Search

This article presents the platform for autonomous vehicle architecture, navigation optimization and mobility services. The basic approach is to develop an intelligent agent to create a safety journey and redefine the world of transportation. The goal is to eliminate human driving errors and save human life from accidents. AI robots are a concept of future transportation with full automation and self-learning. Velodyne laser sensors are used for obstacle detection and autonomous navigation of ground vehicles and to create 3D images of the surround so that navigation and controls are optimized. In this article, existing system accessibility will be optimized by multiple features. The agent accessibility is improved, and users can access the vehicles through different ways like mobile apps, speech recognition and gestures. This article concentrates on the mobility services of autonomous vehicles.

Scene understanding plays an important role in various fields of applications like autonomous driving, robotic navigation, etc. Scene could be considered to be an association of a large number of objects, their actions, and the events they relate in a relevant and valid combination. Scene understanding aims at providing human like ability for machines and completely analyses the visual scenes. Understanding the context of a complex scene and providing an accurate visual information from the basic level of objects to a relation between them form the major objective. Deep learning neural networks which can learn features from a massive data have excelled over conventional machine learning algorithms.

RONNA G4 (RONNA) is a robotic neuronavigation system based on articulated robotic arms and is intended for minimal invasive stereotactic procedures such as biopsies, stereoelectroencephalography, epilepsy surgeries, deep brain stimulation, and tumor resections. RONNA can be configured as a single- or dual-arm system: the single-arm system is intended for stereotactic neuronavigation and serves as a navigation assistant to the surgeon, while the dual-arm configuration performs autonomous invasive operation tasks such as bone drilling, probe or needle insertion, etc. RONNA is characterized by a fully automated patient registration procedure, robot position planning, accurate instrument guidance, and autonomous bone drilling. A novel localization method was developed combining machine vision and mathematical estimation, as well as a novel point-pairing correspondence algorithm and a multiobjective cost function for the optimization of robot placement. RONNA provides surgical tool positioning within the patient intracranial space, robotic assistance in drilling operations, and others which are distinguished by extraordinary accuracy in comparison to existing robotic and other neuronavigation systems. The clinical application of RONNA in stereotactic neurosurgical procedures shortens the operation time, lowers procedure invasiveness, enables faster patient recovery, and better utilization of hospital operational resources. Starting from 2016, RONNA has been undergoing clinical trials at the University Hospital Dubrava.

Introduction: Potential complications associated with screw malposition may result in neurological deficits or vascular injuries. Spine surgery has significantly developed under the assistance of technological progress. The advantages of applying robotic technology in spine surgery include the possibility of improving screw accuracy, reducing complications, decreasing fluoroscopy use.Areas covered: We critically evaluated the current literature on the radiographic and clinical outcomes of robotic-assisted spine surgery, including accuracy, radiation exposure, operative time, and complication rates.Expert opinion: Robotic-assisted spine surgery shows promising results and has the potentials for further investigations. The robot-assisted spine surgery is appeared to be more accurate in pedicle screw placement than the free-hand technique. In general, the robot-assisted technique is associated with shorter radiation exposure time but longer operative time than free-hand technique. For higher accuracy of robotic-assisted spine surgery, technical advancement and high-quality researches are needed. Artificial intelligent technology, decompression function, and higher accuracy are the directions for the development of robotic-assisted spine surgery.

Background: Robotic-guided navigation systems for pedicle screw placement has gained recent interest to ensure accuracy and safety and diminish radiation exposure. There have been no published studies using a new combined robotics and navigation system (Globus ExcelsiusGPS system). The purpose of this study was to demonstrate safety with this system. Methods: This is a case series of consecutive patients at a single institution from February 1, 2018, to August 31, 2018. All patients who had planned placement of thoracic and lumbar pedicle screws using the combined robotics-navigation system were included. Chart review was performed for operative details. A subgroup analysis was performed on patients with postoperative computed tomography (CT) scans to assess screw placement accuracy using the Gertzbein and Robbins system. Acceptable pedicle screw position was defined as grade A or B. Results: One hundred six patients were included, with 636 pedicle screws, 6 iliac screws, and 1 S2AI screw. Five cases were aborted for technical issues. In the remaining 101 patients, 88 patients had screws placed using preoperative CT planning and 13 patients using intraoperative fluoroscopy planning. All screws except for 5 pedicle screws in 2 patients were placed successfully using the robot (99%). These 5 pedicle screws were placed by converting to a fluoro-guided technique without robotic assistance. Eighty-six patients had screws placed using a percutaneous technique, and 15 patients had screws placed using an open technique. Ninety-eight patients underwent interbody placement: 28 anterior lumbar interbody fusions (ALIFs), 12 lateral lumbar interbody fusions (LLIFs), and 58 transforaminal lumbar interbody fusions (TLIFs). All ALIFs and LLIFs were performed prior to placement of the screws. Four LIF patients had screws placed in the lateral position. No patients had screw-related complications intraoperatively or postoperatively, and no patients returned to the operating room for screw revision. Thirteen patients underwent postoperative CT for various reasons. Of the 66 pedicle screws that were examined with postoperative CT, all screws (100%) had acceptable position. Conclusion: This study demonstrates that the combined robotics and navigation system is a novel technology that can be utilized to place pedicle screws and pelvic screws safely and has the potential to reduce screw-related complications. Level of Evidence: 4 (case series).

Avoiding obstacles is one of the main tasks in robotic navigation. In this paper, robot navigation using monocular vision is presented. Therefore, an accuracy in the segmentation of obstacles is necessary to avoid collisions by estimating the Time-to-Contact. Our proposal in this research process is based on using YOLO so that through a training process, the robot identifies which regions of the image are potentially obstacles. The experimentation was performed in a real environment, with low daylight and without controlling lighting parameters. The first results of this approach are satisfactory although this project will continue with the learning of other obstacles.

This paper presents, through simulation and experiment, initial results of using a cognitive architecture for autonomous robotic navigation, including obstacle avoidance and goal-finding. It demonstrates that, by using a perception-action cycle that incorporates memory, it is possible to achieve effective navigation strategies using a simple set of biologically-inspired control rules.

Robotic navigation concerns the task in which a robot should be able to find a safe and feasible path and traverse between two points in a complex environment. We approach the problem of robotic navigation using reinforcement learning and use deep $Q$-networks to train agents to solve the task of robotic navigation. We compare the Entropy-Based Exploration (EBE) with the widely used $\epsilon$-greedy exploration strategy by training agents using both of them in simulation. The trained agents are then tested on different versions of the environment to test the generalization ability of the learned policies. We also implement the learned policies on a real robot in complex real environment without any fine tuning and compare the effectiveness of the above-mentioned exploration strategies in the real world setting. Video showing experiments on TurtleBot3 platform is available at \url{https://youtu.be/NHT-EiN_4n8}., Comment: 5 pages

Robot-assisted spine surgery has recently emerged as a viable tool to enable less invasive and higher precision surgery. The first-ever spine robot, the SpineAssist (Mazor Robotics Ltd., Caesarea, Israel), gained FDA approval in 2004. With its ability to provide real-time intraoperative navigation and rigid stereotaxy, robotic-assisted surgery has the potential to increase accuracy while decreasing radiation exposure, complication rates, operative time, and recovery time. Currently, robotic assistance is mainly restricted to spinal fusion and instrumentation procedures, but recent studies have demonstrated its use in increasingly complex procedures such as spinal tumor resections and ablations, vertebroplasties, and deformity correction. However, robots do require high initial costs and training, and thus, require justification for their incorporation into common practice. In this review, we discuss the history of spinal robots along as well as currently available systems. We then examine the literature to evaluate accuracy, operative time, complications, radiation exposure, and costs – comparing robotic-assisted to traditional fluoroscopy-assisted freehand approaches. Finally, we consider future applications for robots in spine surgery.

Robots have been widely used to reach difficult environments or terrain such as disaster areas, wilderness and ruins of buildings. However, to reach these areas, there are many constraints on the limitations of robotic navigation because of the dynamic terrain. Therefore, a behavioral based control algorithm is needed that can make robots adapt flexibly to their environment.On the scheme of this behavior based control the robot moves based on its tasks. Each task is defined as robotic behavior. Each behavior take input from the sensor and send output to the effector. At each behavior there is a sensor as input for robot that work according to the stages in navigation to overcome uncertain obstacles. The results of the study show that robot can explore, avoid obstacles and reach the final destination.

Dense depth completion is essential for autonomous driving and robotic navigation. Existing methods focused on attaining higher accuracy of the estimated depth, which comes at the price of increasing complexity and cannot be well applied in a real-time system. In this paper, a coarse-to-fine and lightweight network (S&CNet) is proposed for dense depth completion to reduce the computational complexity with negligible sacrifice on accuracy. A dual-stream attention module (S&C enhancer) is proposed according to a new finding of deep neural network-based depth completion, which can capture both the spatial-wise and channel-wise global-range information of extracted features efficiently. Then it is plugged between the encoder and decoder of the coarse estimation network so as to improve the performance. The experiments on KITTI dataset demonstrate that the proposed approach achieves competitive result with respect to state-of-the-art works but via an almost four times faster speed. The S&C enhancer can also be easily plugged into other existing works to boost their performances significantly with negligible additional computations.

Approximately 40% of all US energy usage and carbon emissions are attributed to buildings. Energy audits of buildings are an effective way to identify significant energy savings, but the extensive training required by auditors and cost of the labour intensive audits result in only a small fraction of buildings receiving an audit. Automation of the audit process using robots can offer more detailed information for better recommendations, greater consistency in analysis and recommendations, and greatly reduce the cost of audits. This paper introduces such a system and proposes navigational strategies that would be used by ground and aerial robots as they conduct automated energy audits. The strategies are divided into the interior and exterior environments. Simulations for both the interior and exterior navigational algorithms are presented, showing success in completely exploring previously unknown areas, identifying and maneuvering to objects of specific interest to energy audits, and circumnaviga...

Innovative applications in rapidly evolving domains such as robotic navigation and autonomous (driverless) vehicles rely on binocular computer vision systems that meet stringent response time and accuracy requirements. A key problem in these vision systems is stereo matching, which involves matching pixels from two input images in order to construct the output, a 3D map. Building upon the existing local stereo matching algorithms, this paper proposes a novel stereo matching algorithm that is based on a weighted guided filtering foundation. The proposed algorithm consists of three main steps; each step is designed with the goal of improving accuracy. First, the matching costs are computed using a unique combination of complementary methods (absolute difference, Census, and gradient algorithms) to reduce errors. Second, the costs are aggregated using an adaptive weighted guided image filtering method. Here, the regularization parameters are adjusted adaptively using the Canny method, further reducing errors. Third, a disparity map is generated using the winner-take-all strategy; this map is subsequently refined using a densification method to reduce errors. Our experimental results indicate that the proposed algorithm provides a higher level of accuracy in comparison to a collection of the existing state-of-the-art local algorithms.

With the increasing availability of RGB-D cameras, using RGB-D data for geometric and semantic modeling has received significant interest in recent years. Geometric modeling aims to build an accurate geometric representation for 3D objects or scenes, whereas semantic modeling focuses on analyzing and understanding semantic objects in the captured scenes. They have many applications ranging from robotic navigation to VR/AR. In this chapter, we will overview recent efforts on this research topic, in particular, research using advanced machine learning techniques, exploiting the complementary characteristics of geometry and image information in RGB-D data, and incorporating prior knowledge.

BACKGROUND: Because of the expanding atrial fibrillation (AF) burden, AF catheter ablation (CA) techniques have to become more efficient. Efficient AF CA procedures are characterized by successful pulmonary vein isolation (PVI) within reasonable procedure time. Currently there are many PVI techniques available and all show substantial improvements over time. However, the magnitude of improvement in procedural efficiency has not yet been compared between different techniques. The aim of this study was to compare efficiency improvement between manually (MAN) guided, cryoballoon (CB) and remote magnetic navigation (RMN) guided PVI. METHODS: A total of 221 patients were included in this retrospective study. Procedural parameters of 115 patients treated with first-generation PVI techniques (MAN-1, CB-1, RMN-1) performed in 2010, were compared to 106 patients who were treated with the latest, second generation techniques (MAN-2, CB-2, RMN-2). Efficiency was characterized by the following parameters: total ablation time, total procedure time, first pass isolation (FPI) (i.e. successful isolation after the first pulmonary vein (PV) encirclement) and touch-up rates. RESULTS: Every technique showed significant improvement of procedure times from the first to the second generation (P

Determining a resolving partition of a graph is an interesting study in graph theory due to many applications like censor design, compound classification in chemistry, robotic navigation and internet network. Let and , the distance between an is . For an ordered partition of , the representation of with respect to is . The partition is called a resolving partition of if all representation of vertices are distinct. The partition dimension of graph is the smallest integer such that has a resolving partition with element.In this thesis, we determine the partition dimension of complete multipartite graph , which is limited by , with and . We found that , , and , .

Autonomous robotic navigation in indoor environments is fairly challenging and important to industrial environments. Traditional map-based or mapless navigation methods often fail because of the unstructured characteristics of the environments. Recently, imitation learning using DAgger algorithm has been successfully applied to many real-world robotic tasks. However, it needs human operators to give correct control commands without feedback to overcome data distribution mismatch problem, which is always prone to error and expensive. In this paper, we propose a novel solution to eliminate the need of human manual labeling after the initial data collection in the task of imitating to navigate in indoor environments. This solution introduces an imperfect policy based on multi-sensor fusion and a recording policy that only records the data giving the most knowledge to the navigation policy. The recording policy mitigates the affect of learning too much from an imperfect policy. With extensive experiments in indoor environments, we demonstrate that after several iterations of learning, the robot is able to navigate through real-world hallways in both seen and unseen situations safely. In addition, we show that our system achieves near human performance in most of the tasks and even surpasses human performance in one out of three tasks. To the best of our knowledge, this is the first work that utilizes imperfect sensor measurements to perform self-supervised imitation learning in robotic navigation tasks.

This manuscript presents positioning accuracy test of a self-development 2D C-arm image based robotic navigation system for assisting the surgeon to implant pedicle screws to the planned locations. The main difference of the system to the ROSA Spine system or Mazor X system is the use of 2D C-arm images instead of 3D C-arm (O-arm) or CT images, which is because 2D C-arm is more popular and available in most hospitals. The surgeon uses a positioning probe to plan drill paths directly on the patient’s back, which are projected and shown on the computer-displayed C-arm AP and LA images so that the surgeon can make sure the correction of implantation path. The spatial position and orientation of the implantation path are also input to the robot controller to enable the robot to move automatically the guiding device to align with the planned path. Then the surgeon can easily drill and implant pedicle screw into the pedicle by following the guiding sleeve. The positioning results of phantom experiment indicate that the average distance error of probe tip between planned and guided paths within the pedicle is 1.2 + 0.3mm and the average direction error between the two paths is 0.4 + 0.1o.

Computer navigation increases reproducibility compared to non-navigated total knee arthroplasty (TKA). Robotics navigation is a branch of computer navigation technology that might further improve accuracy of implant placement. The aim of this study is to assess the accuracy achieved in TKA with a robotic navigation system.One hundred seventy three knees. System studied: Omni navigation System (OMNI, Raynham, MA). Navigated femoral and tibial cuts were compared to postoperative computed tomography (CT). Measurements reviewed: femoral coronal alignment (FCA), femoral sagittal alignment (FSA), femoral rotational alignment (FRA), tibial coronal alignment (TCA), tibial sagittal alignment (TSA) and hip-knee-ankle (HKA) angle. Statistical analysis was made using R.The mean differences between the navigated reported and the CT positions were: FCA: 0.1 ± 1.2° more varus (P = 0.58), FSA: 1.5 ± 0.3° more flexed (P 0.001), FRA: 0.0 ± 1.7° (P = 0.93), TCA: 0.7 ± 1.1° more varus (P 0.001), TSA: -1.3 ± 1.5 more negative slope (P 0.001), HKA angle: 0.4 ± 2.4 more varus (P 0.049). The percentages of concordance inside a three degree difference were: FCA: 98% (169 knees), FSA: 100% (173 knees), FRA: 94% (162 knees), TCA: 99% (171 knees), TSA: 93% (161 knees) and HKA angle: 83% (144 knees).The current study showed that the robotic navigation system studied is highly accurate regarding final implant positioning for FCA, FRA and TCA. It has less accuracy in FSA, TSA and the HKA angle.

International audience; Recent years have seen a fast growth in the number of applications of Machine Learning algorithms from Computer Science to Robotics. Nevertheless, while most such attempts were successful in maximizing robot performance after a long learning phase, to our knowledge none of them explicitly takes into account the budget in the algorithm evaluation: e.g. budget limitation on the learning duration or on the maximum number of possible actions by the robot. In this paper, we introduce an algorithm for robot spatial localization based on image classification using a sequential budgeted learning framework. This aims to allow the learning of policies under an explicit budget. In this case our model uses a constraint on the number of actions that can be used by the robot. Our approach enables to reduce the problem to a classification task under budget constraint. We apply this algorithm to a localization problem in a simulated environment. We compare it first to simple neural networks for the classification part and second to different techniques of policy selection. The results show that the model can effectively learn an efficient active sensing policy (i.e. alternating between sensor measurement and movement to get additional information in different positions) in order to optimize its localization performance under each tested fixed budget. We also show that with this algorithm the simulated robot can transfer the learned policy as well as knowledge about which budget gives the best performance/budget ratio in a given environment to other environments with similar properties. We finally test the algorithm with real navigation data acquired in an indoor environment with the PR2 robot. Altogether, these results suggest a promising framework for enabling budgeted localization in robots and avoiding to make robots relearn everything from scratch in each new environment.

BACKGROUND CONTEXT Pedicle screw fixation is an established means of stabilizing the thoracic and lumbar spine. Computer-assisted navigation has been demonstrated to improve the accuracy of pedicle screw placement. Few studies have compared screw breach rates using navigated robotic platforms. PURPOSE The goal of this study is to determine if the use of a navigated robotic platform, Excelsius GPS™ (Globus Medical, Inc., Audubon, PA), minimizes pedicle breach in comparison to conventional techniques, and to determine why breach rates differ between these two techniques. STUDY DESIGN/SETTING Cadaveric study. METHODS Ten board-certified neuro- and orthopaedic spine surgeons inserted 80 percutaneous lumbar screws in 10 unembalmed human cadavers. Forty screws were inserted using conventional fluoroscopic guidance; 40 were inserted using a navigated robotic platform. None of the participating surgeons had prior experience with navigated robotic spine surgery. At the end of the study, each screw was assessed with CT scans, plain radiographs, and visual inspection to determine the presence or absence of pedicle breaches. RESULTS Forty percent (16/40) of screws inserted using conventional fluoroscopic guidance breached the pedicle compared to 2.5% (1/40) of screws inserted with robot assistance (p=0.00005). High-grade breaches accounted for 17.5% (7/40) of screws inserted using fluoroscopic guidance. No high-grade breaches were observed in screws inserted using robotic assistance. High-grade breaches were defined as Gertzbein-Robbins grade C, D or E. Lateral breaches accounted for 88.2% (15/17) of all breaches. A subgroup analysis was performed of the 14 fluoroscopic screws that breached laterally. Detailed analyses revealed that the starting points of screws that breached laterally were significantly more lateral than those of the contralateral accurate screws (p=0.016). Pedicle screw diameter, length, and angulation in the transverse plane did not differ significantly between accurate screws and those that breached (p>0.05). Of the total 80 screws placed, robotic navigation allowed for use of both larger diameter (6.3±0.5mm vs. 6.6±0.6mm, p CONCLUSIONS Use of a navigated robotic platform allows surgeons to identify an appropriate entry point, plan the pedicle screw trajectory based on that entry point, and execute insertion of the pedicle screw in a safe manner, which in the context of the current study resulted in a significantly lower pedicle breach rate compared to conventional techniques. FDA DEVICE/DRUG STATUS Excelsius GPS (Approved for this indication).

Long-term results after circumferential pulmonary vein isolation (CPVI) for the treatment of paroxysmal atrial fibrillation (PAF) using a robotic navigation system (RNS) have not yet been reported.To evaluate long-term results of patients with PAF after CPVI using RNS.In this study, 200 patients (n = 151 (75.5%) male; median age 62.2 (54.7-67.7) years) with PAF were evaluated. In 100 patients, RNS (RN-group) was used for CPVI and compared to 100 manually ablated control patients (MN-group). Radiofrequency was used in conjunction with 3D electroanatomic mapping. Power was limited to 30 watts (W) at the posterior left atrial (LA) wall in the first 49 RNS patients (RN-group-a). After esophageal perforation occurred in one RN-group-a patient, maximum power was reduced to 20 W for the subsequent 51 patients (RN-group-b).After a median follow-up of 2 years, single (77/100 vs 77/100, p = 0.89) and multiple (90/100 vs 93/100, p = 0.29) procedure success rates were comparable between RN-group and MN-group. Single procedure success rate was significantly lower in RN-group-a as compared to RN-group-b (65.3 vs 88.2%, p = 0.047). In RN-group-a patients, procedural times [200 (170-230) vs 152 (132-200) minutes, p0.01] and fluoroscopy times [16.6 (12.9-21.6) minutes vs 13.7 (9.5-19) minutes, p = 0.043] were significantly longer compared to RN-group-b patients.Long-term success rate after CPVI using RNS was comparable to manual ablation. Despite a lower power limit of 20 W at the posterior LA wall, single procedure success rate was higher in RN-group-b as compared to RN-group-a. Procedure time and fluoroscopy time decreased, whilst success rate increased with increasing experience in the RN-group.

Manual radio frequency (RF) ablation to restore a normal cardiac rhythm requires significant skill, manual dexterity and experience. In response to this, ablation methods and technologies have evolved rapidly in the past decade, including the development of remote navigation technologies. Today, two principal methods of remote navigation are available. One utilizes magnetic field vectors to navigate proprietary catheters, the other maneuvers standard catheters robotically. The main advantages of remote navigation include improved catheter stability, reduced fluoroscopy times and decreased total radiation exposure to both the patient and the operator. The main limitations include cost and longer procedure times. Remote magnetic navigation appears to have the best safety profile; however, its efficacy in creating lesions may be lower, which has been attributed to the soft-tip catheter used. Remote robotic navigation on the other hand, which uses regular catheter tips, is associated with a slightly higher overall complication rate, but higher efficacy. This article reviews the pros and cons of remote navigation for ablation of both atrial and ventricular substrates. Finally, it attempts to predict the direction of this field in the coming years.

Purpose: To evaluate the safety and success of target vessel cannulation in the visceral aortic segment using the Magellan robotic catheter system (RCS) during complex endovascular aortic procedures. Methods: Robotic navigation was attempted for access to 37 target vessels in 15 patients (14 men; mean age 75±10 years) during 16 fenestrated and/or branched stent-grafting procedures and 1 endovascular repair requiring the chimney technique. For each target vessel, robotic navigation was attempted for a maximum of 15 minutes; if cannulation was unsuccessful in that time, manual catheters were employed. Safety was evaluated by recording intraoperative adverse events, intraoperative complications related to robotic navigation, and postoperative complications. Technical success of robotic cannulation, wire cannulation times, and times for inserting the leader over the wire in the target vessels were recorded to assess RCS performance. Results: Successful robotic cannulation was achieved for 30 (81%) of the 37 target vessels, with a median wire cannulation time of 263 seconds (range 40–780) and a median 15 seconds (range 5–450) for inserting the leader over the wire. No intraoperative complications related to robotic navigation were observed. Seven of 27 arteries accessed via 7 fenestrations could not be cannulated within 15 minute s; all were cannulated successfully using conventional catheters (mean cannulation time 31±7 minutes). All 10 target vessels accessed via branches and chimney stents were successfully cannulated with the RCS. Conclusion: Cannulation of target vessels with the RCS during complex endovascular aortic procedures is feasible and safe. The robotic system was particularly effective for branched and chimney stents.

This paper proposes an architecture that explores a gap in the spectrum of existing strategies for robot control mode switching in adjustable autonomy. In situations where the environment is reasonably known and/or predictable, pre-planning these control changes could relieve robot operators of the additional task of deciding when and how to switch. Such a strategy provides a clear division of labour between the automation and the human operator(s) before the job even begins, allowing for individual responsibilities to be known ahead of time, limiting confusion and allowing rest breaks to be planned. Assigned Responsibility is a new form of adjustable autonomy-based teleoperation that allows the selective inclusion of automated control elements at key stages of a robot operation plan's execution. Progression through these stages is controlled by automatic goal accomplishment tracking. An implementation is evaluated through engineering tests and a usability study, demonstrating the viability of this approach and offering insight into its potential applications. ispartof: International Journal of Intelligent Robotics and Applications vol:2 issue:1 pages:81-97 ispartof: location:Singapore status: accepted

This paper aims at developing a sensor-based Co-Active adaptive neuro-fuzzy inference system (CANFIS) for solving navigation problems of the mobile robot in an uncertain environment. The infrared sensor reads the distances of right, front and left obstacle. The collision-free path is accomplished by CANFIS controller which selects the desired steering angle by construing the obstacle distance information measured by the infrared sensor. The simulation of CANFIS based algorithm provides more precise steering angle, which implements the navigation task securely and efficiently in an environment populated with static obstacles.

In vivo studies of neurophysiology using the whole cell patch-clamp technique enable exquisite access to both intracellular dynamics and cytosol of cells in the living brain but are underrepresented in deep subcortical nuclei because of fouling of the sensitive electrode tip. We have developed an autonomous method to navigate electrodes around obstacles such as blood vessels after identifying them as a source of contamination during regional pipette localization (RPL) in vivo. In mice, robotic navigation prevented fouling of the electrode tip, increasing RPL success probability 3 mm below the pial surface to 82% (

Factors Influencing AF Ablation Efficacy Introduction Preclinical work suggests factors including catheter orientation and contact consistency during individual radiofrequency ablations influence lesion size. Our aim was to investigate factors affecting catheter contact in the left atrium (LA) and their effects on ablation. Methods and Results A total of 2,298 8-second static LA mapping points were studied in 30 patients undergoing ablation for AF (16 in AF, 14 sinus rhythm [SR], 18 remote robotic navigation [RRN] procedures) using a contact force (CF) sensing catheter. CF variability (CFV: difference between 20 Hz–sampled CF waveform mean peak and trough) increased with mean CF, Spearman's ρ = 0.6, P 5 g) and locational drift (>3.5 mm), perpendicular contact, SR and RRN usage were associated with a lesser impedance drop with ablation (P < 0.005 for each), suggesting reduced efficacy. Conclusions Beyond the FTI, the quality of catheter contact influences ablation efficacy, and clinical catheter contact is affected by multiple factors, including the atrial rhythm and catheter navigation mode. Maximal efficacy is provided by parallel contact with CFV ≤5 g, catheter drift ≤3.5 mm, and manual navigation.

Contact with cardiac tissue is a determinant of lesion efficacy during atrial fibrillation (AF) ablation. The Sensei®X Robotic Catheter System (Hansen Medical, CA) has been validated for contact force sensing. The electrical coupling index (ECI) from the EnSite Contact™ system (St. Jude Medical, MN) has been validated as an indicator of tissue contact. We aimed at analyzing ECI behavior during radiofrequency (RF) pulses maintaining a stable contact through the robotic navigation contact system. In 15 patients (age, 59 ± 12) undergoing AF ablation, pulmonary vein (PV) isolation was guided by the Sensei®X System, employing the Contact™ catheter. During the procedure, we assessed ECI changes associated with adequate contact based on the IntelliSense® force-sensing technology (Hansen Medical, CA. Baseline contact (27 ± 8 g/cm2) ECI value was 99 ± 13, whereas ECI values in a noncontact site (0 g/cm2) and in a light contact site (1–10 g/cm2) were respectively 66 ± 12 and 77 ± 10 (p

This paper serves as an introduction to the concept of path planning and navigation. Contents include path planning algorithms and their many applications. Specific applications include navigation systems in autonomous/semi-autonomous systems. Often these autonomous systems rely on several layers of sensor data, however at the root is a search-algorithm-based navigation system. This paper is to serve as an introduction to these algorithms and the use cases where young/new roboticists can develop path finding/path planning applications to fit their educational robotics needs. The A*, (A-Star), search algorithm and its applications will be the primary algorithm used within this paper. This paper is a portion of an ongoing research project for a robotic vehicle navigation system.

Human beings use doors to access rooms and corridors, to know where they are, to know where they have to go, etc. Similarly, it would be quite useful for robots to be able to detect doors in order to accomplish more complex and flexible navigation tasks. Such a goal is even more desirable when domestic environments are taken into account. Moreover, if the human-robot interaction is considered, the use of this semantic information can be broadly used. In this paper we present a solid and complete door detection system which fuses data from an end-user camera and a laser rangefinder. By using both Haar-like features and the Integral Image, the computation time is significantly reduced when compared to other methods found in the literature. Extensive tests in real-world environments have been performed in order to prove the efficiency, robustness and real-time ability of our system.

Left atrial isthmus (LAI)-ablation in addition to circumferential pulmonary vein isolation (CPVI) may improve outcomes in select patients with atrial fibrillation (AF). However, bidirectional LAI-block is difficult to obtain. No systematic evaluation reporting on the feasibility and efficacy of LAI-ablation using a robotic navigation system (RNS) exists. In this pilot study, CPVI combined with LAI-ablation were performed using a RNS and 3D-mapping system in 42 patients with persistent (n = 24, 57.1 %) or longstanding persistent AF. Ablation was performed using either a 3.5 mm irrigated tip catheter (ITC) with 6 (group-A, n = 16; max. 40 W, contact force 10–40 g) or (after a steam pop occurred in one patient) with a 4 mm ITC with 12 irrigation holes (group-B, n = 26; max. 30 W, contact force 10–30 g). Epicardial ablation was performed manually whenever bidirectional LAI-block could not be obtained with a maximum of 20 endocardial RF-applications. LAI-conduction block was achieved in all patients using RNS; in six patients (14.3 %), additional epicardial ablation was required to achieve LAI-block. A steam pop occurred during LAI-ablation resulting in cardiac tamponade in one patient in group-A. After a median follow-up period of 21 months, arrhythmia recurrence was seen in in 23/42 patients (18 patients with AF and 5 patients with atrial tachycardia) and repeat procedure was performed in 12 (28.6 %) patients; recovered LAI-conduction was found in 5/12 (41.7 %) patients. The RNS-group was compared to a historical group of 20 patients with manual LAI-ablation. Using RNS, LAI-block was more often achieved (42 (100 %) vs 16 (80 %), p

International audience

Algorithms for navigation, localization and mapping are core software for almost all mobile robotic systems. There are variety of such algorithms that use different approaches and utilize different robotic equipment. To select a suitable algorithm that fulfill the constraints on equipment, computational complexity, and performance quality we need a framework that allows to perform a large number of tests and simulations in different conditions. In this paper, we evaluate approaches to the creation of such framework, describe initial release of the framework and provide some results on navigation algorithms evaluation with it.