Biomimetic learning of hand gestures in a humanoid robot.

Hand gestures are a natural and intuitive form of communication, and integrating this communication method into robotic systems presents significant potential to improve human-robot collaboration. Recent advances in motor neuroscience have focused on replicating human hand movements from synergies also known as movement primitives. Synergies, fundamental building blocks of movement, serve as a potential strategy adapted by the central nervous system to generate and control movements. Identifying how synergies contribute to movement can help in dexterous control of robotics, exoskeletons, prosthetics and extend its applications to rehabilitation. In this paper, 33 static hand gestures were recorded through a single RGB camera and identified in real-time through the MediaPipe framework as participants made various postures with their dominant hand. Assuming an open palm as initial posture, uniform joint angular velocities were obtained from all these gestures. By applying a dimensionality reduction method, kinematic synergies were obtained from these joint angular velocities. Kinematic synergies that explain 98% of variance of movements were utilized to reconstruct new hand gestures using convex optimization. Reconstructed hand gestures and selected kinematic synergies were translated onto a humanoid robot, Mitra, in real-time, as the participants demonstrated various hand gestures. The results showed that by using only few kinematic synergies it is possible to generate various hand gestures, with 95.7% accuracy. Furthermore, utilizing low-dimensional synergies in control of high dimensional end effectors holds promise to enable near-natural human-robot collaboration.

Application of Novel Wearable Self-Balancing Exoskeleton Robot Capable for Complete Self-Support in Post-stroke Rehabilitation: A Case Study.

Early weight-bearing and trunk control training are essential components for promoting lower limb motor recovery in individuals with stroke. In this case study, we presented the successful implementation of a three-week wearable self-balancing exoskeleton robot training program for a 57-year-old male patient who had suffered from a stroke. After carefully reviewing the patient's previous medical records, conducting a thorough assessment, and excluding other potential contraindications, we introduced wearable self-balancing exoskeleton robot training to complement conventional rehabilitation in managing balance and lower limb function. The training program included early initiation of weight bearing and trunk control training following an ischemic stroke, aimed at promoting motor recovery and improving functional independence. The findings indicated that training with a wearable self-balancing exoskeleton robot enhanced the balance and motor function of the hemiplegic patient, with commendable adherence. Furthermore, the participants consistently reported increased satisfaction and confidence during the training sessions. This case report not only provided preliminary evidence of the effectiveness of the wearable self-balancing exoskeleton robot in promoting functional recovery following a stroke but also outlined a comprehensive training program that may hold value for future clinical application.

Evaluation of Clinical Research on Novel Multiport Robotic Platforms for Urological Surgery According to the IDEAL Framework: A Systematic Review of the Literature.

Background and objective: Several novel multiport robotic systems have been developed and introduced in clinical practice after regulatory approval. The objective of this systematic review was to assess the evolution status of novel robotic platforms approved for clinical use in urological surgery according to the IDEAL framework. Methods: A systematic review was conducted using the Medline and Scopus databases according to the updated Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines (CRD42024503227). Comparative or noncomparative studies reporting on any urological procedures performed with novel robotic platforms (Hugo RAS; Versius, KangDuo, Senhance, REVO-I, Avatera, Hinotori, Dexter, or Toumai) were selected and included in the analysis. Key findings and limitations: Seventy-four eligible studies were included, of which 67 (90.5%) were noncomparative surgical series representing developmental or explorative studies according to the IDEAL criteria. Only one randomised controlled trial (comparing KangDuo vs da Vinci robot-assisted partial nephrectomy) was included. The trial showed comparable perioperative outcomes between the two robotic systems. Four studies assessed clinical outcomes for patients undergoing urological procedures using a REVO-I (1 study), Senhance (2 studies), or Hinotori (1 study) system in comparison to the same procedures performed using a da Vinci system. All studies revealed outcomes comparable to those with the da Vinci system. Limitations include the small sample size in all studies, and assessment of first-generation novel platforms versus the fourth-generation multiarm da Vinci system in most of the comparative studies. Conclusions and clinical implications: A few poor-quality studies have compared the use of novel robotic platforms to da Vinci systems in urological surgery and demonstrated comparable results. Most studies can be classified as developmental or explorative, representing the initial steps of clinical research. Large multicentre series are needed to understand whether these novel robots could offer advantages beyond cost reductions over the da Vinci systems. Patient summary: We reviewed research on new robotic systems for surgery in urology. Several studies have shown the feasibility and safety of these new robots during the most common procedures. Very few studies have assessed clinical outcomes with the new robots in comparison to the reference standard, which is a fourth-generation da Vinci robot. Large multicentre studies are needed to understand whether the new robots could offer advantages other than cost savings over the da Vinci robot.

Effectiveness of soft coagulation in robot-assisted partial nephrectomy in preventing pseudoaneurysms and its influence on renal function based on propensity score-matched analysis.

Background: Renal artery pseudoaneurysm (RAP) is one of the most stressful and life-threatening complications of partial nephrectomy, the standard treatment for small renal cell carcinoma. The use of a monopolar soft coagulation system for hemostasis during robot-assisted partial nephrectomy (RAPN) is expected to prevent post-surgical RAP development. In this study, we aimed to investigate how the use of a soft coagulation system in RAPN reduces postoperative pseudoaneurysms and changes renal function over time. Methods: The incidence of pseudoaneurysms and postoperative renal function were compared in 208 partial nephrectomies performed between May 2016 and March 2023 at a single institution, with propensity score matching to balance patient backgrounds. Outcomes were analyzed using multivariate logistic or linear regression analyses. Results: In total, 80 matched pairs were analyzed. One (1.2%) and eighteen (22.5%) pseudoaneurysms were found in the soft coagulation users and non-users, respectively (P<0.001). Compared to the non-user group, postoperative estimated glomerular filtration rates (eGFRs) in the user group were 89% vs. 96% (P<0.001), 87% vs. 93% (P=0.009), and 88% vs. 92% (P=0.15) at 1, 3, and 12 months, respectively. Subsequent multivariate analyses showed a lower incidence of pseudoaneurysms in the user group with an odds ratio of 0.05 [95% confidence interval (CI): 0.01 to 0.44; P=0.007], and no significant difference in the rate of change in renal function at 12 months postoperatively (-1.1%, 95% CI: -5.5% to 3.3%; P=0.61). Conclusions: The use of a soft coagulation system reduces pseudoaneurysm occurrence after partial nephrectomy. Although renal function decreased in the short-term for the use group, no long-term differences were observed.

Magnetically Controllable Paper-Based Soft Robots for Colorimetric Detection of Heavy Metal Ions.

Magnetically controllable soft robots are of great interest because they have unique properties compared with conventional rigid counterparts and can be used in diverse applications such as intelligent electronics, bionics, personalized medicine, and cargo grasping. However, the fabrication of such multifunctional soft robots has been challenging because of the integration of dissimilar materials into the robot body. Herein, we designed and fabricated a soft robotic multifunctional system using conventional papers and elastomeric polymers for the colorimetric detection of heavy metal ions (Hg2+ and Fe3+) in water samples. The magnetic actuation of the platforms was shown to correlate with the type of underlying paper and magnetic particle content in the mixtures. Moreover, it was observed that actuation can also be manipulated by controlling the magnetic field strength. A proof-of-concept robotic paper-based Hg2+, Zn2+, and Fe3+ ion detection was demonstrated by combining colorimetric paper sensors and magneto-papers. Our study highlights the significant potential of paper as a material for the fabrication of effective and multifunctional untethered soft robots.

Microinterventional system for robot-assisted gonioscopic surgery- technical feasibility and preclinical evaluation in synthetic eye models.

BACKGROUND: Preclinical technical feasibility study of robot-assisted microinvasive glaucoma surgery using a novel ophthalmic robot-assisted surgery system. METHODS: Feasibility was assessed in synthetic eye models in two stages: Stage I, nonimplantable robot-assisted goniotomy; and Stage II, robot-assisted stent implantation using a trabecular bypass stent. Robot-assisted interventions were subsequently compared to the manual approach. RESULTS: Stage I: Two surgeons completed 10 trials each of ab-interno sectoral goniotomy with and without robotic assistance for at least 3 clock hours using a standard goniotomy knife and more than 10 clock hours of extended goniotomy using a flexible, guided goniotomy instrument. Stage II: Trabecular bypass stent deployment was successfully achieved in 100% of the attempts with and without robotic assistance. Surgical time was recorded and compared between the robotic-assisted and the manual approach. CONCLUSIONS: A system for robot-assisted microinvasive glaucoma surgery can successfully achieve implantable and nonimplantable interventions in the anterior segment. This is the first known demonstration of the feasibility of robot-assisted glaucoma surgery.

Efficacy and prognostic analysis of carbon nanotracers combined with the da Vinci robot in the treatment of esophageal cancer.

BACKGROUND: Traditional methods cannot clearly visualize esophageal cancer (EC) tumor contours and metastases, which limits the clinical application of da Vinci robot-assisted surgery. AIM: To investigate the efficacy of the da Vinci robot in combination with nanocarbon lymph node tracers in radical surgery of EC. METHODS: In total, 104 patients with early-stage EC who were admitted to Liuzhou worker's Hospital from January 2020 to June 2023 were enrolled. The patients were assigned to an observation group (n = 52), which underwent da Vinci robot-assisted minimally invasive esophagectomy (RAMIE) with the intraoperative use of nanocarbon tracers, and a control group (n = 52), which underwent traditional surgery treatment. The operation time, intraoperative blood loss, postoperative drainage tube indwelling time, hospital stay, number of lymph nodes dissected, incidence of complications, and long-term curative effects were comparatively analyzed. The postoperative stress response C-reactive protein (CRP), cortisol, epinephrine (E) and inflammatory response interleukin (IL)-6, IL-8, IL-10, and tumor necrosis factor-alpha (TNF-α) were evaluated. RESULTS: Compared with the control group, the observation group had significantly lower postoperative CRP, cortisol, and E levels (P < 0.05) with a milder inflammatory response, as indicated by lower IL-6, IL-10, and TNF-α levels (P < 0.05). Patients who underwent RAMIE had less intraoperative blood loss and shorter operation times and hospital stays than those who underwent traditional surgery. The average number of dissected lymph nodes, time of lymph node dissection, and mean smallest lymph node diameter were all significantly lower in the observation group (P < 0.05). The rate of postoperative complications was 5.77% in the observation group, significantly lower than the 15.38% observed in the control group. Furthermore, the lymphatic metastasis rate, reoperation rate, and 12- and 24-month cumulative mortality in the observation group were 1.92%, 0%, 0%, and 0%, respectively, all of which were significantly lower than those in the control group (P < 0.05). CONCLUSION: The treatment of EC using the da Vinci robot combined with nanocarbon lymph node tracers can achieve good surgical outcomes and demonstrates promising clinical applications.

Da Vinci robot-assisted retroperitoneal tumor resection in 105 patients: a single-center experience.

Background: The Da Vinci Surgical System (DVSS) has the advantages of minimal invasion, rapid recovery, safety, and reliability. Although the DVSS has been widely used in various abdominal surgeries, descriptions of its use in robot-assisted retroperitoneal tumor resection (RRTR) are limited to case reports; large-sample systematic studies are lacking. The present study was performed to analyze the data of RRTR in our center, summarize our experience, and provide a reference for other retroperitoneal tumor centers. Methods: We retrospectively analyzed the clinical data of 105 patients who underwent RRTR at the Affiliated Hospital of Qingdao University from January 2015 to December 2022. Logistic univariate and multivariate analyses were performed to identify independent risk factors affecting RRTR. A receiver operating characteristic curve was used to find the cut-off value, which was then included in the logistic multivariate analysis for verification. Results: Among the 105 patients, 87 successfully underwent RRTR (DVSS group) and 18 underwent conversion to open surgery (conversion group). There was no significant difference in sex, age, body mass index, history of abdominal surgery, or tumor location between the two groups (P > 0.05). The maximum tumor diameter [odds ratio (OR), 1.041; 95% confidence interval (CI), 1.015-1.067; P = 0.002] and pathological property (OR, 8.646; 95% CI, 2.370-31.544; P = 0.001) were independent risk factors for conversion to open surgery. Further analysis confirmed that the success rate of RRTR was higher for tumors with a maximum diameter of ≤64 mm and benign tumors. Based on our experience and statistical results, we believe that retroperitoneal tumors that meet the following criteria have a higher success rate of DVSS resection: maximum tumor diameter of ≤64 mm, benign tumors, the tumor has relatively clear boundary, no obvious invasion of surrounding tissues and organs, and no need for combined organ resection. Conclusions: RRTR is safe and effective in the treatment of RPT, and the clinical prognosis is similar to that of open surgery. The success rate of RRTR in patients with appropriate surgical indications for this procedure is higher.

Design and validation a minimally invasive robotic surgical instrument with decoupled pose and multi-DOF.

High-performance miniature surgical instruments play an important role in complicated minimally invasive surgery (MIS). Based on in-depth analysis of the requirements of MIS and the characteristics of the existing minimally invasive surgical instruments, a multiple degrees of freedom (DOF) robotic surgical instrument with decoupled pose was proposed. Firstly, the design concept of the pose decoupling instrument was described in detail, and its physical structure, transmission structure, and mechanical properties were designed and analyzed. A surgical instrument control algorithm based on the master-slave mode was established. Finally, a physical prototype was developed, and its motion ranges of joints, load capacity, and suture operation performance were comprehensively evaluated, which confirmed the effectiveness of the proposed minimally invasive robotic surgical instrument.

A systematic review and meta-analysis compared the safety and effectiveness of the AirSeal system with traditional pneumoperitoneum systems in robot-assisted laparoscopic urologic surgery.

This study aimed to analyze perioperative results in robot-assisted laparoscopic urological surgeries, comparing the AirSeal system with traditional pneumoperitoneum systems. This study adhered to the PRISMA guidelines for conducting systematic reviews and meta-analyses. Extensive searches were conducted in PubMed, EMBASE, and Google Scholar, including randomized controlled trials (RCTs) and cohort studies up to June 15, 2024. A combined examination of the studies found that the AirSeal system had superior results in terms of surgery duration, end-tidal carbon dioxide levels, and tidal volume compared to the traditional pneumoperitoneum system. During robotic-assisted partial nephrectomy, the AirSeal team experienced a notable decrease in surgical time, ETCO2, and VT. In addition, the occurrence of SCE was lower in the AirSeal group. However, there were no significant differences observed between the groups regarding EBL, LOHS, overall complications, and major complications. Compared to conventional pneumoperitoneum systems, the AirSeal system offers several advantages in robot-assisted laparoscopic urological surgery: reduced operative time, lower end-tidal CO2 pressure, and decreased tidal volume. Furthermore, implementing the AirSeal system does not lead to higher rates of complications, estimated blood loss, or lengthier hospital stays.

Safety and efficiency of deep brain stimulation in the elderly patients with Parkinson's disease.

AIMS: Deep brain stimulation (DBS) is not routinely performed in elderly patients (≥75 years old) to date because of concerns about complications and decreased benefit. This study aimed to evaluate the safety and efficacy of DBS in elderly patients with Parkinson's disease. METHODS: A retrospective analysis was performed using data from 40 elderly patients from four centers who were treated with neurosurgical robot-assisted DBS between September 2016 and December 2021. These patients were followed up for a minimum period of 2 years, with a subgroup of nine patients followed up for 5-7 years. Patient demographic characteristics, surgical information, pre- and postoperative motor scores, non-motor scores, activities of daily living, and complications were retrospectively analyzed. RESULTS: The mean surgical procedure duration was 1.65 ± 0.24 h, with a mean electrode implantation duration of 1.10 ± 0.23 h and a mean pulse generator implantation duration of 0.55 ± 0.07 h. The mean pneumocephalus volume, electrode fusion error, and Tao's DBS surgery scale were 16.23 ± 12.81 cm3, 0.81 ± 0.23 mm, and 77.63 ± 8.08, respectively. One patient developed a skin infection, and the device was removed. The Unified Parkinson's disease rating scale, Unified Parkinson's disease rating scale of Part III, tremor, rigidity, bradykinesia, axial, and Barthel index for activities of daily living (ADL-Barthel) scores significantly improved at the 2-year follow-up (p < 0.05). The levodopa equivalent daily dose (LEDD) was significantly reduced at the 2-year follow-up (p < 0.05). However, the Montreal cognitive assessment, Hamilton depression scale, and Hamilton anxiety scale scores did not significantly change during the 2-year follow-up (p > 0.05). Additionally, in the subgroup with a 5-year follow-up, the motor symptoms, ADL-Barthel score, and cognitive function worsened over time compared to baseline. However, there was still an improvement in motor symptoms and ADL with DBS on-stimulation compared with the off-stimulation state. The LEDD increased 5 years after surgery compared to that at baseline. Eleven patients had passed away during follow-up, the mean survival time was 38.3 ± 17.3 months after surgery, and the mean age at the time of death was 81.2 (range 75-87) years. CONCLUSION: Robot-assisted DBS surgery for the elderly patients with Parkinson's disease is accurate and safe. Motor symptoms and ADL significantly improve and patients can benefit from long-term neuromodulation, which may decrease the risk of death.

Robot-assisted Single-port Radical Prostatectomy with the SHURUI SP and da Vinci SP Platforms: Comparison of the Technology, Intraoperative Performance, and Outcomes.

Background and objective: The purpose-built SHURUI single-port (SP) robotic platform has recently been introduced for several procedures in urology, general surgery, and gynecology. However, comparative evidence on its performance in relation to earlier models such as the da Vinci SP is lacking. Our aim was to compare the step-by-step techniques and 1-yr outcomes for radical prostatectomy (RP) between the SHURUI SP and da Vinci SP robots. Methods: Data were retrieved from two prospectively maintained databases. The SHURUI SP robot was used to perform RP in 34 patients in China (September 2021 to August 2022); the da Vinci SP robot was used to perform 100 consecutive RP cases in the USA (June 2019 to October 2020). A comparative analysis was conducted before and after 1:1 propensity score matching for age, body mass index, American Urological Association symptom score, prostate size, prostate-specific antigen (PSA) levels, biopsy grade group, and D'Amico risk group. Intraoperative performance and short-term oncological and continence outcomes were compared between the groups. Biochemical recurrence was defined as two consecutive postoperative PSA levels >0.2 ng/ml. Continence was defined as full recovery of urinary control without the use of pads. The Kaplan-Meier method was used to estimate continence recovery curves, and a log-rank test for trend was used to detect ordered differences in continence recovery between the SHURUI SP and da Vinci SP groups after surgery. Key findings and limitations: For the matched SHURUI and da Vinci groups, median age (69 vs 69 yr), median PSA (8.4 vs 7.1 ng/ml), and the proportion of patients with low-risk (33.3% vs 29.6%), intermediate-risk (66.7% vs 63%), and high-risk disease (0% vs 7.4%) were comparable (all p > 0.05). All surgeries were successfully accomplished without conversion. A higher percentage of cases in the SHURUI group involved extraperitoneal access (81.5% vs 0%; p < 0.001) and a pure SP approach (25.9% vs 0%; p = 0.01), while a higher percentage of cases in the da Vinci group had nerve-sparing surgery. The median total operative (215 vs 110 min; p < 0.001) and median console time (162 vs 75 min; p < 0.001) were significantly longer in the SHURUI group. No intraoperative or major postoperative complications were observed in either group. Rates of positive surgical margins (18.5% vs 14.8%; p = 1.0) and extraprostatic extension (14.8% vs 29.6%; p = 0.19) were similar. At median follow-up of 13.5 versus 15.9 mo, none of the patients had experienced biochemical recurrence. At 1 yr after surgery, the continence rate was 96.3% in both groups. Conclusions: Despite differences in driving mechanisms between the two SP robotic systems, RP can be performed safely and effectively with the SHURUI RP robot during the initial learning phase, with similar short-term oncological and continence outcomes to those with the da Vinci SP robot. Patient summary: We compared two surgical robots (SHURUI SP and da Vinci SP) used to perform robotic surgery to remove the prostate through a single keyhole incision instead of multiple incisions. Our results show comparable technology and similar surgical and short-term cancer control outcomes for the two robots.

The pilot study of the effect of six-week robot-assisted ankle training on mobility and strength of lower extremity and life habits for children with cerebral palsy.

Background: Children with cerebral palsy often have weak ankle muscles and reduced ankle dorsiflexion, which leads to activity limitations and eventually affects quality of life. Robotic ankle training was recently developed to facilitates muscle function through a high repetition of exercises. This study investigated the effect of six-week ankle training using the Anklebot device to improve lower limb structural and functional impairments and the resulting impact on quality of life. Methods: Five children with spastic cerebral palsy aged between 4 and 11 years participated in six weeks of bilateral ankle assistive training using the Anklebot device. All lower limb muscle strength was measured with a hand-held dynameter, and range of motion was measured with a goniometer, at four different time points. Muscle architecture was assessed using a portable diagnostic ultrasound device, and quality of life was assessed using the Life Habits for Children scale, at two points in time only. Results: Muscle strength and range of motion for all lower limb joints demonstrated significant improvement on both sides after training. The ankle muscle architecture showed non-significant improvement, while an overall significant improvement in the total score of the Life Habits for Children scale was detected after training. Conclusion: Robot-assisted task-specific ankle training provides promising effects by allowing the required repetition to improve structural and functional muscle and joint impairments, which has a positive influence on the children's quality of life. However, due to a limited sample size, these results should be considered as preliminary; further study is needed.

Beyond simulation: Unlocking the frontiers of humanoid robot capability and intelligence with Pepper's open-source digital twin.

This research paper presents a high-fidelity, open-source digital-twin of the Pepper robot developed within the framework of the Robot Operating System 2 (ROS 2) for better simulation realism in complex tasks of machine learning. We developed a dedicated, custom ROS 2 package with modern simulation tools, such as Gazebo Sim, MoveIt 2, Rviz2, that brings complete, realistic environments in line with the exact behaviors and interactions of robots in reality. Better accuracy of the physical movement of Pepper robot's simulation was shown on the digital twin, validated by the Choregraphe software and real robot performance, to be a strong platform of collaboration and further research by the community. This development greatly pushes the envelope of human-like humanoid robotics further by offering a scaled, flexible, and plausible training environment conducive to integrating complex algorithms of robot learning and interaction capabilities.

Approaches for hysterectomy and implementation of robot-assisted surgery in benign gynaecological disease: A cost analysis study in a large university hospital.

BACKGROUND: As a minimally invasive technique, robot-assisted hysterectomy (RAH) offers surgical advantages and significant reduction in morbidity compared to open surgery. Despite the increasing use of RAH in benign gynaecology, there is limited data on its cost-effectiveness, especially in a European context. Our goal is to assess the costs of the different hysterectomy approaches, to describe their clinical outcomes, and to evaluate the impact of introduction of RAH on the rates of different types of hysterectomy. METHODS: A retrospective single-centre cost-analysis was performed for patients undergoing a hysterectomy for benign indications. Abdominal hysterectomy (AH), vaginal hysterectomy (VH), laparoscopic hysterectomy (LH), laparoscopically assisted vaginal hysterectomy (LAVH) and RAH were included. We considered the costs of operating room and hospital stay for the different hysterectomy techniques using the "Activity Centre-Care program model". We report on intra- and postoperative complications for the different approaches as well as their cost relationship. RESULTS: Between January 2014 and December 2021, 830 patients were operated; 67 underwent VH (8%), 108 LAVH (13%), 351 LH (42%), 148 RAH (18%) and 156 AH (19%). After the implementation and learning curve of a dedicated program for RAH in 2018, AH declined from 27.3% in 2014-2017, to 22.1% in 2018 and 6.9 % in 2019-2021. The reintervention rate was 3-4% for all surgical techniques. Pharmacological interventions and blood transfusions were performed after AH in 28%, and in 17-22% of the other approaches. AH had the highest hospital stay cost with an average of €2236.40. Mean cost of the hospital stay ranged from €1136.77-€1560.66 for minimally invasive techniques. The average total costs for RAH were €6528.10 compared to €4400.95 for AH. CONCLUSION: Implementation of RAH resulted in a substantial decrease of open surgery rate. However, RAH remains the most expensive technique in our cohort, mainly due to high material and depreciation costs. Therefore, RAH should not be considered for every patient, but for those who would otherwise need more invasive surgery, with higher risk of complications. Future prospective studies should focus on the societal costs and patient reported outcomes, in order to do cost-benefit analysis and further evaluate the exact value of RAH in the current healthcare setting.

Human-Robot Collaboration With a Corrective Shared Controlled Robot in a Sanding Task.

OBJECTIVE: Physical and cognitive workloads and performance were studied for a corrective shared control (CSC) human-robot collaborative (HRC) sanding task. BACKGROUND: Manual sanding is physically demanding. Collaborative robots (cobots) can potentially reduce physical stress, but fully autonomous implementation has been particularly challenging due to skill, task variability, and robot limitations. CSC is an HRC method where the robot operates semi-autonomously while the human provides real-time corrections. METHODS: Twenty laboratory participants removed paint using an orbital sander, both manually and with a CSC robot. A fully automated robot was also tested. RESULTS: The CSC robot improved subjective discomfort compared to manual sanding in the upper arm by 29.5%, lower arm by 32%, hand by 36.5%, front of the shoulder by 24%, and back of the shoulder by 17.5%. Muscle fatigue measured using EMG, was observed in the medial deltoid and flexor carpi radialis for the manual condition. The composite cognitive workload on the NASA-TLX increased by 14.3% for manual sanding due to high physical demand and effort, while mental demand was 14% greater for the CSC robot. Digital imaging showed that the CSC robot outperformed the automated condition by 7.16% for uniformity, 4.96% for quantity, and 6.06% in total. CONCLUSIONS: In this example, we found that human skills and techniques were integral to sanding and can be successfully incorporated into HRC systems. Humans performed the task using the CSC robot with less fatigue and discomfort. APPLICATIONS: The results can influence implementation of future HRC systems in manufacturing environments.

Wearable high-density EMG sleeve for complex hand gesture classification and continuous joint angle estimation.

High-density electromyography (HD-EMG) can provide a natural interface to enhance human-computer interaction (HCI). This study aims to demonstrate the capability of a novel HD-EMG forearm sleeve equipped with up to 150 electrodes to capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous hand position via joint angle predictions. Ten able-bodied participants performed 37 hand movements and grasps while EMG was recorded using the HD-EMG sleeve. Simultaneously, an 18-sensor motion capture glove calculated 23 joint angles from the hand and fingers across all movements for training regression models. For classifying across the 37 gestures, our decoding algorithm was able to differentiate between sequential movements with 97.3 ± 0.3 % accuracy calculated on a 100 ms bin-by-bin basis. In a separate mixed dataset consisting of 19 movements randomly interspersed, decoding performance achieved an average bin-wise accuracy of 92.8 ± 0.8 % . When evaluating decoders for use in real-time scenarios, we found that decoders can reliably decode both movements and movement transitions, achieving an average accuracy of 93.3 ± 0.9 % on the sequential set and 88.5 ± 0.9 % on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a R 2 of 0.884 ± 0.003 in the sequential set and 0.750 ± 0.008 in the mixed set. Median absolute error (MAE) was kept below 10° across all joints, with a grand average MAE of 1.8 ± 0 . 04 ∘ and 3.4 ± 0 . 07 ∘ for the sequential and mixed datasets, respectively. We also assessed two algorithm modifications to address specific challenges for EMG-driven HCI applications. To minimize decoder latency, we used a method that accounts for reaction time by dynamically shifting cue labels in time. To reduce training requirements, we show that pretraining models with historical data provided an increase in decoding performance compared with models that were not pretrained when reducing the in-session training data to only one attempt of each movement. The HD-EMG sleeve, combined with sophisticated machine learning algorithms, can be a powerful tool for hand gesture recognition and joint angle estimation. This technology holds significant promise for applications in HCI, such as prosthetics, assistive technology, rehabilitation, and human-robot collaboration.

Learning a Tracking Controller for Rolling µbots.

Micron-scale robots (µbots) have recently shown great promise for emerging medical applications. Accurate control of µbots, while critical to their successful deployment, is challenging. In this work, we consider the problem of tracking a reference trajectory using a µbot in the presence of disturbances and uncertainty. The disturbances primarily come from Brownian motion and other environmental phenomena, while the uncertainty originates from errors in the model parameters. We model the µbot as an uncertain unicycle that is controlled by a global magnetic field. To compensate for disturbances and uncertainties, we develop a nonlinear mismatch controller. We define the model mismatch error as the difference between our model's predicted velocity and the actual velocity of the µbot. We employ a Gaussian Process to learn the model mismatch error as a function of the applied control input. Then we use a least-squares minimization to select a control action that minimizes the difference between the actual velocity of the µbot and a reference velocity. We demonstrate the online performance of our joint learning and control algorithm in simulation, where our approach accurately learns the model mismatch and improves tracking performance. We also validate our approach in an experiment and show that certain error metrics are reduced by up to 40%.

Child-centered home service design for a family robot companion.

The home robot-based child activity service aims to cultivate children's social emotions. A design theme was produced by interviewing child development experts and parents. The activity service is composed of 50 plays and 70 conversations. These were developed based on activities from psychomotor therapy and the guidelines of Ministry of Early Childhood Education in South Korea. In the field test, 50 children aged five-seven years participated to experience the activity services at home for 4 days. After completing the 4 days of field testing, we conducted customer satisfaction (CSAT) surveys, Godspeed evaluations and interviews to quantitatively and qualitatively verify the evaluations by the children and parents. As a result, 92% of the children and 80% of the parents evaluated that they were satisfied with the service. In addition, our results revealed that the social robot-based service contributed to improving the relationship between children and families by functioning as a messenger. Finally, the lessons learned from the service development and field tests were discussed to aid service designers and robotics engineers.

Miniature Modular Reconfigurable Underwater Robot Based on Synthetic Jet.

Modular reconfigurable robots exhibit prominent advantages in the reconnaissance and exploration tasks within unstructured environments for their characteristics of high adaptability and high robustness. However, due to the limitations in locomotion mechanism and integration requirements, the modular design of miniature robots in the aquatic environment encounters significant challenges. Here, a modular strategy based on the synthetic jet principle is proposed, and a modular reconfigurable robot system is developed. Specialized bottom and side jet actuators are designed with vibration motors as excitation sources, and a motion module is developed incorporating the jet actuators to realize three-dimensional agile motion. Its linear, rotational, and ascending motion speeds reach 70.7 mm s-1, 3.3 rad s-1, and 28.7 mm s-1, respectively. The module integrates the power supply, communication, and control system with a small size of 48 mm × 38 mm × 38 mm, which ensures a wireless controllable motion. Then, various configurations of the multi-module robot system are established with corresponding motion schemes, and the experiments with replaceable intermediate modules are further conducted to verify the transportation and image-capturing functions. This work demonstrates the effectiveness of synthetic jet propulsion for aquatic modular reconfigurable robot systems, and it exhibits profound potential in future underwater applications.