Robotic Devices Research Articles

A Cooperative game theory-based feature selection for efficient hand grasp classification using minimal number of sEMG signals

Deploying bio-electrical signals and image processing (visual) techniques are the two popular means to provide input to generate grasp control for robotic and prosthetic devices. Visual perception-based techniques rely on computationally expensive image processing algorithms and are affected by lighting conditions. In contrast, grasp control based on bio-electric signals such as surface electromyography (sEMG) is invariant to lighting conditions. It can reflect human intent to hand motion or grasp with lesser computational costs. In this article, we propose an efficient machine-learning pipeline to classify hand grasp using a minimal number of sEMG sensors. A cooperative game theory-based feature selection technique is applied to find the representative feature subset. The feature selection method uses a modified marginal contribution based on the class distribution coefficient to generate feature ranking. This feature ranking is further used to find the most representative feature subset from the extracted feature set. Our proposed pipeline has been evaluated on a benchmark dataset and has achieved a classification accuracy of 98.20%, using single-channel EMG when coupled with the XGBoost classifier. Thorough assessments were conducted to confirm the reliability of the results obtained. Our proposed pipeline holds the potential to facilitate the development of cost-effective sEMG prosthetics.

Robotic Surgery: Transforming Healthcare Landscape

Robotic surgery has come to light as an innovative advance in medicine that has drastically changed the face of healthcare. Patients can benefit from this technology's unparalleled precision, control, and minimally invasive choices to its integration of sophisticated robotics, artificial intelligence, and accurate surgical methods. With the use of robotic devices, surgeons may now conduct difficult procedures with increased accuracy, less trauma, and quicker recovery times. Shorter hospital stays and reduced complication rates are the results of this better patient outcome. The article examines the development of robotic surgery, its present uses in a range of medical specialties, and its effects on patient care and the larger healthcare system. It also addresses the difficulties and prospects for robotic surgery in the future, particularly how it might be integrated with cutting-edge innovations like telemedicine and machine learning, which have the potential to completely transform the surgical field. This analysis highlights how robotic surgery can change healthcare delivery and improve patient outcomes. It also shows how robotic surgery has the potential to become a new norm in modern medicine.

Sweeten the pill: Multi-faceted polysaccharide-based carriers for colorectal cancer treatment

Colorectal cancer (CRC) ranks as the second deadliest cancer globally and the third most common malignant tumor. While surgery remains the primary treatment for CRC, alternative therapies such as chemotherapy, molecular targeted therapy, and immunotherapy are also commonly used. The significant side effects and toxicity of conventional drugs drive the search for novel targeted therapies, including the design of advanced drug delivery systems. Polysaccharide-based biopolymers, with their low toxicity, non-immunogenic behavior, synergistic interactions with other biopolymers, and tissue and cell compatibility, emerge as excellent drug carriers for this application. This review aims to provide an in-depth overview of recent advancements in developing polysaccharide-based biopolymeric carriers for anticancer compounds in the treatment of CRC. We highlight the multifunctional nature of polysaccharides, showcasing their potential as standalone drug carriers or as integral components of intelligent robotic devices for biomedical therapeutic applications. In addition to exploring the opportunities for using carbohydrate polymers in CRC treatment, we address the challenges and failures that may limit their applicability in biomedical research, as well as summarize the recent preclinical and clinical trials, resulting in several commercialization attempts. This comprehensive overview critically summarizes the potential of polysaccharide-based biomaterials in CRC treatment.

Development of a Robotic Device That Performs Head Bunting to Relieve User Tension

Inspired by an animal behavior called bunting, in which the animal rubs its head against other objects, including humans, we developed robotic prototypes capable of performing such bunting behaviors. Since physical contact plays an important role in therapeutic interactions between pets and their owners, we hypothesize that robot bunting can have a similar effect on its user. This paper reports on the development of such a robot with a flexible neck that can change its stiffness while the robot is rubbing its head against the user. An exploratory study was also conducted with 22 human participants, on whom the developed robot performed head bunting with three different (low/high/variable) stiffness conditions. The results show that the participants’ psychological tension, as measured by the Temporary Mood Scale (TMS), was significantly reduced ( \(p\lt 0.001\) ) after interacting with the robot. The difference between the three stiffness conditions was not significant in this study. Due to the lack of a control condition, we cannot confirm a clear effect of the stiffness change; however, some participants commented that the stiffness change made the robot's behavior lifelike and relaxing.

Effect of Programed Walking Exercise Using Bot Fit in Younger Adults

IntroductionPhysical inactivity and sedentary behavior both increase the risk of chronic disease and mortality. Regular participation in physical activity and reducing sedentary behavior play important roles in maintaining physical health and disease prevention.ObjectiveThe purpose of this study was to investigate the effect of programed walking exercise using a wearable hip exoskeleton, Bot Fit on muscle strength, muscle effort, and the kinematics of the pelvis in younger adults.MethodsWe designed three parallel experimental conditions and randomly assigned participants to one of three groups: those assigned to exercise using an interval program of Bot Fit (interval group), those who used a power program of Bot Fit (power group), and a control group who exercised without Bot Fit. A total of 45 young adults participated in 18 exercise-intervention sessions over six weeks, and all participants were assessed at two time points: before and after the 18 exercise sessions. Each assessment evaluated muscle strength, muscle effort, and the kinematics of the pelvis during walking. In addition, the number of steps, distance, energy expenditure, and heart rate for 30 min during the exercise sessions were recorded.ResultsA significant increase in the maximum voluntary contraction (MVC) of the left biceps femoris (BF) was evident in the interval group, while significant changes in the MVC of the bilateral BF were seen in the power group after Bot Fit exercise. A significant decrease of muscle effort in the right BF in the interval group and right lumbar erector spinae and bilateral BF in the power group were also observed. In addition, the symmetry index of pelvic tilt significantly improved in the interval group, and greater exercise volume and intensity in both the interval and power groups compared with the control group were confirmed as measured by the number of steps, distance, energy expenditure, and heart rate.ConclusionsThe results of this study confirmed the beneficial effect of programed walking exercise using the Bot Fit on muscle strength of trunk and lower extremities, muscle effort, and pelvic movement symmetry in younger adults. Personalized exercise programs can be provided for younger adults using various resistance or assistance modes of robotic device with the Bot Fit.Trial RegistrationClinicalTrials.gov, NCT05862077. Registered 22 March 2022, https://register.clinicaltrials.gov/.

Kinematic-Muscular Synergies Describe Human Locomotion with a Set of Functional Synergies.

Kinematics, kinetics and biomechanics of human gait are widely investigated fields of research. The biomechanics of locomotion have been described as characterizing muscle activations and synergistic control, i.e., spatial and temporal patterns of coordinated muscle groups and joints. Both kinematic synergies and muscle synergies have been extracted from locomotion data, showing that in healthy people four-five synergies underlie human locomotion; such synergies are, in general, robust across subjects and might be altered by pathological gait, depending on the severity of the impairment. In this work, for the first time, we apply the mixed matrix factorization algorithm to the locomotion data of 15 healthy participants to extract hybrid kinematic-muscle synergies and show that they allow us to directly link task space variables (i.e., kinematics) to the neural structure of muscle synergies. We show that kinematic-muscle synergies can describe the biomechanics of motion to a better extent than muscle synergies or kinematic synergies alone. Moreover, this study shows that at a functional level, modular control of the lower limb during locomotion is based on an increased number of functional synergies with respect to standard muscle synergies and accounts for different biomechanical roles that each synergy may have within the movement. Kinematic-muscular synergies may have impact in future work for a deeper understanding of modular control and neuro-motor recovery in the medical and rehabilitation fields, as they associate neural and task space variables in the same factorization. Applications include the evaluation of post-stroke, Parkinson's disease and cerebral palsy patients, and for the design and development of robotic devices and exoskeletons during walking.

Monitored and Cared for at Home? Privacy Concerns When Using Smart Home Health Technologies to Care for Older Persons

Background States and families are facing growing challenges provide adequate care for older persons. Smart home health technologies (SHHTs) in the forms of sensor or robotic devices have been discussed as technical solutions for caregiving. Ethical and social concerns are raised with the use of such technologies for caregiving purposes, a particularly prominent one being privacy. This paper contributes to the literature by distinguishing privacy concerns into both the type of technologies and conceptual dimensions. Methods Data for this paper stem from sixty semi-structured interviews with older persons, informal, and formal caregivers living in the German-speaking regions of Switzerland. All information related to privacy, that were initially inductively coded, were thematically sorted into four dimensions of privacy (physical, psychological, social, and informational) and by the type of technologies studied. Results Participants were especially concerned about privacy intrusions from smart wearables and ambient sensors than robotic technologies, which may be due to the relative lack of familiarity with the latter. Informational privacy was evident in the context of data collection capacities and potential for misuses of data. The installation and implementation of both visual and ambient sensors induced discomfort to their senses of physical space. Alerts of smart wearables and obtrusive sightings of SHHTs garnered worries related to stigmatization and manipulation, indicating intrusions into end-users’ psychological privacy. Little discussions of social dimensions of privacy were evident in the data, even toward robotic technologies for their functions to promote social interactions for older persons. Conclusions This paper is one of the first that use the stratification approach on empirical data to highlight the multi-faceted privacy concerns when technologies may be implemented in elder care. Our paper could thus supports potential end-users in deciding which technologies to use and how to balance different privacy concerns against other values that they may hold important.

Design, Analysis, and Optimization Testing of a Novel Modular Walking Device for Pipeline Robots

This article investigates the limitations associated with traditional wheel-type pipeline walking devices, which are characterized by a single movement mode and an inability to navigate complex or irregular pipeline structures. A modular walking device (MWD) designed for pipeline robots was developed utilizing structural and mechanical analysis techniques. The reliability of the mechanical analysis was validated through single-factor dynamic testing. To analyze and optimize the factors influencing the maneuverability and obstacle-crossing capabilities of the MWD, a three-factor, three-level orthogonal testing method was utilized. The factors examined included the rotational speed of the walking wheel (RS), the pre-tightening force of the wheel brackets (PF), and the height of the annular obstacle (OH). The evaluation metrics used were the slip rate and passability. The results indicated that a parameter combination of RS at 70 rpm, PF at 30 N, and OH at 10 mm produced a slip rate of 11.6% ± 1.5%. During the obstacle traversal process, the remainder of the device maintained a safe distance from the obstacles, with only the walking wheel making contact. The verification testing also confirmed that the MWD is capable of executing three distinct modes of motion: rectilinear, rotational, and helical. The MWD designed and developed in this study can switch between multiple motion modes and successfully overcome obstacles within 15 mm, providing a new equipment for universities to enhance mechanized pipeline detection technology.

Application of a Dual Upper Limb Task-Oriented Robotic System for the Functional Recovery of the Upper Limb in Stroke Patients.

Highly repetitive and task-oriented training has been shown to promote the recovery of limb function in stroke patients. Additionally, bilateral arm training can help stroke survivors regain their upper limb function and improve their daily activities. The dual upper limb task-oriented robotic system is designed to assist the healthy side of the stroke patient in driving the affected side to perform bilateral arm training through the use of a robotic device. It can also guide the patient in carrying out dual upper limb coordinated movements and engage them in a task-oriented virtual game using force feedback and human-computer interaction technology. This study aimed to assess the efficacy of the system in enhancing upper limb function and activities of daily living in stroke patients. The assessment methods used included motor evoked potential (MEP), functional test for the hemiplegic upper extremity-Hong Kong (FTHUE-HK), Fugl-Meyer Assessment Upper Extremity Scale (FMA-UE), and modified Barthel index (MBI). The results of the study indicate that the dual upper limb task-oriented robotic system can significantly improve the corticospinal pathway, upper limb function, and activities of daily living in stroke patients after 6 weeks of treatment. This system can serve as an effective adjunct to upper limb functional rehabilitation in stroke survivors, reducing the dependence on rehabilitation therapists. In conclusion, the dual upper limb task-oriented robotic system provides a new strategy for post-stroke limb functional rehabilitation and holds great potential for application, as it offers certain social and financial benefits.

Improving manual dexterity using ergonomic wearable glove in patients with multiple sclerosis: A quasi-randomized clinical trial

One main problem faced by people with multiple sclerosis (PwMS) is upper limb dysfunction, which can occur in the first decade of the disease and with the highest prevalence of disability in the progressive type of the disease. Then, PwMS may benefit from personalised and intensive treatment as provided by robotic devices. These innovative devices have increasingly been brought into the neurorehabilitation field, due to their ability to provide repetitive and task-oriented training. In this quasi-randomized study, we aim to evaluate the effects of robotic-assisted hand training, using the Hand TutorTM device, on hand functionality, active RoM, and manual dexterity, compared to conventional rehabilitation in PwMS. We enrolled 30 MS patients, who received 20 training sessions, each lasting 45 min with robotic-assisted hand training with Hand Tutor (n 15, experimental group) or conventional rehabilitation therapy (n 15, control group). All patients were evaluated at pre- and post-intervention with clinical scales for upper limb functionality (DASH, BBT, NHPT, and MI). In addition, only patients in the experimental group received an objective kinematic analysis of the hand and wrist movements, delivered by the Hand Tutor glove, both pre- and post-intervention. We found that PwMS in both groups statistically improved their upper limb functions, however the experimental group achieved better results in terms of manual dexterity. This promising rehabilitation training with Hand Tutor glove led to positive effects on upper limbs motor outcomes and kinematic parameters in patients with MS.

Propulsive efficiency of spatiotemporally asymmetric oscillating appendages at intermediate Reynolds numbers

Many organisms use flexible appendages for locomotion, feeding, and other functional behaviors. The efficacy of these behaviors is determined in large part by the fluid dynamics of the appendage interacting with its environment. For oscillating appendages at low Reynolds numbers, viscosity dominates over inertia, and appendage motion must be spatially asymmetric to generate net flow. At high Reynolds numbers, viscous forces are negligible and appendage motion is often also temporally asymmetric, with a fast power stroke and a slow recovery stroke; such temporal asymmetry does not affect the produced flow at low Reynolds numbers. At intermediate Reynolds numbers, both viscous and inertial forces play non-trivial roles---correspondingly, both spatial and temporal asymmetry can strongly affect overall propulsion. Here we perform experiments on three robotic paddles with different material flexibilities and geometries, allowing us to explore the effects of motion asymmetry (both spatial and temporal) on force production. We show how a flexible paddle's time-varying shape throughout the beat cycle can reorient the direction of the produced force, generating both thrust and lift. We also evaluate the propulsive performance of the paddle by introducing a new quantity, which we term "integrated efficiency". This new definition of propulsive efficiency can be used to directly evaluate an appendage's performance independently from full-body swimming dynamics. Use of the integrated efficiency allows for accurate performance assessment, generalization, and comparison of oscillating appendages in both robotic devices and behaving organisms. Finally, we show that a curved flexible paddle generates thrust more efficiently than a straight paddle, and produces spatially asymmetric motion---thereby improving performance---without the need for complex actuation and controls, opening new avenues for bioinspired technology development.

The Use of Remote Presence Robotic Tele-Presentation in Rural and Remote Canada: A Systematic Review.

Objective: One potential solution to limited health care in rural and remote regions is remote presence robotic tele-presentation to allow health care providers to care for patients in their home community via a robotic interface. We synthesized evidence regarding the use of remote presence robotic tele-presentation in rural and/or remote Canadian health settings. Methods: Medline, PubMed, and Embase were searched up to August 2023. Remote presence robotic tele-presentation refers to any robotic device used for the purpose of presenting and/or collecting patient information. Primary research was included if the patient was located in remote and/or rural Canada, featured remote presence robotic tele-presentation, and assessed patient, family, or clinician satisfaction, patient transport to nearby regional or urban center, health care costs, clinical outcomes, infrastructure outcomes, adverse events, or telementoring. Results: Six studies were included. Patients, nurses, and physicians all reported high levels of satisfaction when using the remote presence robotic tele-presentation. Fifty to sixty-three percent of patients were managed in their home community and did not require transfer to another center. Remote presence robotic sonography resulted in adequate imaging in 81% of first trimester ultrasound limited exams but was less useful for second trimester complete obstetric ultrasounds (20% adequate imaging). Two of eight laparoscopic colorectal surgeries had to be converted to open surgeries. Telerobotic ultrasound clinics resulted in a diagnosis in 70% of cases. Conclusions: Evidence suggests remote presence robotic tele-presentation is a safe and cost-effective approach to providing care in distant communities and can prevent some transfers and evacuations to tertiary hospitals.

Clinical Applications and Future Translation of Somatosensory Neuroprostheses.

Somatosensory neuroprostheses restore, replace, or enhance tactile and proprioceptive feedback for people with sensory impairments due to neurological disorders or injury. Somatosensory neuroprostheses typically couple sensor inputs from a wearable device, prosthesis, robotic device, or virtual reality system with electrical stimulation applied to the somatosensory nervous system via noninvasive or implanted interfaces. While prior research has mainly focused on technology development and proof-of-concept studies, recent acceleration of clinical studies in this area demonstrates the translational potential of somatosensory neuroprosthetic systems. In this review, we provide an overview of neurostimulation approaches currently undergoing human testing and summarize recent clinical findings on the perceptual, functional, and psychological impact of somatosensory neuroprostheses. We also cover current work toward the development of advanced stimulation paradigms to produce more natural and informative sensory feedback. Finally, we provide our perspective on the remaining challenges that need to be addressed prior to translation of somatosensory neuroprostheses.

EMG and SSVEP-based bimodal estimation of elbow angle trajectory

Detecting intentions and estimating movement trajectories in a human–machine interface (HMI) using electromyogram (EMG) signals is particularly challenging, especially for individuals with movement impairments. Therefore, incorporating additional information from other biological sources, potential discrete information in the movement, and the EMG signal can be practical. This study combined EMG and target information to enhance estimation performance during reaching movements. EMG activity of the shoulder and arm muscles, elbow angle, and the electroencephalogram signals of ten healthy subjects were recorded while they reached blinking targets. The reaching target was recognized by steady-state visual evoked potential (SSVEP). The selected target’s final angle and EMG were then mapped to the elbow angle trajectory. The proposed bimodal structure, which integrates EMG and final elbow angle information, outperformed the EMG-based decoder. Even under conditions of higher fatigue, the proposed structure provided better performance than the EMG decoder. Including additional information about the recognized reaching target in the trajectory model improved the estimation of the reaching profile. Consequently, this study’s findings suggest that bimodal decoders are highly beneficial for enhancing assistive robotic devices and prostheses, especially for real-time upper limb rehabilitation.

Development of a robotic wheel door opener system assistive device

Physical disabilities significantly impact individuals' ability to perform activities of daily living (ADL), leading to reduced autonomy and difficulty to accomplish daily living tasks. One such barrier is the difficulty or inability to open doors, preventing access to different rooms in their residence (bathroom, bedroom, etc.), rooms at work, or shopping areas. Existing solutions, such as robotic arms on wheelchairs and door openers mounted at the top of doors, remain expensive, complex to install, and relatively difficult for the target population to use. Addressing this challenge, this study introduces a Robotic Wheel Door Opener System (RWDOS) designed to facilitate the opening and closing of the door. The RWDOS is installed at the bottom of a door and is controlled remotely through a smartphone application. The paper presents the mechanical design and control system along with a cost analysis. It concludes with initial results and outlines the future directions for the project.

Development and research of an autonomous mobile platform with reduced computing power requirements

Today, the market is saturated with a variety of autonomous robotic devices that offer a variety of solutions to opti-mize workflows in various industries. One of the leading areas of their application is the automation of warehouse operations, where store robots move and optimize warehouse processes, reducing labor costs and speeding up task completion. These technologies reveal some limitations and shortcomings. For example, categories of robots such as transport carts, forklifts, and automated towing vehicles are limited in their functionality, often resulting in the need to use multiple types of devices for different tasks. This leads to equipment redundancy and complicates integration into existing warehouse systems. Another significant aspect is the need to improve the routing and nav-igation algorithms for these devices. Modern autonomous robot systems often face route optimization challenges, especially in dynamic and complex warehouse environments. This can lead to inefficiencies and increased time delays [1]. The goal of this work is to develop an autonomous mobile platform that would solve possible problems with navigation, have well-developed routing algorithms combined with low cost for affordable use in small busi-nesses. The research methods involve conducting various experiments on a real mobile platform to collect data and evaluate performance, including measuring the speed, accuracy, and power consumption of transportation tasks. Development and optimization of new algorithms for managing a mobile platform, planning routes, analyz-ing signals from sensors, processing images and video from a camera. The result of the work is that the possibility of compatibility of the on-board computer (single board computer) with the flight controller for movement on the ground surface has been investigated. On this basis, a mobile platform was created, which is presented in this arti-cle. This configuration is suitable for moving the platform either autonomously or using a control panel. The role of the technical vision system in providing navigation has been studied. The results of the work highlight innovation and the use of model functionality to create effective autonomous land navigation systems, including coordinates. The mobile platform can be used for transporting goods in warehouses, for working in extreme situations, for environmental monitoring or for educational purposes.

Использование робот-ассистированных трепан-биопсий забрюшинных опухолевидных образований под контролем мультиспиральной компьютерной томографии

Various types of tumors, both benign and malignant, can be localized in the retroperitoneal space, which can develop not only in retroperitoneal organs, but also originate from nerves, connective or lymphatic tissue. Their pathomorphological diagnosis is relevant for the appointment of adequate treatment. There is a technique of percutaneous core-biopsy of such formations under the control of multispiral computed tomography, most often carried out by the "free hand" method. However, high radiation exposure not only to the patient, but also to the interventionist doctor are its negative sides. The author has developed a robotic device that automatically inserts a biopsy needle into the "place of interest". It was used for diagnostic punctures in the retroperitoneal space in 24 patients. In the control retrospective group, punctures were performed using the "free hand" method in 20 patients. The authors reveal an enhancement of the accuracy of puncture in the main group, a reduction in the amount of complications and of the duration of manipulation. The latter, along with the exclusion of radiation exposure to medical personnel, made it possible to reduce it on the subject.

Enhancing stroke rehabilitation with whole-hand haptic rendering: development and clinical usability evaluation of a novel upper-limb rehabilitation device

IntroductionThere is currently a lack of easy-to-use and effective robotic devices for upper-limb rehabilitation after stroke. Importantly, most current systems lack the provision of somatosensory information that is congruent with the virtual training task. This paper introduces a novel haptic robotic system designed for upper-limb rehabilitation, focusing on enhancing sensorimotor rehabilitation through comprehensive haptic rendering.MethodsWe developed a novel haptic rehabilitation device with a unique combination of degrees of freedom that allows the virtual training of functional reach and grasp tasks, where we use a physics engine-based haptic rendering method to render whole-hand interactions between the patients’ hands and virtual tangible objects. To evaluate the feasibility of our system, we performed a clinical mixed-method usability study with seven patients and seven therapists working in neurorehabilitation. We employed standardized questionnaires to gather quantitative data and performed semi-structured interviews with all participants to gain qualitative insights into the perceived usability and usefulness of our technological solution.ResultsThe device demonstrated ease of use and adaptability to various hand sizes without extensive setup. Therapists and patients reported high satisfaction levels, with the system facilitating engaging and meaningful rehabilitation exercises. Participants provided notably positive feedback, particularly emphasizing the system’s available degrees of freedom and its haptic rendering capabilities. Therapists expressed confidence in the transferability of sensorimotor skills learned with our system to activities of daily living, although further investigation is needed to confirm this.ConclusionThe novel haptic robotic system effectively supports upper-limb rehabilitation post-stroke, offering high-fidelity haptic feedback and engaging training tasks. Its clinical usability, combined with positive feedback from both therapists and patients, underscores its potential to enhance robotic neurorehabilitation.

Performance of Organic Electrochemical Transistors with Ionic Liquid Crystal Elastomers as Solid Electrolytes.

Organic electrochemical transistors (OECTs) have emerged as attractive devices for bioelectronics, wearable electronics, soft robotics, and energy storage devices. The electrolyte, being a fundamental component of OECTs, plays a crucial role in their performance. Recently, it has been demonstrated that ionic liquid crystal elastomers (iLCEs) can be used as a solid electrolyte for OECTs. Their capabilities, however, have only been shown for relatively large size substrate-free OECTs. Here, we study the influence of the different alignments of iLCEs on steady state and transient behavior of OECTs using a lateral geometry with source, drain, and gate in the same plane. We achieve excellent electrical response with an ON/OFF switching ratio of >105 and minimal leakage current. The normalized maximum transconductance gm/w of the most sensitive iLCE was found to be 33 S m-1, which is one of the highest among all solid-state-based OECTs reported so far. Additionally, iLCEs show high stability and can be removed and reattached multiple times to the same OECT device without decreasing performance.

On human-in-the-loop optimization of human-robot interaction.

From industrial exoskeletons to implantable medical devices, robots that interact closely with people are poised to improve every aspect of our lives. Yet designing these systems is very challenging; humans are incredibly complex and, in many cases, we respond to robotic devices in ways that cannot be modelled or predicted with sufficient accuracy. A new approach, human-in-the-loop optimization, can overcome these challenges by systematically and empirically identifying the device characteristics that result in the best objective performance for a specific user and application. This approach has enabled substantial improvements in human-robot performance in research settings and has the potential to speed development and enhance products. In this Perspective, we describe methods for applying human-in-the-loop optimization to new human-robot interaction problems, addressing each key decision in a variety of contexts. We also identify opportunities to develop new optimization techniques and answer underlying scientific questions. We anticipate that our readers will advance human-in-the-loop optimization and use it to design robotic devices that truly enhance the human experience.