that the proposed approach effectively enhances both convergence speed and model performance, while significantly improving the navigation capabilities of robot swarms in complex environments.

Perform assessment of COLREGs onboard a maritime autonomous surface ship: Narrow Channels and Traffic Separation Schemes

Abstract The usage of Maritime Autonomous Surface Ships in coastal and heavily used maritime environments necessitates advanced navigation systems capable of fully complying with the International Regulations for Preventing Collisions at Sea 1972 and not only open sea encounters. A significant challenge in this domain is enabling autonomous vessels to understand and navigate complex collision avoidance scenarios dictated by Rule 9 Narrow Channels and Rule 10 Traffic Separation Schemes. These rules are not well covered by research and only partial solutions have been proposed. To address this, we propose a ruleset for a system that can blend the traffic situation and geometric constraints extracted from Electronic Navigational Charts in S-57 format. The proposed ruleset extends our previous work on operationalization of COLREGs by introducing spatial features describing the maritime geometries relevant for traffic situations in Narrow Channels and Traffic Separation Schemes. We apply the ruleset to various traffic situations, showing how the inclusion of geometric context improves decision-making by reducing ambiguity and therefore enables the assessment of traffic situations and ship encounters in the vicinity of Narrow Channels and Traffic Separation Schemes. Our work outlines how the integration of spatial features into a rule-based system enables autonomous navigation capabilities of MASS for safe operations and compliance with maritime regulations.

Deep‐Learning‐Assisted Triboelectric Whisker Sensor Array for Real‐Time Motion Sensing of Unmanned Underwater Vehicle

AbstractAquatic animals can perceive their surrounding flow fields through highly evolved sensory systems. For instance, a seal whisker array understands the hydrodynamic field that allows seals to forage and navigate in dark environments. In this work, a deep learning‐assisted underwater triboelectric whisker sensor array (TWSA) is designed for the 3D motion estimation and near‐field perception of unmanned underwater vehicles. Each sensor comprises a high aspect ratio elliptical whisker shaft, four sensing units at the root of the elliptical whisker shaft, and a flexible corrugated joint simulating the skin on the cheek surface of aquatic animals. The TWSA effectively identifies flow velocity and direction in the 3D underwater environments and exhibits a rapid response time of 19 ms, a high sensitivity of 0.2V/ms−1, and a signal‐to‐noise ratio of 58 dB. The device also locks onto the frequency of the upstream wake vortex, achieving a minimal detection accuracy of 81.2%. Moreover, when integrated with an unmanned underwater vehicle, the TWSA can estimate 3D trajectories assisted by a trained deep learning model, with a root mean square error of ≈0.02. Thus, the TWSA‐based assisted perception holds immense potential for enhancing unmanned underwater vehicle near‐field perception and navigation capabilities across a wide range of applications.

Optimizing Autonomous UAV Navigation with D* Algorithm for Sustainable Development

Autonomous navigation for Unmanned Aerial Vehicles (UAVs) has emerged as a critical enabler in various industries, from agriculture, delivery services, and surveillance to search and rescue operations. However, navigating UAVs in dynamic and unknown environments remains a formidable challenge. This paper explores the application of the D* algorithm, a prominent path-planning method rooted in artificial intelligence and widely used in robotics, alongside comparisons with other algorithms, such as A* and RRT*, to augment autonomous navigation capabilities in UAVs’ implication for sustainability development. The core problem addressed herein revolves around enhancing UAV navigation efficiency, safety, and adaptability in dynamic environments. The research methodology involves the integration of the D* algorithm into the UAV navigation system, enabling real-time adjustments and path planning that account for dynamic obstacles and evolving terrain conditions. The experimentation phase unfolds in simulated environments designed to mimic real-world scenarios and challenges. Comprehensive data collection, rigorous analysis, and performance evaluations paint a vivid picture of the D* algorithm’s efficacy in comparison to other navigation methods, such as A* and RRT*. Key findings indicate that the D* algorithm offers a compelling solution, providing UAVs with efficient, safe, and adaptable navigation capabilities. The results demonstrate a path planning efficiency improvement of 92%, a 5% reduction in collision rates, and an increase in safety margins by 2.3 m. This article addresses certain challenges and contributes by demonstrating the practical effectiveness of the D* algorithm, alongside comparisons with A* and RRT*, in enhancing autonomous UAV navigation and advancing aerial systems. Specifically, this study provides insights into the strengths and limitations of each algorithm, offering valuable guidance for researchers and practitioners in selecting the most suitable path-planning approach for their UAV applications. The implications of this research extend far and wide, with potential applications in industries such as agriculture, surveillance, disaster response, and more for sustainability.

Intelligent Surface Recognition for Autonomous Tractors Using Ensemble Learning with BNO055 IMU Sensor Data

This study aims to enhance the navigation capabilities of autonomous tractors by predicting the surface type they are traversing using data collected from BNO055 Inertial Measurement Units (IMU sensors). IMU sensor data were collected from a small mobile robot driven over seven different floor surfaces within a university environment, including tile, carpet, grass, gravel, asphalt, concrete, and sand. Several machine learning models, including Logistic Regression, K-Neighbors, SVC, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, and XGBoost, were trained and evaluated to predict the surface type based on the sensor data. The results indicate that Random Forest and XGBoost achieved the highest accuracy, with scores of 98.5% and 98.7% in K-Fold Cross-Validation, respectively, and 98.8% and 98.6% in an 80/20 Random State split. These findings demonstrate that ensemble methods are highly effective for this classification task. Accurately identifying surface types can prevent operational errors and improve the overall efficiency of autonomous systems. Integrating these models into autonomous tractor systems can significantly enhance adaptability and reliability across various terrains, ensuring safer and more efficient operations.

Semantic Environment Atlas for Object-Goal Navigation

In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the relationships between places and objects, thereby enriching the navigational context. These maps are constructed from image observations and capture visual landmarks as sparsely encoded nodes within the environment. The SEA integrates multiple semantic maps from various environments, retaining a memory of place-object relationships, which proves invaluable for tasks such as visual localization and navigation. We developed navigation frameworks that effectively leverage the SEA, and we evaluated these frameworks through visual localization and object-goal navigation tasks. Our SEA-based localization framework significantly outperforms existing methods, accurately identifying locations from single query images. Experimental results in Habitat Savva et al. (2019)scenarios show that our method not only achieves a success rate of 39.0%—an improvement of 12.4% over the current state-of-the-art—but also maintains robustness under noisy odometry and actuation conditions, all while keeping computational costs low.

Load-adaptive MAC protocol for frontier detection in Underwater Mobile Sensor Network

This work proposes a load-adaptive Medium Access Control (MAC) protocol for the frontier/boundary detection application of underwater phenomena using Underwater Mobile Sensor Network (UWMSN). A leader-follower architecture of a swarm of underwater vehicles is proposed here. Autonomous Underwater Vehicles (AUVs) traverse a random mobility pattern beneath one Autonomous Surface Vehicle (ASV) (leader) in the proposed network. ASV has to guide multiple-follower AUVs in the event of interest. The vehicular swarm aims to explore the frontiers in the event to build the map. Load-adaptive MAC protocol is therefore proposed and implemented in this hybrid multi-vehicular network to ensure seamless vehicular communications. The ASV has navigational capabilities to aid the AUVs in navigation and data collection. The proposed MAC protocol can adjust the dynamic mobility and load in the network. The protocol aims to provide dynamic Time Division Multiple Access (TDMA) slots for the AUVs wirelessly linked in the vicinity of the ASV. These slots are used for ranging/navigation and data transmission. Additional urgent data from any AUVs can be transmitted in open Carrier Sense Multiple Access (CSMA) protocol following the TDMA duration. Results have been generated by comparing protocols like CSMA, ALOHA, and TDMA with the proposed Load-Adaptive MAC protocol. The protocols have been compared to the throughput vs number of nodes and throughput vs simulation time. It has been observed that the proposed MAC can perform better than ALOHA and CSMA protocols. Nevertheless, it can produce comparable results for TDMA protocol while supporting the dynamic mobility and load in the network meantime supporting urgent data transmission for nodes in demand.

Adaptive Navigation Performance Evaluation Method for Civil Aircraft Navigation Systems with Unknown Time-Varying Sensor Noise.

During civil aviation flights, the aircraft needs to accurately monitor the real-time navigation capability and determine whether the onboard navigation system performance meets the required navigation performance (RNP). The airborne flight management system (FMS) uses actual navigation performance (ANP) to quantitatively calculate the uncertainty of aircraft position estimation, and its evaluation accuracy is highly dependent on the position estimation covariance matrix (PECM) provided by the airborne integrated navigation system. This paper proposed an adaptive PECM estimation method based on variational Bayes (VB) to solve the problem of ANP misevaluation, which is caused by the traditional simple ANP model failing to accurately estimate PECM under unknown time-varying noise. Combined with the 3D ANP model proposed in this paper, the accuracy of ANP evaluation can be significantly improved. This enhancement contributes to ensured navigation integrity and operational safety during civil flight.

Trajectory tracking control based on genetic algorithm and proportional integral derivative controller for two-wheel mobile robot

This paper uses the genetic algorithm (GA) to optimize the proportional integral derivative (PID) controller parameters to present the motion control design for a two-wheeled mobile robot autonomous system. The GA algorithm determines a collision-free travel curve for a robot with a tangential velocity restriction constraint. A trajectory-tracking controller based on the PID control structure is developed to monitor the calculated route curves for the mobile robot. Simulation results show the effectiveness of the GA-PID controller compared to the PID controller. The GA-PID controller demonstrates improved performance in trajectory tracking and collision avoidance, making it suitable for controlling the motion of two-wheeled mobile robots. The GA's optimization process allows for better tuning of the PID controller parameters, resulting in more efficient and accurate robot motion control. The results suggest that the proposed GA-PID controller is a promising approach for enhancing mobile robots' autonomous navigation capabilities.

Virtual Reality Head-Mounted Display (HMD) and Preoperative Patient-Specific Simulation: Impact on Decision-Making in Pediatric Urology: Preliminary Data.

To assess how virtual reality (VR) patient-specific simulations can support decision-making processes and improve care in pediatric urology, ultimately improving patient outcomes. Children diagnosed with urological conditions necessitating complex procedures were retrospectively reviewed and enrolled in the study. Patient-specific VR simulations were developed with medical imaging specialists and VR technology experts. Routine CT images were utilized to create a VR environment using advanced software platforms. The accuracy and fidelity of the VR simulations was validated through a multi-step process. This involved comparing the virtual anatomical models to the original medical imaging data and conducting feedback sessions with pediatric urology experts to assess VR simulations' realism and clinical relevance. A total of six pediatric patients were reviewed. The median age of the participants was 5.5 years (IQR: 3.5-8.5 years), with an equal distribution of males and females across both groups. A minimally invasive laparoscopic approach was performed for adrenal lesions (n = 3), Wilms' tumor (n = 1), bilateral nephroblastomatosis (n = 1), and abdominal trauma in complex vascular and renal malformation (ptotic and hypoplastic kidney) (n = 1). Key benefits included enhanced visualization of the segmental arteries and the deep vascularization of the kidney and adrenal glands in all cases. The high depth perception and precision in the orientation of the arteries and veins to the parenchyma changed the intraoperative decision-making process in five patients. Preoperative VR patient-specific simulation did not offer accuracy in studying the pelvic and calyceal anatomy. VR patient-specific simulations represent an empowering tool in pediatric urology. By leveraging the immersive capabilities of VR technology, preoperative planning and intraoperative navigation can greatly impact surgical decision-making. As we continue to advance in medical simulation, VR holds promise in educational programs to include even surgical treatment of more complex urogenital malformations.

Real-time cloud computing of GNSS measurements from smartphones and mobile devices for enhanced positioning and navigation

In recent years, Global Navigation Satellite Systems (GNSSs) have become integral to our daily lives because of their precise positioning and navigation capabilities. Widespread use of smartphones equipped with GNSS receivers results in the generation of a huge amount of positioning data. Therefore, real-time cloud computing has emerged as a promising approach to effectively leverage this wealth of location information. In this study, we developed an Android app that captures raw GNSS data from smartphones, leverages cloud computing resources, calculates the position of the device, and returns the computed solution to the user. Integration of cloud-based processing not only conserves the device resources but also enables real-time position calculation, paving the way for enhanced location-based applications and services.

Advancements and limitations in integrating robotics into medicine: A comprehensive review

The integration of robotics into medicine represents a groundbreaking advancement with transformative potential across various medical domains. This comprehensive review delves into both the remarkable advancements and the significant limitations associated with this integration. Advancements in robotic medicine include precision surgery, which facilitatesintricate procedures with enhanced accuracy and minimal invasiveness. Robotic systems enable teleoperation, allowing surgeons to perform procedures remotely, and expanding access to specialized care. Enhanced imaging and navigation capabilities further augment surgical precision and efficiency. Additionally, robotics play a vital role in rehabilitation therapy, aiding in personalized patient recovery. However, these advancements have substantial limitations. The cost of acquiring and maintaining robotic systems poses a significant barrier to widespread adoption, particularly in resource-constrained healthcare settings. Moreover, mastering robotic surgical techniques demands extensive training, contributing to a steep learning curve for healthcare professionals. Technical challenges such as system reliability and interoperability also present hurdles to seamless integration. Ethical considerations surrounding patient autonomy, accountability, and data privacy must be carefully addressed. Legal frameworks and regulatory standards are essential to ensure patient safety and mitigate liability risks associated with robotic-assisted interventions. Furthermore, disparities in access to robotic technology may exacerbate existing healthcare inequalities. Addressing these limitations requires concerted efforts from healthcare stakeholders, policymakers, and technology developers. Collaborative initiatives are needed to overcome financial, educational, technical, ethical, and regulatory barriers to integrating robotics into mainstream medical practice. By navigating these challenges, the full potential of robotics in medicine can be realized, ushering in an era of enhanced precision, efficiency, and accessibility in healthcare delivery.

SoftWind: Software-defined trajectory correction modelling of gust wind effects on internet of drone things using glowworm swarm optimization

The dynamic nature of the atmosphere, especially wind gust, poses a crucial challenge to efficient and real-time drone operations. This article presents a novel MQTT based software-defined drone network for trajectory correction of drone flights in gusty wind conditions using Glowworm Swarm Optimization (GSO). By imposing the GSO to the software-defined drone network, our proposed model SoftWind has optimized the navigation and control capabilities of drones by correcting the trajectories in a gusty wind environment. We have analyzed the trajectories and convergence of drones due to wind gusts. As wind disturbances affect the trajectories of drones, we have corrected it by our trajectory correction model and evaluated the direction of the drones must fly to mitigate the wind gust and the resultant velocity compared to the no-wind environment. This study analyzed the trajectories of 100 drone flights due to various wind gust lengths (i.e., 40 m, 10 m, 6 m, and 3 m) for a fixed gust amplitude of 15 m/s and various gust amplitude (i.e., 0 m/s, 5 m/s, 15 m/s, and 40 m/s) for a fixed gust length 5 m. We observed that all the drones are converged to a single point due to low gust length (≤ 5 m) and high gust amplitude (≥ 35 m/s). It is also found that the direction of the drone must fly 28.87°. East of South to mitigate the effect of wind gusts having 10 m gust length and 15 m/s gust amplitude and the resultant velocity of the drone is 22.38 m/s. The result shows that SoftWind reduces the convergence time by 26 %-54 % as compared to other existing models.

Enhancing mobile robot navigation: integrating reactive autonomy through deep learning and fuzzy behavior

Objective: This study aimed to develop a control architecture for reactive autonomous navigation of a mobile robot by integrating Deep Learning techniques and fuzzy behaviors based on traffic signal recognition. Materials: The research utilized transfer learning with the Inception V3 network as a base for training a neural network to identify traffic signals. The experiments were conducted using a Donkey-Car, an Ackermann-steering-type open-source mobile robot, with inherent computational limitations. Results: The implementation of the transfer learning technique yielded a satisfactory result, achieving a high accuracy of 96.2% in identifying traffic signals. However, challenges were encountered due to delays in frames per second (FPS) during testing tracks, attributed to the Raspberry Pi's limited computational capacity. Conclusions: By combining Deep Learning and fuzzy behaviors, the study demonstrated the effectiveness of the control architecture in enhancing the robot's autonomous navigation capabilities. The integration of pre-trained models and fuzzy logic provided adaptability and responsiveness to dynamic traffic scenarios. Future research could focus on optimizing system parameters and exploring applications in more complex environments to further advance autonomous robotics and artificial intelligence technologies.

An Automatic Method for Elbow Joint Recognition, Segmentation and Reconstruction.

Elbow computerized tomography (CT) scans have been widely applied for describing elbow morphology. To enhance the objectivity and efficiency of clinical diagnosis, an automatic method to recognize, segment, and reconstruct elbow joint bones is proposed in this study. The method involves three steps: initially, the humerus, ulna, and radius are automatically recognized based on the anatomical features of the elbow joint, and the prompt boxes are generated. Subsequently, elbow MedSAM is obtained through transfer learning, which accurately segments the CT images by integrating the prompt boxes. After that, hole-filling and object reclassification steps are executed to refine the mask. Finally, three-dimensional (3D) reconstruction is conducted seamlessly using the marching cube algorithm. To validate the reliability and accuracy of the method, the images were compared to the masks labeled by senior surgeons. Quantitative evaluation of segmentation results revealed median intersection over union (IoU) values of 0.963, 0.959, and 0.950 for the humerus, ulna, and radius, respectively. Additionally, the reconstructed surface errors were measured at 1.127, 1.523, and 2.062 mm, respectively. Consequently, the automatic elbow reconstruction method demonstrates promising capabilities in clinical diagnosis, preoperative planning, and intraoperative navigation for elbow joint diseases.

Second generation robotic-assisted percutaneous balloon sacroplasty

Abstract Sacroplasty is one of the surgical modalities described in the treatment of sacral insufficiency fractures that don’t respond to non-operative treatment. While the percutaneous procedure is generally done under sedation, complications can arise from cement leakage into the spinal canal and sacral foramina. We present a case of Robotic-Assisted Percutaneous Balloon Sacroplasty in a patient with unilateral sacral insufficiency fracture using the MazorX stealth edition. A 55-year-old female presented with a left-sided sacral insufficiency fracture which was not responding to non-operative treatment. She underwent Robotic-Assisted Percutaneous Balloon Sacroplasty using the robotic arm and navigation capabilities of the MazorX stealth edition. About 9 mL of bone cement with hydroxyapatite was injected into the S1 body and left ala. The patient was mobilized post-operatively with minimal pain, 2 h after the procedure. Robotic assistance in percutaneous balloon sacroplasty ensures proper tracks for injection of bone cement with reduced chances of cement leakage.

Evaluating the feasibility of using augmented reality for tooth preparation

ObjectivesTooth preparation is complicated because it requires the preparation of an abutment while simultaneously predicting the ideal shape of the tooth. This study aimed to develop and evaluate a system using augmented reality (AR) head-mounted displays (HMDs) that provide dynamic navigation capabilities for tooth preparation. MethodsThe proposed system utilizes optical see-through HMDs to overlay digital information onto the real world and enrich the user's environment. By integrating tracking algorithms and three-dimensional modeling, the system provides real-time visualization and navigation capabilities during tooth preparation by using two different visualization techniques. The experimental setup involved a comprehensive analysis of the distance to the surface and cross-sectional angles between the ideal and prepared teeth using three scenarios: traditional (without AR), overlay (AR-assisted visualization of the ideal prepared tooth), and cross-sectional (AR-assisted visualization with cross-sectional views and angular displays). ResultsA user study (N = 24) revealed that the cross-sectional approach was more effective for angle adjustment and reduced the occurrence of over-reduction. Additional questionnaires revealed that the AR-assisted approaches were perceived as less difficult, with the cross-sectional approach excelling in terms of performance. ConclusionsVisualization and navigation using cross-sectional approaches have the potential to support safer tooth preparation with less overreduction than traditional and overlay approaches do. The angular displays provided by the cross-sectional approach are considered helpful for tooth preparation. Clinical significanceThe AR navigation system can assist dentists during tooth preparation and has the potential to enhance the accuracy and safety of prosthodontic treatment.