Publications

Astronauts are at risk for pneumothorax, a condition where injury or disease introduces air between the chest wall and the lungs (i.e., the pleural cavity). In a worst-case scenario, it can rapidly lead to a fatality if left unmanaged and will require prompt treatment in situ if developed during spaceflight. Chest tube insertion is the definitive treatment for pneumothorax, but it requires a high level of skill and frequent practice for safe use. Physician astronauts may struggle to maintain this skill on medium- and long-duration exploration-class missions, and it is inappropriate for pure just-in-time learning or skill refreshment paradigms. This paper proposes semi-automating tool insertion to reduce the risk of complications in austere environments and describes preliminary experiments providing initial validation of an intelligent prototype system. Specifically, we showcase and analyse motion and force recordings from a sensorized percutaneous access needle inserted repeatedly into an ex vivo tissue phantom, along with relevant physiological data simultaneously recorded from the operator. When coupled with minimal just-in-time training and/or augmented reality guidance, the proposed system may enable non-expert operators to safely perform emergency chest tube insertion without the use of ground resources.

Surgery, typically seen as the surgeon's sole responsibility, requires a broader perspective acknowledging the vital roles of other operating room (OR) personnel. The interactions among team members are crucial for delivering quality care and depend on shared situation awareness. I propose a two-phase approach to design and evaluate a multimodal platform that monitors OR members, offering insights into surgical procedures. The first phase focuses on designing a data-collection platform, tailored to surgical constraints, to generate novel collaboration and situation-awareness metrics using synchronous recordings of the participants' voices, positions, orientations, electrocardiograms, and respiration signals. The second phase concerns the creation of intuitive dashboards and visualizations, aiding surgeons in reviewing recorded surgery, identifying adverse events and contributing to proactive measures. This work aims to demonstrate an innovative approach to data collection and analysis, augmenting the surgical team's capabilities. The multimodal platform has the potential to enhance collaboration, foster situation awareness, and ultimately mitigate surgical adverse events. This research sets the stage for a transformative shift in the OR, enabling a more holistic and inclusive perspective that recognizes that surgery is a team effort.

When teaching or coaching, humans augment their words with carefully timed hand gestures, head and body movements, and facial expressions to provide feedback to their students. Robots, however, rarely utilize these nuanced cues. A minimally supervised social robot equipped with these abilities could support people in exercising, physical therapy, and learning new activities. This thesis examines how the intuitive power of human gestures can be harnessed to enhance human-robot interaction. To address this question, this research explores gesture-based interactions to expand the capabilities of a socially assistive robotic exercise coach, investigating the perspectives of both novice users and exercise-therapy experts. This thesis begins by concentrating on the user's engagement with the robot, analyzing the feasibility of minimally supervised gesture-based interactions. This exploration seeks to establish a framework in which robots can interact with users in a more intuitive and responsive manner. The investigation then shifts its focus toward the professionals who are integral to the success of these innovative technologies: the exercise-therapy experts. Roboticists face the challenge of translating the knowledge of these experts into robotic interactions. We address this challenge by developing a teleoperation algorithm that can enable exercise therapists to create customized gesture-based interactions for a robot. Thus, this thesis lays the groundwork for dynamic gesture-based interactions in minimally supervised environments, with implications for not only exercise-coach robots but also broader applications in human-robot interaction.

Causal inference could give future learning robots strong generalization and scalability capabilities, which are crucial for safety, fault diagnosis and error prevention. One application area of interest consists of the haptic recognition of surfaces. We seek to understand cause and effect during physical surface interaction by examining surface and tool identity, their interplay, and other contact-irrelevant factors. To work toward elucidating the mechanism of surface encoding, we attempt to recognize surfaces from haptic-auditory data captured by previously unseen hemispherical steel tools that differ from the recording tool in diameter and mass. In this context, we leverage ideas from kernel methods to quantify surface similarity through descriptive differences in signal distributions. We find that the effect of the tool is significantly present in higher-order statistical moments of contact data: aligning the means of the distributions being compared somewhat improves recognition but does not fully separate tool identity from surface identity. Our findings shed light on salient aspects of haptic-auditory data from tool-surface interaction and highlight the challenges involved in generalizing artificial surface discrimination capabilities.

We present a shared control framework for teleoperation that combines the human and autonomous robot agents operating in different dimension spaces. The shared control problem is an optimization problem to maximize the human's internal action-value function while guaranteeing that the shared control policy is close to the autonomous robot policy. This results in a state update rule that augments the human controls using the Riemannian metric that emerges from computing the curvature of the robot's value function to account for any cost terms or constraints that the human operator may neglect when operating a redundant manipulator. In our experiments, we apply Linear Quadratic Regulators to locally approximate the robot policy using a single optimized robot trajectory, thereby preventing the need for an optimization step at each time step to determine the optimal policy. We show preliminary results of reach-and-grasp teleoperation tasks with a simulated human policy and a pilot user study using the VR headset and controllers. However, the mixed user preference ratings and quantitative results show that more investigation is required to prove the efficacy of the proposed paradigm.

Surgeons cannot directly touch the patient's tissue in robot-assisted minimally invasive procedures. Instead, they must palpate using instruments inserted into the body through trocars. This way of operating largely prevents surgeons from using haptic cues to localize visually undetectable structures such as tumors and blood vessels, motivating research on direct and indirect force sensing. We propose an indirect force-sensing method that combines monocular images of the operating field with measurements from IMUs attached externally to the instrument shafts. Our method is thus suitable for various robotic surgery systems as well as laparoscopic surgery. We collected a new dataset using a da Vinci Si robot, a force sensor, and four different phantom tissue samples. The dataset includes 230 one-minute-long recordings of repeated bimanual palpation tasks performed by four lay operators. We evaluated several network architectures and investigated the role of the network inputs. Using the DenseNet vision model and including inertial data best-predicted palpation forces (lowest average root-mean-square error and highest average coefficient of determination). Ablation studies revealed that video frames carry significantly more information than inertial signals. Finally, we demonstrated the model's ability to generalize to unseen tissue and predict shear contact forces.

Intelligent interaction with the physical world requires perceptual abilities beyond vision and hearing; vibrant tactile sensing is essential for autonomous robots to dexterously manipulate unfamiliar objects or safely contact humans. Therefore, robotic manipulators need high-resolution touch sensors that are compact, robust, inexpensive, and efficient. The soft vision-based haptic sensor presented herein is a miniaturized and optimized version of the previously published sensor Insight. Minsight has the size and shape of a human fingertip and uses machine learning methods to output high-resolution maps of 3D contact force vectors at 60 Hz. Experiments confirm its excellent sensing performance, with a mean absolute force error of 0.07 N and contact location error of 0.6 mm across its surface area. Minsight's utility is shown in two robotic tasks on a 3-DoF manipulator. First, closed-loop force control enables the robot to track the movements of a human finger based only on tactile data. Second, the informative value of the sensor output is shown by detecting whether a hard lump is embedded within a soft elastomer with an accuracy of 98\%. These findings indicate that Minsight can give robots the detailed fingertip touch sensing needed for dexterous manipulation and physical human–robot interaction.

Robots are increasingly being developed as assistants for household, education, therapy, and care settings. Such robots can use adaptive emotional behavior to communicate warmly and effectively with their users and to encourage interest in extended interactions. However, autonomous physical robots often lack a dynamic internal emotional state, instead displaying brief, fixed emotion routines to promote specific user interactions. Furthermore, despite the importance of social touch in human communication, most commercially available robots have limited touch sensing, if any at all. We propose that users' perceptions of a social robotic system will improve when the robot provides emotional responses on both shorter and longer time scales (reactions and moods), based on touch inputs from the user. We evaluated this proposal through an online study in which 51 diverse participants watched nine randomly ordered videos (a three-by-three full-factorial design) of the koala-like robot HERA being touched by a human. Users provided the highest ratings in terms of agency, ambient activity, enjoyability, and touch perceptivity for scenarios in which HERA showed emotional reactions and either neutral or emotional moods in response to social touch gestures. Furthermore, we summarize key qualitative findings about users' preferences for reaction timing, the ability of robot mood to show persisting memory, and perception of neutral behaviors as a curious or self-aware robot.

The sophistication of biological sensing and transduction processes during finger-surface and tool-surface interaction is remarkable, enabling humans to perform ubiquitous tasks such as discriminating and manipulating surfaces. Capturing and processing these rich contact-elicited signals during surface exploration with similar success is an important challenge for artificial systems. Prior research introduced sophisticated mobile surface-sensing systems, but it remains less clear what quality, resolution and acuity of sensor data are necessary to perform human tasks with the same efficiency and accuracy. In order to address this gap in our understanding about artificial surface perception, we have designed a novel auditory-haptic test bed. This study aims to inspire new designs for artificial sensing tools in human-machine and robotic applications.

Telerobotics is regularly used on construction sites to build large structures efficiently. A human operator remotely controls the construction robot under direct visual feedback, but visibility is often poor. Future construction robots that move autonomously will also require operator monitoring. Thus, we designed a wireless haptic feedback system to provide the operator with task-relevant mechanical information from a construction robot in real time. Our AiroTouch system uses an accelerometer to measure the robot end-effector's vibrations and uses off-the-shelf audio equipment and a voice-coil actuator to display them to the user with high fidelity. A study was conducted to evaluate how this type of naturalistic vibration feedback affects the observer's understanding of telerobotic assembly on a real construction site. Seven adults without construction experience observed a mix of manual and autonomous assembly processes both with and without naturalistic vibrotactile feedback. Qualitative analysis of their survey responses and interviews indicated that all participants had positive responses to this technology and believed it would be beneficial for construction activities.

Wearable haptic devices can provide salient real-time feedback (typically vibration) for rehabilitation, sports training, and skill acquisition. Although the body provides many sites for such cues, the influence of the mounting location on vibrotactile mechanics is commonly ignored. This study builds on previous research by quantifying how changes in strap tightness and local tissue composition affect the physical acceleration generated by a typical vibrotactile device.

Haptic displays act on the user's body to stimulate the sense of touch and enrich applications from gaming and computer-aided design to rehabilitation and remote surgery. However, when crafted from typical rigid robotic components, they tend to be heavy, bulky, and expensive, while sleeker designs often struggle to create clear haptic cues. This article introduces a lightweight wearable silicone finger sheath that can deliver salient and rich vibrotactile cues using electromagnetic actuation. We fabricate the sheath on a ferromagnetic mandrel with a process based on dip molding, a robust fabrication method that is rarely used in soft robotics but is suitable for commercial production. A miniature rare-earth magnet embedded within the silicone layers at the center of the finger pad is driven to vibrate by the application of alternating current to a nearby air-coil. Experiments are conducted to determine the amplitude of the magnetic force and the frequency response function for the displacement amplitude of the magnet perpendicular to the skin. In addition, high-fidelity finite element analyses of the finger wearing the device are performed to investigate the trends observed in the measurements. The experimental and simulated results show consistent dynamic behavior from 10 to 1000 Hz, with the displacement decreasing after about 300 Hz. These results match the detection threshold profile obtained in a psychophysical study performed by 17 users, where more current was needed only at the highest frequency. A cue identification experiment and a demonstration in virtual reality validate the feasibility of this approach to fingertip haptics.

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. Thirty-two users each exchanged and rated sixteen 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 sixteen 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.

Sign language (SL) is the primary method of communication for the 70 million Deaf people around the world. Video dictionaries of isolated signs are a core SL learning tool. Replacing these with 3D avatars can aid learning and enable AR/VR applications, improving access to technology and online media. However, little work has attempted to estimate expressive 3D avatars from SL video; occlusion, noise, and motion blur make this task difficult. We address this by introducing novel linguistic priors that are universally applicable to SL and provide constraints on 3D hand pose that help resolve ambiguities within isolated signs. Our method, SGNify, captures fine-grained hand pose, facial expression, and body movement fully automatically from in-the-wild monocular SL videos. We evaluate SGNify quantitatively by using a commercial motion-capture system to compute 3D avatars synchronized with monocular video. SGNify outperforms state-of-the-art 3D body-pose- and shape-estimation methods on SL videos. A perceptual study shows that SGNify's 3D reconstructions are significantly more comprehensible and natural than those of previous methods and are on par with the source videos. Code and data are available at sgnify.is.tue.mpg.de.

This work investigates real-time 3D surface reconstruction for minimally invasive surgery. Specifically, we analyze depth sensing through laser-based time-of-flight sensing (lidar) and stereo endoscopy on ex-vivo porcine tissue samples. When compared to modern learning-based stereo matching from endoscopic images, lidar achieves lower processing delay, higher frame rate, and superior robustness against sensor distance and poor illumination. Furthermore, we report on the negative effect of near-infrared light penetration on the accuracy of time-of-flight measurements across different tissue types.

Sliding a finger or tool along a surface generates rich haptic and auditory contact signals that encode properties crucial for manipulation, such as friction and hardness. To engage in contact-rich manipulation, future robots would benefit from having surface-characterization capabilities similar to humans, but the optimal sensing configuration is not yet known. Thus, we developed a test bed for capturing high-quality measurements as a human touches surfaces with different tools: it includes optical motion capture, a force/torque sensor under the surface sample, high-bandwidth accelerometers on the tool and the fingertip, and a high-fidelity microphone. After recording data from three tool diameters and nine surfaces, we describe a surface-classification pipeline that uses the maximum mean discrepancy (MMD) to compare newly gathered data to each surface in our known library. The results achieved under several pipeline variations are compared, and future investigations are outlined.

This paper presents a real-time optimization-based algorithm for mapping motion between two kinematically dissimilar serial linkages, such as a human arm and a robot arm. OCRA can be customized based on the target task to weight end-effector orientation versus the configuration of the central line of the arm, which we call the skeleton. A video-watching study (N=70) demonstrated that when this algorithm considers both the hand orientation and the arm skeleton, it creates robot arm motions that users perceive to be highly similar to those of the human operator, indicating OCRA would be suitable for telerobotics and telepresence through avatars.

Background: Several automated skill-assessment approaches have been proposed for robotic surgery, but their utility is not well understood. This article investigates the effects of one machine-learning-based skill-assessment approach on psychomotor skill development in robotic surgery training. Methods: N=29 trainees (medical students and residents) with no robotic surgery experience performed five trials of inanimate peg transfer with an Intuitive Surgical da Vinci Standard robot. Half of the participants received no post-trial feedback. The other half received automatically calculated scores from five Global Evaluative Assessment of Robotic Skill (GEARS) domains post-trial. Results: There were no significant differences between the groups regarding overall improvement or skill improvement rate. However, participants who received post-trial feedback rated their overall performance improvement significantly lower than participants who did not receive feedback. Conclusions: These findings indicate that automated skill evaluation systems might improve trainee selfawareness but not accelerate early-stage psychomotor skill development in robotic surgery training.

Grounded force-feedback (GFF) devices are an established and diverse class of haptic technology based on robotic arms. However, the number of designs and how they are specified make comparing devices difficult. We thus present Haptify, a benchmarking system that can thoroughly, fairly, and noninvasively evaluate GFF haptic devices. The user holds the instrumented device end-effector and moves it through a series of passive and active experiments. Haptify records the interaction between the hand, device, and ground with a seven-camera optical motion-capture system, a 60-cm-square custom force plate, and a customized sensing end-effector. We demonstrate six key ways to assess GFF device performance: workspace shape, global free-space forces, global free-space vibrations, local dynamic forces and torques, frictionless surface rendering, and stiffness rendering. We then use Haptify to benchmark two commercial haptic devices. With a smaller workspace than the 3D Systems Touch, the more expensive Touch X outputs smaller free-space forces and vibrations, smaller and more predictable dynamic forces and torques, and higher-quality renderings of a frictionless surface and high stiffness.

The human body has the tremendous capacity to learn a new way of walking that reduces its risk of musculoskeletal disease progression. Wearable haptic biofeedback has been used to guide gait retraining in patients with knee osteoarthritis, enabling reductions in pain and improvement in function. However, this promising therapy is not yet a part of standard clinical practice. Here, I propose a two-pronged approach to improving the design and deployment of biofeedback for gait retraining. The first section concerns prescription, with the aim of providing clinicians with an interpretable model of gait retraining outcome in order to best guide their treatment decisions. The second section concerns learning, by examining how internal physiological state and external environmental factors influence the process of learning a therapeutic gait. This work aims to address the challenges keeping a highly promising intervention from being widely used to maintain pain-free mobility throughout the lifespan.

Robots are increasingly being developed as assistants for household, education, therapy, and care settings. Such robots need social skills to interact warmly and effectively with their users, as well as adaptive behavior to maintain user interest. While complex emotion models exist for chat bots and virtual agents, autonomous physical robots often lack a dynamic internal affective state, instead displaying brief, fixed emotion routines to promote or discourage specific user actions. We address this need by creating a mathematical emotion model that can easily be implemented in a social robot to enable it to react intelligently to external stimuli. The robot's affective state is modeled as a second-order dynamic system analogous to a mass connected to ground by a parallel spring and damper. The present position of this imaginary mass shows the robot's valence, which we visualize as the height of its displayed smile (positive) or frown (negative). Associating positive and negative stimuli with appropriately oriented and sized force pulses applied to the mass enables the robot to respond to social touch and other inputs with a valence that evolves over a longer timescale, capturing essential features of approach-avoidance theory. By adjusting the parameters of this emotion model, one can modify three main aspects of the robot's personality, which we term disposition, stoicism, and calmness.

Screen-based pedestrian navigation assistance can be distracting or inaccessible to users. Shape-changing haptic interfaces can overcome these concerns. The S-BAN is a new handheld haptic interface that utilizes a parallel kinematic structure to deliver 2-DOF spatial information over a continuous workspace, with a form factor suited to integration with other travel aids. The ability to pivot, extend and retract its body opens possibilities and questions around spatial data representation. We present a static study to understand user perception of absolute pose and relative motion for two spatial mappings, showing highest sensitivity to relative motions in the cardinal directions. We then present an embodied navigation experiment in virtual reality. User motion efficiency when guided by the S-BAN was statistically equivalent to using a vision-based tool (a smartphone proxy). Although haptic trials were slower than visual trials, participants' heads were more elevated with the S-BAN, allowing greater visual focus on the environment.

Electrical resistance tomography (ERT) can be used to create large-scale soft tactile sensors that are flexible and robust. Good performance requires a fast and accurate mapping from the sensor's sequential voltage measurements to the distribution of force across its surface. However, particularly with multiple contacts, this task is challenging for both previously developed approaches: physics-based modeling and end-to-end data-driven learning. Some promising results were recently achieved using sim-to-real transfer learning, but estimating multiple contact locations and accurate contact forces remains difficult because simulations tend to be less accurate with a high number of contact locations and/or high force. This paper introduces a modular hybrid method that combines simulation data synthesized from an electromechanical finite element model with real measurements collected from a new ERT-based tactile sensor. We use about 290,000 simulated and 90,000 real measurements to train two deep neural networks: the first (Transfer-Net) captures the inevitable gap between simulation and reality, and the second (Recon-Net) reconstructs contact forces from voltage measurements. The number of contacts, contact locations, force magnitudes, and contact diameters are evaluated for a manually collected multi-contact dataset of 150 measurements. Our modular pipeline's results outperform predictions by both a physics-based model and end-to-end learning.

Individuals who use myoelectric upper-limb prostheses often rely heavily on vision to complete their daily activities. They thus struggle in situations where vision is overloaded, such as multitasking, or unavailable, such as poor lighting conditions. Able-bodied individuals can easily accomplish such tasks due to tactile reflexes and haptic sensation guiding their upper-limb motor coordination. Based on these principles, we developed and tested two novel prosthesis systems that incorporate autonomous controllers and provide the user with touch-location feedback through either vibration or distributed pressure. These capabilities were made possible by installing a custom contact-location sensor on the fingers of a commercial prosthetic hand, along with a custom pressure sensor on the thumb. We compared the performance of the two systems against a standard myoelectric prosthesis and a myoelectric prosthesis with only autonomous controllers in a difficult reach-to-pick-and-place task conducted without direct vision. Results from 40 able-bodied participants in this between-subjects study indicated that vibrotactile feedback combined with synthetic reflexes proved significantly more advantageous than the standard prosthesis in several of the task milestones. In addition, vibrotactile feedback and synthetic reflexes improved grasp placement compared to only synthetic reflexes or pressure feedback combined with synthetic reflexes. These results indicate that autonomous controllers and haptic feedback together facilitate success in dexterous tasks without vision, and that the type of haptic display matters.