Custom Robot Research Articles

New protocol for early robot-assisted gait training after spinal surgery.

Early rehabilitation post-spinal surgery is vital for patients' recovery. Robot-assisted gait training (RAGT) shows promise but requires further study to establish a specific protocol and gauge its effects on both patients and physical therapists. This study aimed to determine the impact of a newly developed protocol for early RAGT on patients' functional enhancement and satisfaction levels after spinal surgery, as well as on the physical therapists who implemented the therapy. First, we developed the protocol in collaboration with three physiatrists and two physical therapists with extensive experience in musculoskeletal rehabilitation. The protocol was updated three times, each after three rounds of face-to-face meetings. Afterward, we conducted a cross-sectional study involving five physical therapists and 32 post-spinal surgery patients at a tertiary hospital rehabilitation center. The intervention consisted of five sessions of RAGT. Main outcome measures included the Functional Ambulation Category (FAC), the ambulation item of the Modified Barthel Index (MBI ambulation), and satisfaction surveys for both patients and physical therapists. RAGT typically started 17.91 ± 9.76 days postoperatively and was successfully applied with no remarkable adverse effects. The FAC scores increased from 2.65 ± 1.21 to 3.78 ± 0.71 (p = 0.006), and MBI ambulation increased from 7.69 ± 2.71 to 10.66 ± 2.90 (p < 0.001) between transfer and discharge. Satisfaction with the robot, RAGT, and treatment, assessed using a 5-point Likert scale, were 3.30 ± 0.79, 3.72 ± 0.85, and 3.08 ± 0.84, respectively. Satisfaction was notably the highest for alleviating fear of falling, whereas managing pain and discomfort during position changes scored the lowest. Physical therapists rated RAGT satisfaction, impact on the working environment, and treatment stability at 3.0 ± 0.65, 2.80 ± 0.67, and 3.50 ± 0.61, respectively. Early spinal surgery rehabilitation with RAGT improved patients' functionality and gait satisfaction. While physical therapists considered RAGT safe, its impact on their work environment was limited. Integrating RAGT into post-spinal surgery rehabilitation demands ongoing protocol refinement, custom robot development, and efficacy evaluations.

Assessment of ChatGPT-4 in Family Medicine Board Examinations Using Advanced AI Learning and Analytical Methods: Observational Study.

This research explores the capabilities of ChatGPT-4 in passing the American Board of Family Medicine (ABFM) Certification Examination. Addressing a gap in existing literature, where earlier artificial intelligence (AI) models showed limitations in medical board examinations, this study evaluates the enhanced features and potential of ChatGPT-4, especially in document analysis and information synthesis. The primary goal is to assess whether ChatGPT-4, when provided with extensive preparation resources and when using sophisticated data analysis, can achieve a score equal to or above the passing threshold for the Family Medicine Board Examinations. In this study, ChatGPT-4 was embedded in a specialized subenvironment, "AI Family Medicine Board Exam Taker," designed to closely mimic the conditions of the ABFM Certification Examination. This subenvironment enabled the AI to access and analyze a range of relevant study materials, including a primary medical textbook and supplementary web-based resources. The AI was presented with a series of ABFM-type examination questions, reflecting the breadth and complexity typical of the examination. Emphasis was placed on assessing the AI's ability to interpret and respond to these questions accurately, leveraging its advanced data processing and analysis capabilities within this controlled subenvironment. In our study, ChatGPT-4's performance was quantitatively assessed on 300 practice ABFM examination questions. The AI achieved a correct response rate of 88.67% (95% CI 85.08%-92.25%) for the Custom Robot version and 87.33% (95% CI 83.57%-91.10%) for the Regular version. Statistical analysis, including the McNemar test (P=.45), indicated no significant difference in accuracy between the 2 versions. In addition, the chi-square test for error-type distribution (P=.32) revealed no significant variation in the pattern of errors across versions. These results highlight ChatGPT-4's capacity for high-level performance and consistency in responding to complex medical examination questions under controlled conditions. The study demonstrates that ChatGPT-4, particularly when equipped with specialized preparation and when operating in a tailored subenvironment, shows promising potential in handling the intricacies of medical board examinations. While its performance is comparable with the expected standards for passing the ABFM Certification Examination, further enhancements in AI technology and tailored training methods could push these capabilities to new heights. This exploration opens avenues for integrating AI tools such as ChatGPT-4 in medical education and assessment, emphasizing the importance of continuous advancement and specialized training in medical applications of AI.

A Posterior Acromial Bone Block Augmentation Is Biomechanically Effective at Restoring the Force Required To Translate the Humeral Head Posteriorly in a Cadaveric, Posterior Glenohumeral Instability Model

The purpose of this study was to assess the biomechanical utility of a posterior acromial bone block (PABB) for the treatment of posterior glenohumeral instability. 10 fresh-frozen cadaveric specimens were obtained based upon an a priori power analysis. A 2.5 cm scapular spine autograft was harvested from all shoulders. A custom robot device was used to apply a 50-N compressive force to the glenohumeral joint. The humeral head was translated 10mm posteroinferiorly at 30 degrees from the center of the glenoid at a rate of 1.0 mm/s in 6 consecutive conditions: 1) intact specimen, 2) intact with PABB, 3) posterior capsulolabral tear 4) addition of the PABB, 5) removal of the PABB and repair of the capsulolabral tear (LR), and 6) addition of the PABB with LR. The maximum force required to obtain this translation was recorded. Paired T-tests were performed to compare relevant testing conditions. 10 cadavers with mean age 54.4 years (Standard Deviation (SD) ± 13.1) and mean glenoid retroversion of 6.5 degrees (SD ± 1.0) were studied. The PABB provided greater resistance force to humeral head translation compared to the instability state (instability, 29.3 ± 15.3N versus PABB, 47.6 ± 21.0 N, P = 0.001, 95% confidence interval [CI] -27.6, -10.0). When comparing PABB to LR, the PABB produced higher resistance force than LR alone (PABB, 47.6 ± 21.0 N, LR, 34.2 ± 20.5N, P = 0.012, 95% CI -23.4, -4.1). An instability lesion treated with the PABB, with (P =0.056, 95% CI -0.30, 20.4) or without LR (P = 0.351, 95% CI -6.8, 15.7), produced resistance forces similar to the intact specimen. A posterior acromial bone block is biomechanically effective at restoring the force required to translate the humeral head posteriorly in a cadaveric, posterior glenohumeral instability model. A posterior acromial bone block is a biomechanically feasible option to consider in patients with recurrent posterior instability.

GoBot Go! Using a Custom Assistive Robot to Promote Physical Activity in Children.

Children worldwide are becoming increasingly inactive, leading to significant wellness challenges. Initial findings from our research team indicate that robots could potentially provide a more effective approach (compared to other age-appropriate toys) for encouraging physical activity in children. However, the basis of this past work relied on either interactions with groups of children (making it challenging to isolate specific factors that influenced activity levels) or a preliminary version of results of the present study (which centered on just a single more exploratory method for assessing child movement). This paper delves into more controlled interactions involving a single robot and a child participant, while also considering observations over an extended period to mitigate the influence of novelty on the study outcomes. We discuss the outcomes of a two-month-long deployment, during which [Formula: see text] participants engaged with our custom robot, GoBot, in weekly sessions. During each session, the children experienced three different conditions: a teleoperated robot mode, a semi-autonomous robot mode, and a control condition in which the robot was present but inactive. Compared to our past related work, the results expanded our findings by confirming with greater clout (based on multiple data streams, including one more robust measure compared to the past related work) that children tended to be more physically active when the robot was active, and interestingly, there were no significant differences between the teleoperated and semi-autonomous modes in terms of our study measures. These insights can inform future applications of assistive robots in child motor interventions, including the guiding of appropriate levels of autonomy for these systems. This study demonstrates that incorporating robotic systems into play environments can boost physical activity in young children, indicating potential implementation in settings crafted to enhance children's physical movement.

How To Create Our Custom Model in CoppeliaSim From 3D File

Purpose: This paper aims to provide a comprehensive guide to creating custom models in CoppeliaSim from 3D files. It equips users with the necessary knowledge and skills to design and simulate their unique robotic systems within the CoppeliaSim environment. By creating it, users can design robots with unique geometries and configurations that align with their specific requirements and research objectives. It enables users to represent real-world robots or prototypes in the virtual environment accurately. It provides a platform to test and validate robot designs before physical implementation. Users can simulate different scenarios, assess the feasibility of their concepts, and identify potential issues or improvements early in the design process, thereby saving time and resources. It equips students, researchers, and robotics enthusiasts with practical knowledge and hands-on experience designing and simulating custom robot models. It also encourages collaboration and knowledge sharing within the robotics community. Design/Methodology/Approach: Download the desired model for Simulation from the website. Import 3D model into the environment. Configures various properties of the model. This includes defining physical properties, and visual appearance, for realistic rendering. The process also determines the kinematic properties of the model. It involves creating linkages, defining joint properties, and establishing parent-child relationships between objects. Add child scripts. Save the model for future use. Findings/Result: Here, we provide the process for importing 3D files into CoppeliaSim. Users could import their necessary models without an issue, ensuring the accurate representation of 3D object geometry in the simulation environment. Users could establish linkages, define joint properties, and set parent-child relationships, allowing for accurate kinematic simulations and motion analysis. Originality/Value: It provides a comprehensive step-by-step guide on creating custom models in CoppeliaSim from 3D files. It covers all the essential aspects and ensures that users understand the entire process clearly, making it a valuable resource for beginners and experienced users. Paper Type: Experimental-based Research.

Multi-Body 3D-2D Registration for Robot-Assisted Joint Reduction: Preclinical Evaluation in the Ankle Syndesmosis.

Existing methods to improve the accuracy of tibiofibular joint reduction present workflow challenges, high radiation exposure, and a lack of accuracy and precision, leading to poor surgical outcomes. To address these limitations, we propose a method to perform robot-assisted joint reduction using intraoperative imaging to align the dislocated fibula to a target pose relative to the tibia. The approach (1) localizes the robot via 3D-2D registration of a custom plate adapter attached to its end effector, (2) localizes the tibia and fibula using multi-body 3D-2D registration, and (3) drives the robot to reduce the dislocated fibula according to the target plan. The custom robot adapter was designed to interface directly with the fibular plate while presenting radiographic features to aid registration. Registration accuracy was evaluated on a cadaveric ankle specimen, and the feasibility of robotic guidance was assessed by manipulating a dislocated fibula in a cadaver ankle. Using standard AP and mortise radiographic views registration errors were measured to be less than 1 mm and 1° for the robot adapter and the ankle bones. Experiments in a cadaveric specimen revealed up to 4 mm deviations from the intended path, which was reduced to <2 mm using corrective actions guided by intraoperative imaging and 3D-2D registration. Preclinical studies suggest that significant robot flex and tibial motion occur during fibula manipulation, motivating the use of the proposed method to dynamically correct the robot trajectory. Accurate robot registration was achieved via the use of fiducials embedded within the custom design. Future work will evaluate the approach on a custom radiolucent robot design currently under construction and verify the solution on additional cadaveric specimens.

In the Arms of a Robot: Designing Autonomous Hugging Robots with Intra-Hug Gestures

Hugs are complex affective interactions that often include gestures like squeezes. We present six new guidelines for designing interactive hugging robots, which we validate through two studies with our custom robot. To achieve autonomy, we investigated robot responses to four human intra-hug gestures: holding, rubbing, patting, and squeezing. A Total of 32 users each exchanged and rated 16 hugs with an experimenter-controlled HuggieBot 2.0. The robot’s inflated torso’s microphone and pressure sensor collected data of the subjects’ demonstrations that were used to develop a perceptual algorithm that classifies user actions with 88% accuracy. Users enjoyed robot squeezes, regardless of their performed action, they valued variety in the robot response, and they appreciated robot-initiated intra-hug gestures. From average user ratings, we created a probabilistic behavior algorithm that chooses robot responses in real time. We implemented improvements to the robot platform to create HuggieBot 3.0 and then validated its gesture perception system and behavior algorithm with 16 users. The robot’s responses and proactive gestures were greatly enjoyed. Users found the robot more natural, enjoyable, and intelligent in the last phase of the experiment than in the first. After the study, they felt more understood by the robot and thought robots were nicer to hug.

Morphological computation and decentralized learning in a swarm of sterically interacting robots.

Whereas naturally occurring swarms thrive when crowded, physical interactions in robotic swarms are either avoided or carefully controlled, thus limiting their operational density. Here, we present a mechanical design rule that allows robots to act in a collision-dominated environment. We introduce Morphobots, a robotic swarm platform developed to implement embodied computation through a morpho-functional design. By engineering a three-dimensional printed exoskeleton, we encode a reorientation response to an external body force (such as gravity) or a surface force (such as a collision). We show that the force orientation response is generic and can augment existing swarm robotic platforms (e.g., Kilobots) as well as custom robots even 10 times larger. At the individual level, the exoskeleton improves motility and stability and also allows encoding of two contrasting dynamical behaviors in response to an external force or a collision (including collision with a wall or a movable obstacle and on a dynamically tilting plane). This force orientation response adds a mechanical layer to the robot's sense-act cycle at the swarm level, leveraging steric interactions for collective phototaxis when crowded. Enabling collisions also promotes information flow, facilitating online distributed learning. Each robot runs an embedded algorithm that ultimately optimizes collective performance. We identify an effective parameter that controls the force orientation response and explore its implications in swarms that transition from dilute to crowded. Experimenting with physical swarms (of up to 64 robots) and simulated swarms (of up to 8192 agents) shows that the effect of morphological computation increases with growing swarm size.

In Vitro Simulation of Shoulder Motion Driven by Three-Dimensional Scapular and Humeral Kinematics.

In vitro simulation of three-dimensional (3D) shoulder motion using in vivo kinematics obtained from human subjects allows investigation of clinical conditions in the context of physiologically relevant biomechanics. Herein, we present a framework for laboratory simulation of subject-specific kinematics that combines individual 3D scapular and humeral control in cadavers. The objectives were to: (1) robotically simulate seven healthy subject-specific 3D scapulothoracic and glenohumeral kinematic trajectories in six cadavers, (2) characterize system performance using kinematic orientation accuracy and repeatability, and muscle force repeatability metrics, and (3) analyze effects of input kinematics and cadaver specimen variability. Using an industrial robot to orient the scapula range of motion (ROM), errors with repeatability of ±0.1 mm and <0.5 deg were achieved. Using a custom robot and a trajectory prediction algorithm to orient the humerus relative to the scapula, orientation accuracy for glenohumeral elevation, plane of elevation, and axial rotation of <3 deg mean absolute error (MAE) was achieved. Kinematic accuracy was not affected by varying input kinematics or cadaver specimens. Muscle forces over five repeated setups showed variability typically <33% relative to the overall simulations. Varying cadaver specimens and subject-specific human motions showed effects on muscle forces, illustrating that the system was capable of differentiating changes in forces due to input conditions. The anterior and middle deltoid, specifically, showed notable variations in patterns across the ROM that were affected by subject-specific motion. This machine provides a platform for future laboratory studies to investigate shoulder biomechanics and consider the impacts of variable input kinematics from populations of interest, as they can significantly impact study outputs and resultant conclusions.

An E2ED-based Approach to Custom Robot Navigation and Localization

An E2ED-based Approach to Custom Robot Navigation and Localization

ABB IRB 120-30.6 Build Procedure in RoboDK

Purpose: Research on robotics needs a robot to experiment on it. The actual industrial robot is costly. So, the only resort is to use a Robot simulator. The RoboDK is one of the best robot simulators now. It has covered most of the popular industrial robots. Its interface is straightforward. Just open the software, download the robot as we need, and start experiments. Up to that, no issue was found anywhere. However, the problem begins when we want to build the simulated robot by own. Lots of complexity arises like coordinate assignment, rotation not aligned, length mismatch, robot not synced with DH parameter. We begin to find some documents for making the robots. A few bits of the document are present. That is why we research it. After doing that, we prepared this paper for the researcher who wants to develop the simulated robot independently. This paper can be referenced for them. To minimize the complexity of our research, we study an industrial robot, ABB IRB 120-30.6. It is a good and popular robot. It is six degrees of freedom robot. We will use the specification and STEP file from their respective website and build a simulated robot from the STEP file for our research purpose. Design/Methodology/Approach: We will create a simulated robot from ABB IRB 120-30.6 STEP file. To create a robot by own, we took the help of the IRB 120 robot model. To demonstrate as simple as possible, we start with that robot whose default design is already present. We match and tune the joint coordinate based on robot parameters through this experiment. Findings/results: Here, we see how to create a custom robot. Using the IRB 120 robot model, we will create a robot model step by step. Furthermore, it will move it around its axis. Originality/Value: Using this experiment, the new researcher can get valuable information to create their custom robot. Paper Type: Simulation-based Research.

An Inverse Kinematics Demonstration of a Custom Robot using C# and CoppeliaSim

Purpose: Inverse Kinematics (I.K.) is not as easy as Forward kinematics (F.K.), where we get a definite result. I.K. algorithm provides several possible solutions. From those finding the best solution is such a critical task. For standard robots which are commercially available in the market, the user is not concerned about I.K.'s complexity. They provide the control board and programming IDE to make it easy. However, when we develop a robotic arm from our D.H. parameter and driver board, complexity arises due to lots of difficulties for executing and successful completion. To make life easy, keeping CoppeliaSim background can eliminate the calculation overhead and get good results. The custom robot is running with less computation power. It may be a good approach. We are using C# for User Interaction. Following step by step, anyone can create a robust I.K. engine with little effort. The complete code is available in GitHub to test and experiment further. Design/Methodology/Approach: The data are propagated through Interprocess communication. For the user interaction, we use visual studio IDE using the most accessible language, C#. The user interaction data are sent to another application, CoppeliaSim, which calculates inverse kinematics, and effective results are displayed through robotic arm movement. Findings/Result: Implementing this procedure can get the excellent result of the robotics arm. Furthermore, by imposing the Value on the real robot, we can get effective results. It minimizes the research overhead on I.K. calculation. Originality/Value: Without knowing I.K. calculation complexity, receiving the Value, we can apply it to the real robot. Two issues we can solve here. One is the calculation, and another one is experiment overhead. Paper Type: Simulation-based Research.

An Inverse Kinematics Demonstration of a Custom Robot using C# and CoppeliaSim

Purpose: Inverse Kinematics (I.K.) is not as easy as Forward kinematics (F.K.), where we get a definite result. I.K. algorithm provides several possible solutions. From those finding the best solution is such a critical task. For standard robots which are commercially available in the market, the user is not concerned about I.K.'s complexity. They provide the control board and programming IDE to make it easy. However, when we develop a robotic arm from our D.H. parameter and driver board, complexity arises due to lots of difficulties for executing and successful completion. To make life easy, keeping CoppeliaSim background can eliminate the calculation overhead and get good results. The custom robot is running with less computation power. It may be a good approach. We are using C# for User Interaction. Following step by step, anyone can create a robust I.K. engine with little effort. The complete code is available in GitHub to test and experiment further. Design/Methodology/Approach: The data are propagated through Interprocess communication. For the user interaction, we use visual studio IDE using the most accessible language, C#. The user interaction data are sent to another application, CoppeliaSim, which calculates inverse kinematics, and effective results are displayed through robotic arm movement. Findings/Result: Implementing this procedure can get the excellent result of the robotics arm. Furthermore, by imposing the Value on the real robot, we can get effective results. It minimizes the research overhead on I.K. calculation. Originality/Value: Without knowing I.K. calculation complexity, receiving the Value, we can apply it to the real robot. Two issues we can solve here. One is the calculation, and another one is experiment overhead. Paper Type: Simulation-based Research.

A Custom Robotic ARM in CoppeliaSim

Purpose: For robotics research, we require the robot to test our functions, Logics, algorithms, tasks, etc. Generally, we do not experiment with the practical robot. The primary issue is Practical robots are costly. The individual researcher usually cannot afford it. The second one is, the test with the real robot is risky and can damage property, human life, and itself due to bugs in the program or abnormal activity. So, it is best practice to experiment in Simulator first. When the algorithm is finalized, it can be implemented into a real robot. A researcher who starts the Robotics research, the learning curve is too long to develop a workable robot in Simulator. This paper demonstrates how we can easily create a 7 Degree of Freedom (DOF) custom robot for our research purpose. We will use the CoppeliaSim robot simulator for this purpose. It is free, opensource, and entirely GUI-based. We can create a robot without writing any code using this software. Design/Methodology/Approach: Here we describe to develop a custom robot. At first, we created a DH parameter for our robot. Then following the step-by-step procedure, the robot is created. After creating, we can attach our code on any object using LUA script language. To control the robot from external world, we can connect through TCP/IP socket communication. Establishing the communication, our robot will move depending on processed algorithm. Findings/Result: The robotic arm researcher needs robotics arm to test their forward kinematics, Inverse kinematics, statics, dynamics etc. code. Here we design our custom robots for research purpose. Originality/Value: Using CoppeliaSim, we can design custom robot for our research.

A Custom Robotic ARM in CoppeliaSim

Purpose: For robotics research, we require the robot to test our functions, Logics, algorithms, tasks, etc. Generally, we do not experiment with the practical robot. The primary issue is Practical robots are costly. The individual researcher usually cannot afford it. The second one is, the test with the real robot is risky and can damage property, human life, and itself due to bugs in the program or abnormal activity. So, it is best practice to experiment in Simulator first. When the algorithm is finalized, it can be implemented into a real robot. A researcher who starts the Robotics research, the learning curve is too long to develop a workable robot in Simulator. This paper demonstrates how we can easily create a 7 Degree of Freedom (DOF) custom robot for our research purpose. We will use the CoppeliaSim robot simulator for this purpose. It is free, opensource, and entirely GUI-based. We can create a robot without writing any code using this software. Design/Methodology/Approach: Here we describe to develop a custom robot. At first, we created a DH parameter for our robot. Then following the step-by-step procedure, the robot is created. After creating, we can attach our code on any object using LUA script language. To control the robot from external world, we can connect through TCP/IP socket communication. Establishing the communication, our robot will move depending on processed algorithm. Findings/Result: The robotic arm researcher needs robotics arm to test their forward kinematics, Inverse kinematics, statics, dynamics etc. code. Here we design our custom robots for research purpose. Originality/Value: Using CoppeliaSim, we can design custom robot for our research. Paper Type: Simulation based Research

A simulation driven development framework for parallel kinematics

This work presents a novel software tool to design, analyze and simulate parallel robots. It considers any desired constraints, requirements and load scenarios, while being able to be used by non-experts. This is comprehensively shown for one kind of the Gough/Stewart-platform kinematics class. First, the inverse kinematics is derived, which allows for the interactive exploration of the workspace, as well as other properties, prior to building the machine. In addition, the forward kinematics are implemented iteratively. The validation of the simulation is done by presenting a low cost, six degree of freedom robot for laboratory applications, being designed using this framework. Here, both the inverse and forward kinematics are used in real time to allow for precise and correct movement, detailed in-process measurements, such as process loads, along with overload protection. The approach fosters the efficient selection of existing as well as the design of custom robots of this kind.

An Optimization-Based Algorithm for Trajectory Planning of an Under-Actuated Robotic Arm to Perform Autonomous Suturing.

In single-port access surgeries, robot size is crucial due to the limited workspace. Thus, a robot may be designed under-actuated. Suturing, in contrast, is a complicated task and requires full actuation. This study aims to overcome this shortcoming by implementing an optimization-based algorithm for autonomous suturing for an under-actuated robot. The proposed algorithm approximates the ideal suturing trajectory by slightly reorienting the needle while deviating as little as possible from the ideal, full degree-of-freedom suturing case. The deviation of the path taken by a custom robot with respect to the ideal trajectory varies depending on the suturing starting location within the workspace as well as the needle size. A quantitative analysis reveals that in 13% of the investigated workspace, the accumulative deviation was less than 10 mm. In the remaining workspace, the accumulative deviation was less than 30 mm. Likewise, the accumulative deviation of a needle with a radius of 10 mm was 2.2 mm as opposed to 8 mm when the radius was 20 mm. The optimization-based algorithm maximized the accuracy of a four-DOF robot to perform a path-constrained trajectory and illustrates the accuracy-workspace correlation.

Accuracy analysis of robotic assistant needle placement for trigeminal gasserian ganglion

To evaluate the accuracy and feasibility of a custom robot system guided by optical navigation for needle puncture on trigeminal gasserian ganglion. A synthetic human skull model was used, with plasticine placed around the skull base to imitate the human soft tissue. Cone beam CT (CBCT) scanning was performed before the operation. With image data transferred to the graphical user interface of the computer workstation, the oval foramen was selected as the target and the "skin entry point" was also determined by the surgeon on the surgical planning software. Thus the needle trajectory was eventually planned. The skull model was fixed firmly to the trial table with a head clamp and relative size of the trial table was the same as a standard operating table. Following point-based registration, the data were sent to the robot control unit. Only after the surgeon's confirmation, the needle was automatically inserted into the intended target by the robot guided by optical navigation. When the procedure was completed, the instantaneous data of the needle tip orientation acquired by navigation system was sent back to the computer workstation for accuracy verification by calculating the geometric distance between the needle tip and the planning target after matrix transformation. Subsequently, after the needle had been released, CBCT scanning was also acquired to make image fusion of the preoperative skull and the postoperative skull. The data of the needle tip orientation was acquired on the postoperative image and the accuracy was re-verified by calculating the geometric distance between the needle tip and the planning target after matrix transformation. IBM SPSS Statistics 20 was used for statistical analysis and the paired t-test was used to compare the differences in the accuracy measured by the intraoperative navigation and postoperative image fusion. All 20 interventions were successfully located in oval foramen at the first needle insertion. The mean deviation of the needle tip was (0.56±0.07) mm (measured by the navigation system) and (1.49±0.14) mm (measured by the image fusion), respectively (P<0.001). The experimental results show the robot system is efficient and reliable. The navigation accuracy is one of the most significant factors in robotic procedures.

Design and Control of Aerial Modules for Inflight Self-Disassembly

Robotic modular systems have the ability to create and break physical links to self-assemble larger custom robots for general tasks. In case of changes in the task or the environment, they can dynamically self-adapt by self-reconfiguring during the mission. However, applying these concepts to flying vehicles is still a challenge. In this letter, we present a novel modular design based on a quadrotor platform that uses a lightweight passive mechanism to dock and undock in midair. Using this mechanism and a control strategy, we can divide a rectangular structure into two sub-structures during the flight. The undocking action can be sequentially applied to disassemble structures into individual modules. Since self-assembly methods for aerial vehicles have been proposed in the literature, here we focus on the self-disassembly process. We validate our undocking method and self-disassembly algorithm through experiments with actual modules. We highlight that combining our proposed self-disassembly algorithm and existing self-assembly algorithms, aerial modules are able to perform inflight self-reconfiguration.

Obtaining fault tolerance avoidance behavior using deep reinforcement learning

In this article, a mapless movement policy for mobile agents, designed specifically to be fault-tolerant, is presented. The provided policy, which is learned using deep reinforcement learning, has advantages compared to the usual mapless policies: this policy is capable of handling a robot even when some of its sensors are broken. It is an end-to-end policy based on three neuronal models capable not only of moving the robot and maximizing the coverage of the environment but also of learning the best movement behavior to adapt it to its perception needs. A custom robot, for which none of the readings of the sensors overlap each other, has been used. This setup makes it possible to determine the operation of a robust failure policy, since the failure of a sensor unequivocally affects the perceptions. The proposed system exhibits several advantages in terms of robustness, extensibility and utility. The system has been trained and tested exhaustively in a simulator, obtaining very good results. It has also been transferred to real robots, verifying the generalization and the good functioning of our model in real environments.