Robot Navigation System Research Articles

Comparison of robot versus fluoroscopy-assisted pedicle screw instrumentation in adolescent idiopathic scoliosis surgery: a Meta-analysis

AimTo investigate the safety and accuracy of robot-assisted pedicle screw placement in adolescent idiopathic scoliosis (AIS) surgery.MethodsPubMed, Medline, Embase, Cochrane Library, Web of Science, CNKI, and EMCC databases were searched for studies utilizing the clinical data of adolescent idiopathic scoliosis patients (robot-assisted and fluoroscopy-assisted group) who underwent posterior pedicle screw fixation to collect preoperative, postoperative and follow-up indexes and imaging parameters, including screw implantation accuracy, the number of intraoperative fluoroscopy times, amount of bleeding, operation time, postoperative VAS score and postoperative Cobb angle.ResultsSix studies were included in this meta-analysis, including 154 patients in the intervention group and 171 patients in the control group. Our results showed that screw implantation accuracy (WMD 1.07, 95% CI (1.01,1.14), P = 0.03) was higher than that in the control group. The number of intraoperative fluoroscopy times (WMD -6.11, 95% CI (-9.60, -2.62), P = 0.0006) and operation time (WMD 31.52, 95% CI (5.70,57.35), P = 0.02) in the robot group were less, and the differences were statistically significant. Intraoperative blood (WMD -59.05, 95% CI (-212.81,94.70), P = 0.45), postoperative VAS score (WMD -0.07, 95% CI (-0.24,0.11), P = 0.46), preoperative Cobb angle (WMD 0.79, 95% CI (-1.12,2.69), P = 0.42) (Fig. 7), postoperative Cobb angle (WMD -0.25, 95% CI (-1.12,0.62), P = 0.57) (Fig. 8) had no statistical significance in the robot group compared with control group.ConclusionThe robot navigation system can improve screw implantation accuracy and reduce the operation time and radiation exposure during the operation.

Comparing the accuracy and treatment time of a robotic and dynamic navigation system in osteotomy and root-end resection: An invitro study.

To compare the accuracy and treatment time of a robotic system (RS) and a dynamic navigation system (DNS) in osteotomy and root-end resection in an invitro study. In this study, four identical mandibular models were created using three-dimensional (3D) printing, each model including 18 teeth. In the surgical procedures, teeth #35, #33, #32, #42, #43 and #45, along with the mesiobuccal roots of teeth #36 and #46, were specifically selected for operation on each model. Cone-beam computed tomography (CBCT) and intraoral scans were performed on all models. DentalNavi software was used to plan a drilling path and depth as well as design surgical accessories. In the RS, osteotomy and root-end resection were performed with robotic assistance, whereas in the DNS, these procedures were performed using dynamic navigation. Post-operative CBCT scans were obtained. Global platform deviation, global apex deviation, angular deflection, and time were compared to evaluate the accuracy and treatment time of the surgeries. The treatment time was defined as the registration time and drilling time. Statistical analyses were performed using the Shapiro-Wilk and independent sample t-test. The global platform deviation, global apex deviation and angular deflection in the RS group were significantly smaller than those in the DNS group (p <.05). The registration time in the RS group was significantly longer than that in the DNS group (p <.001), whereas the drilling time was significantly shorter (p <.001). The overall surgical time was significantly longer in the RS group than in the DNS group (p <.001). Subgroup accuracy analysis revealed that in both the anterior and posterior tooth regions, the RS group exhibited significantly smaller apical and angular deviations than the DNS group (p <.001). Additionally, in both the anterior and posterior tooth subgroups, the total time for the DNS group was significantly shorter than that for the RS group in the anterior tooth area (p <.01). RS showed higher accuracy and shorter drilling time in osteotomy and root-end resection compared to DNS. The RS holds promise as a reliable technological advancement in endodontic microsurgery. However, future endeavours should prioritize the reduction in registration time.

Comparison between robot-assisted and navigation-guided minimally invasive transforaminal lumbar interbody fusion: a multicenter study.

Both robot and computer navigation have significantly improved the accuracy and safety of percutaneous pedicle screw placement compared with a freehand fluoroscopy-guided technique. However, how the two new technologies compare with each other is unknown. The aim of this study was to investigate the accuracy and safety of robot-assisted and navigation-guided percutaneous pedicle screw placement in minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF). A multicenter, retrospective study was conducted with patients who underwent 1- to 3-level MIS-TLIF from 2019 to 2022. The surgical indication was symptomatic spinal stenosis and spondylolisthesis that failed conservative management. Screw accuracy and safety were compared between robot and computer navigation systems by obtaining postoperative CT images in all patients. The screw accuracy was determined by the Gertzbein and Robbins classification. A total of 100 patients were divided into robot-assisted (RA; n = 42) and O-arm navigation (ON; n = 58) groups, with 514 percutaneous pedicle screws placed. Clinically satisfactory accuracy was achieved in 100% of the RA group and 92.1% of the ON group (p < 0.001). There were no medial breaches or revision surgeries for screw malposition in either group. The RA group showed similar overall operation time to the ON group (263.54 ± 114.33 vs 243.4 ± 68.96 minutes, p = 0.2821). Subgroup analyses showed that there was no difference in 1-level MIS-TLIF, but the RA group had significantly more operative time for 2-level MIS-TLIF than the ON group (324.67 ± 101.25 vs 266.4 ± 66.38 minutes, p = 0.0264). Screw accuracy was significantly better in the RA group, with slightly more operation time, compared with the navigation group. Neither group required revision surgery or reoperation for screw malposition.

A Comprehensive Review of Mobile Robot Navigation Using Deep Reinforcement Learning Algorithms in Crowded Environments

Navigation is a crucial challenge for mobile robots. Currently, deep reinforcement learning has attracted considerable attention and has witnessed substantial development owing to its robust performance and learning capabilities in real-world scenarios. Scientists leverage the advantages of deep neural networks, such as long short-term memory, recurrent neural networks, and convolutional neural networks, to integrate them into mobile robot navigation based on deep reinforcement learning. This integration aims to enhance the robot's motion control performance in both static and dynamic environments. This paper illustrates a comprehensive survey of deep reinforcement learning methods applied to mobile robot navigation systems in crowded environments, exploring various navigation frameworks based on deep reinforcement learning and their benefits over traditional simultaneous localization and mapping-based frameworks. Subsequently, we comprehensively compare and analyze the relationships and differences among three types of navigation: autonomous-based navigation, navigation based on simultaneous localization and mapping, and planning-based navigation. Moreover, the crowded environment includes static, dynamic, and a combination of obstacles in different typical application scenarios. Finally, we offer insights into the evolution of navigation based on deep reinforcement learning, addressing the problems and providing potential solutions associated with this emerging field.

HE-Nav: A High-Performance and Efficient Navigation System for Aerial-Ground Robots in Cluttered Environments

HE-Nav: A High-Performance and Efficient Navigation System for Aerial-Ground Robots in Cluttered Environments

Accuracy of Zygomatic Implant Placement Using Task-Autonomous Robotic System or Dynamic Navigation: An InVitro Study.

To evaluate and compare the accuracy of task-autonomous robot-assisted implant surgery (RAIS) and dynamic computer-assisted implant surgery (dCAIS) for zygomatic implant placement. Ten atrophic edentulous maxilla models requiring zygomatic implant (ZI) placement were randomly divided into the RAIS and dCAIS groups. Osteotomies and implant placement were performed under the guidance of a task-autonomous robotic system or dynamic navigation system. A total of 20 ZIs were analyzed. The angular, coronal, lateral coronal, coronal depth, apical, lateral apical, and apical depth deviations were measured and analyzed between the two groups. The primary outcome parameters were the angular deviations between the planned and the placed ZIs. Data was subjected to descriptive and comparative statistical analysis. The significance of inter-group differences for continuous variables was assessed with Student's two-sample t-tests, Welch two-sample t-tests, and Mann-Whitney U tests according to the distribution normality and variance homogeneity. ZI placement deviations were compared between the RAIS and dCAIS groups, showing a mean angular deviation of 0.92 ± 0.40° versus 2.03 ± 0.53° (p < 0.001), a mean (±SD) coronal deviation of 0.48 ± 0.25 mm versus 1.29 ± 0.46 mm (p < 0.001), and a mean apical deviation of 0.88 ± 0.28 mm versus 1.96 ± 0.46 mm (p < 0.001). For computer-guided ZI placement, task-autonomous RAIS was superior to dCAIS in terms of accuracy.

A clinical study on robot navigationassisted intramedullary nail treatment for humeral shaft fractures

BackgroundThe purpose of this study was to evaluate the advantages of robot navigation system-assisted intramedullary nail treatment for humeral shaft fractures and compare it’s efficacy with that of traditional surgical intramedullary nail treatment.Materials and methodsThis was a retrospective analysis of patients with humeral shaft fractures who received intramedullary nail treatment at our centre from March 2020 to September 2022. The analysis was divided into a robot group and a traditional surgical group on the basis of whether the surgery involved a robot navigation system. We compared the baseline data (age, sex, cause of injury, fracture AO classification, and time of injury-induced surgery), intraoperative conditions (surgery time, length of main nail insertion incision, postoperative fluoroscopy frequency, intraoperative bleeding), fracture healing time, and shoulder joint function at 1 year postsurgery (ASES score and Constant–Murley score) between the two groups of patients.ResultsThere was no statistically significant difference in the baseline data or average fracture healing time between the two groups of patients. However, the robotic group had significantly shorter surgical times, longer main nail incisions, fewer intraoperative fluoroscopies, and less intraoperative blood loss than did the traditional surgery group (P < 0.001).ConclusionRobot navigation system-assisted intramedullary nail fixation for humeral shaft fractures is a reasonable and effective surgical plan. It can help surgeons determine the insertion point and proximal opening direction faster and more easily, shorten the surgical time, reduce bleeding, avoid more intraoperative fluoroscopy, and enable patients to achieve better shoulder functional outcomes.

Robotic navigation with deep reinforcement learning in transthoracic echocardiography

Abstract Purpose The search for heart components in robotic transthoracic echocardiography is a time-consuming process. This paper proposes an optimized robotic navigation system for heart components using deep reinforcement learning to achieve an efficient and effective search technique for heart components. Method The proposed method introduces (i) an optimized search behavior generation algorithm that avoids multiple local solutions and searches for the optimal solution and (ii) an optimized path generation algorithm that minimizes the search path, thereby realizing short search times. Results The mitral valve search with the proposed method reaches the optimal solution with a probability of 74.4%, the mitral valve confidence loss rate when the local solution stops is 16.3% on average, and the inspection time with the generated path is 48.6 s on average, which is 56.6% of the time cost of the conventional method. Conclusion The results indicate that the proposed method improves the search efficiency, and the optimal location can be searched in many cases with the proposed method, and the loss rate of the confidence in the mitral valve was low even when a local solution rather than the optimal solution was reached. It is suggested that the proposed method enables accurate and quick robotic navigation to find heart components.

Comparison of robotic system and dynamic navigation for zygomatic implant placement: An in vitro study

ObjectivesTo compare the accuracy of robotic and dynamic navigation systems in assisting zygomatic implant (ZI) using an in vitro model experiment. MethodsPreoperative cone-beam computed tomography (CBCT) images of patients who underwent ZI treatment between 2011 and 2023 were collected from local databases. Corresponding three-dimensional resin models were printed and assigned to two groups: the robotic and dynamic navigation system groups. Following preoperative plans, ZIs were placed in the models with the assistance of either a robotic or dynamic navigation system. Deviations in the in vitro navigation surgery were measured and compared between the groups. ResultsA total of 110 ZIs were placed in 56 models, with 55 ZIs in each group. No significant differences were observed in entry and angle deviations between the groups (p>0.05). However, the exit deviation in the robotic system group (2.39±1.24 mm) was larger than that in the dynamic navigation group (1.83±1.25 mm) (p<0.05). On the exit side, the Z-axis deviation in the robotic group (left: -0.28±1.43 mm, right: -0.21±1.30 mm) was smaller than that in the dynamic navigation group (left: 0.76±1.11 mm, right: 0.85±1.52 mm) (p<0.05), while no significant differences were found in X- and Y-axis deviations (p>0.05). ConclusionsCompared with the dynamic navigation system, the robotic system can effectively prevent ZI overextension. However, its accuracy on the exit side is slightly lower than that of the dynamic navigation system. Clinical SignificanceThis preliminary in vitro study showed that the accuracy of the robotic system was slightly inferior to that of the dynamic navigation system in terms of exit deviation when used in ZI placement. Further clinical studies are required to confirm these findings.

An experimental system for detection and localization of hemorrhage using ultra-wideband microwaves with deep learning

Stroke is a leading cause of mortality and disability. Emergent diagnosis and intervention are critical, and predicated upon initial brain imaging; however, existing clinical imaging modalities are generally costly, immobile, and demand highly specialized operation and interpretation. Low-energy microwaves have been explored as a low-cost, small form factor, fast, and safe probe for tissue dielectric properties measurements, with both imaging and diagnostic potential. Nevertheless, challenges inherent to microwave reconstruction have impeded progress, hence conduction of microwave imaging remains an elusive scientific aim. Herein, we introduce a dedicated experimental framework comprising a robotic navigation system to translate blood-mimicking phantoms within a human head model. An 8-element ultra-wideband array of modified antipodal Vivaldi antennas was developed and driven by a two-port vector network analyzer spanning 0.6–9.0 GHz at an operating power of 1 mW. Complex scattering parameters were measured, and dielectric signatures of hemorrhage were learned using a dedicated deep neural network for prediction of hemorrhage classes and localization. An overall sensitivity and specificity for detection >0.99 was observed, with Rayleigh mean localization error of 1.65 mm. The study establishes the feasibility of a robust experimental model and deep learning solution for ultra-wideband microwave stroke detection.

Agricultural path detection systems using Canny-edge detection and Hough transform

Navigation is one of the crucial aspects of automation technology within the field of agriculture, such as robotics systems or autonomous agricultural vehicles. Despite many navigation systems having been developed for agricultural land, due to their high development and component costs, these systems are difficult to access for farmers or organizations with limited capital. In this study, the Canny-edge detection and Hough transform methods are implemented in a path detection system on agricultural land to find an alternative, cost-effective navigation system for autonomous farming robots or vehicles. The system is tested on ground-level view images, which are captured from a low perspective and under three different lighting conditions. The testing and experimentation process involves adjusting the parameters of the Canny-edge detection and Hough transform methods for different lighting conditions. Subsequently, an evaluation is conducted using Intersection over Union to obtain the best accuracy results, followed by fine-tuning of the canny-edge detection and Hough transform method parameters. The identified parameters, specifically a 15×15 Gaussian kernel, low threshold of 50, high threshold of 150, Hough threshold, minimum line length of 150, and maximum line gap, have been discerned as optimal for the canny-edge and Hough transform algorithms under medium lighting conditions (G=1.0). The observed efficacy of these parameter configurations suggests the method’s viability for implementation in path detection systems for agricultural vehicles or robots. This underscores its potential to deliver reliable performance and navigate seamlessly across diverse lighting scenarios within the agricultural context.

The Impact of Robotic Assistance-Based Navigation Systems on the Adequacy of EBUS-Guided Cytology Specimens - Experience From a Large University Hospital

The Impact of Robotic Assistance-Based Navigation Systems on the Adequacy of EBUS-Guided Cytology Specimens - Experience From a Large University Hospital

Teleoperated Magnetic Endoscopy: A Case Study and Perspective

Teleoperated robotic surgery is a rapidly growing field that promises to overcome geographical barriers and share expertise over long distances for a variety of minimally invasive procedures. A particularly promising technology for teleoperation is robotic magnetic navigation. In contrast to conventional surgical robots, a robotic magnetic navigation system generates external magnetic fields to safely and dexterously steer soft magnetic devices within the human body, enabling a versatile, economical, and accessible telesurgery platform for a variety of procedures. This perspective highlights the recent research efforts in robotic magnetic platforms for telesurgery and their translation to clinical settings in the context of endoscopic procedures. This discussion is supported by a case study performed at the Multi‐Scale Medical Robotics Center in Hong Kong, where an in vivo gastroscopy in a porcine model is performed in tandem with two operators, alternating between a clinician controlling the procedure from the operating room in Hong Kong and a remote expert controlling the procedure from an operator console in Zurich. The achievements and challenges of this study highlight the capabilities and future potential of robotic magnetic navigation for telesurgery.

Optimizing Orchard Planting Efficiency with a GIS-Integrated Autonomous Soil-Drilling Robot

A typical orchard’s mechanical operation consists of three or four stages: lining and digging for plantation, moving the seedling from nurseries to the farm, moving the seedling to the planting hole, and planting the seedling in the hole. However, the digging of the planting hole is the most time-consuming operation. In fruit orchards, the use of robots is increasingly becoming more prevalent to increase operational efficiency. They offer practical and effective services to both industry and people, whether they are assigned to plant trees, reduce the use of chemical fertilizers, or carry heavy loads to relieve staff. Robots can operate for extended periods of time and can be highly adept at repetitive tasks like planting many trees. The present study aims to identify the locations for planting trees in orchards using geographic information systems (GISs), to develop an autonomous drilling machine and use the developed robot to open planting holes. There is no comparable study on autonomous hole planting in the literature in this regard. The agricultural mobile robot is a four=wheeled nonholonomic robot with differential steering and forwarding capability to stable target positions. The designed mobile robot can be used in fully autonomous, partially autonomous, or fully manual modes. The drilling system, which is a y-axis shifter driven by a DC motor with a reducer includes an auger with a 2.1 HP gasoline engine. SOLIDWORKS 2020 software was used for designing and drawing the mobile robot and drilling system. The Microsoft Visual Basic.NET programming language was used to create the robot navigation system and drilling mechanism software. The cross-track error (XTE), which determines the distances between the actual and desired holes positions, was utilized to analyze the steering accuracy of the mobile robot to the drilling spots. Consequently, the average of the arithmetic means was determined to be 4.35 cm, and the standard deviation was 1.73 cm. This figure indicates that the suggested system is effective for drilling plant holes in orchards.

A review of research about automatic navigation system of mobile robots based on ROS

A review of research about automatic navigation system of mobile robots based on ROS

Ontology for BIM-Based Robotic Navigation and Inspection Tasks

The availability of inspection robots in the construction and operation phases of buildings has led to expanding the scope of applications and increasing technological challenges. Furthermore, the building information modeling (BIM)-based approach for robotic inspection is expected to improve the inspection process as the BIM models contain accurate geometry and relevant information at different phases of the lifecycle of a building. Several studies have used BIM for navigation purposes. Also, some studies focused on developing a knowledge-based ontology to perform activities in a robotic environment (e.g., CRAM). However, the research in this area is still limited and fragmented, and there is a need to develop an integrated ontology to be used as a first step towards logic-based inspection. This paper aims to develop an ontology for BIM-based robotic navigation and inspection tasks (OBRNIT). This ontology can help system engineers involved in developing robotic inspection systems by identifying the different concepts and relationships between robotic inspection and navigation tasks based on BIM information. The developed ontology covers four main types of concepts: (1) robot concepts, (2) building concepts, (3) navigation task concepts, and (4) inspection task concepts. The ontology is developed using Protégé. The following steps are taken to reach the objectives: (1) the available literature is reviewed to identify the concepts, (2) the steps for developing OBRNIT are identified, (3) the basic components of the ontology are developed, and (4) the evaluation process is performed for the developed ontology. The semantic representation of OBRNIT was evaluated through a case study and a survey. The evaluation confirms that OBRNIT covers the domain’s concepts and relationships, and can be applied to develop robotic inspection systems. In a case study conducted in a building at Concordia University, OBRNIT was used to support an inspection robot in navigating to identify a ceiling leakage. Survey results from 33 experts indicate that 28.13% strongly agreed and 65.63% agreed on the usage of OBRNIT for the development of robotic navigation and inspection systems. This highlights its potential in enhancing inspection reliability and repeatability, addressing the complexity of interactions within the inspection environment, and supporting the development of more autonomous and efficient robotic inspection systems.

Design a mobile robot navigation system based on FPGA

Design a mobile robot navigation system based on FPGA

BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition.

Visual Place Recognition (VPR) aims to determine whether a robot or visual navigation system locates in a previously visited place using visual information. It is an essential technology and challenging problem in computer vision and robotic communities. Recently, numerous works have demonstrated that the performance of Convolutional Neural Network (CNN)-based VPR is superior to that of traditional methods. However, with a huge number of parameters, large memory storage is necessary for these CNN models. It is a great challenge for mobile robot platforms equipped with limited resources. Fortunately, Binary Neural Networks (BNNs) can reduce memory consumption by converting weights and activation values from 32-bit into 1-bit. But current BNNs always suffer from gradients vanishing and a marked drop in accuracy. Therefore, this work proposed a BinVPR model to handle this issue. The solution is twofold. Firstly, a feature restoration strategy was explored to add features into the latter convolutional layers to further solve the gradient-vanishing problem during the training process. Moreover, we identified two principles to address gradient vanishing: restoring basic features and restoring basic features from higher to lower layers. Secondly, considering the marked drop in accuracy results from gradient mismatch during backpropagation, this work optimized the combination of binarized activation and binarized weight functions in the Larq framework, and the best combination was obtained. The performance of BinVPR was validated on public datasets. The experimental results show that it outperforms state-of-the-art BNN-based approaches and full-precision networks of AlexNet and ResNet in terms of both recognition accuracy and model size. It is worth mentioning that BinVPR achieves the same accuracy with only 1% and 4.6% model sizes of AlexNet and ResNet.

Adaptive autonomous navigation system for coal mine inspection robots: overcoming intersection challenges

PurposeIn response to the navigation challenges faced by coal mine tunnel inspection robots in semistructured underground intersection environments, many current studies rely on structured map-based planning algorithms and trajectory tracking techniques. However, this approach is highly dependent on the accuracy of the global map, which can lead to deviations from the predetermined route or collisions with obstacles. To improve the environmental adaptability and navigation precision of the robot, this paper aims to propose an adaptive navigation system based on a two-dimensional (2D) LiDAR.Design/methodology/approachLeveraging the geometric features of coal mine tunnel environments, the clustering and fitting algorithms are used to construct a geometric model within the navigation system. This not only reduces the complexity of the navigation system but also optimizes local positioning. By constructing a local potential field, there is no need for path-fitting planning, thus enhancing the robot’s adaptability in intersection environments. The feasibility of the algorithm principles is validated through MATLAB and robot operating system simulations in this paper.FindingsThe experiments demonstrate that this method enables autonomous driving and optimized positioning capabilities in harsh environments, with high real-time performance and environmental adaptability, achieving a positioning error rate of less than 3%.Originality/valueThis paper presents an adaptive navigation system for a coal mine tunnel inspection robot using a 2D LiDAR sensor. The system improves robot attitude estimation and motion control accuracy to ensure safe and reliable navigation, especially at tunnel intersections.

Robot navigation on inclined terrain using social force model

&lt;p&gt;&lt;span lang="EN-US"&gt;This research introduces an innovative approach to address the limitations of the commonly used social force model-based robot navigation method on flat terrain when applied to sloped terrain. The incline of the terrain becomes a crucial factor in calculating the robot’s steering output when navigating from the initial position to the target position while avoiding obstacles. Therefore, we propose a social forced model-based robot navigation system that can adapt to inclined terrain using inertial measurement unit sensor assistance. The system can detect the surface incline in real time and dynamically adjust friction and gravitational forces, ensuring the robot’s speed and heading direction are maintained. Simulation results conducted using CoppeliaSim show a significant improvement in speed adjustment efficiency. With this new navigation system, the robot can reach its destination in 59.935089 seconds, compared to the conventional social forced model which takes 63.506442 seconds, the robot is also able to reduce slip to reduce wasted movement. This method shows the potential of implementing a faster and more efficient navigation system in the context of inclined terrain.&lt;/span&gt;&lt;/p&gt;