Search

Dexterous manipulation is a challenging and important problem in robotics. While data-driven methods are a promising approach, current benchmarks require simulation or extensive engineering support due to the sample inefficiency of popular methods. We present benchmarks for the TriFinger system, an open-source robotic platform for dexterous manipulation and the focus of the 2020 Real Robot Challenge. The benchmarked methods, which were successful in the challenge, can be generally described as structured policies, as they combine elements of classical robotics and modern policy optimization. This inclusion of inductive biases facilitates sample efficiency, interpretability, reliability and high performance. The key aspects of this benchmarking is validation of the baselines across both simulation and the real system, thorough ablation study over the core features of each solution, and a retrospective analysis of the challenge as a manipulation benchmark. The code and demo videos for this work can be found on our website (https://sites.google.com/view/benchmark-rrc).

New mobile manipulator platforms, like the Hello Robot Stretch, have made the idea of long-term in-home robotic assistance feasible. However, existing autonomous capabilities for such robots in unstructured, highly-varied environments are still not available. Instead, using robots with human tele-operation can have huge immediate impact. For these robots to serve populations that need them the most, their interfaces need to be accessible to people with mobility limitations. In this paper we explore the utility, usability, and accessibility of a tele-operated Stretch robot in the home. We first describe a browser-based interface for controlling the Stretch robot designed with accessibility in mind. We then present findings from a study (N=18) in which participants used the interface to remotely control the robot to perform realistic tasks in a kitchen, demonstrating the feasibility of tele-operated assistance and revealing challenges and opportunities. Next, we present a study with individuals with mobility limitations (N=3) identifying additional accessibility requirements for the interface. Participants in both studies agree to the utility of the robot despite current limitations.

Billions of people use chopsticks, a simple yet versatile tool, for fine manipulation of everyday objects. The small, curved, and slippery tips of chopsticks pose a challenge for picking up small objects, making them a suitably complex test case. This paper leverages human demonstrations to develop an autonomous chopsticks-equipped robotic manipulator. Due to the lack of accurate models for fine manipulation, we explore model-free imitation learning, which traditionally suffers from the covariate shift phenomenon that causes poor generalization. We propose two approaches to reduce covariate shift, neither of which requires access to an interactive expert or a model, unlike previous approaches. First, we alleviate single-step prediction errors by applying an invariant operator to increase the data support at critical steps for grasping. Second, we generate synthetic corrective labels by adding bounded noise and combining parametric and non-parametric methods to prevent error accumulation. We demonstrate our methods on a real chopstick-equipped robot that we built, and observe the agent's success rate increase from 37.3% to 80%, which is comparable to the human expert performance of 82.6%., Submitted to ICRA 2021

Working together, heated and unheated temperature sensors can recognize contact with different materials and contact with the human body. As such, distributing these sensors across a robot’s body could be beneficial for operation in human environments. We present a stretchable fabric-based skin with force and thermal sensors that is suitable for covering areas of a robot’s body, including curved surfaces. It also adds a layer of compliance that conforms to manipulated objects, improving thermal sensing. Our open hardware design addresses thermal sensing challenges, such as the time to heat the sensors, the efficiency of sensing, and the distribution of sensors across the skin. It incorporates small self-heated temperature sensors on the surface of the skin that directly make contact with objects, improving the sensors’ response times. Our approach seeks to fully cover the robot’s body with large force sensors, but treats temperature sensors as small, point-like sensors sparsely distributed across the skin. We present a mathematical model to help predict how many of these point-like temperature sensors should be used in order to increase the likelihood of them making contact with an object. To evaluate our design, we conducted tests in which a robot arm used a cylindrical end effector covered with skin to slide objects and press on objects made from four different materials. After assessing the safety of our design, we also had the robot make contact with the forearms and clothed shoulders of 10 human participants. With 2.0 s of contact, the actively-heated temperature sensors enabled binary classification accuracy over 90% for the majority of material pairs. The system could more rapidly distinguish between materials with large differences in their thermal effusivities (e.g., 90% accuracy for pine wood vs. aluminum with 0.5 s of contact). For discrimination between humans vs. the four materials, the skin’s force and thermal sensing modalities achieved 93% classification accuracy with 0.5 s of contact. Overall, our results suggest that our skin design could enable robots to recognize contact with distinct task-relevant materials and humans while performing manipulation tasks in human environments.

Autonomous robot-assisted feeding requires the ability to acquire a wide variety of food items. However, it is impossible for such a system to be trained on all types of food in existence. Therefore, a key challenge is choosing a manipulation strategy for a previously unseen food item. Previous work showed that the problem can be represented as a linear bandit with visual context. However, food has a wide variety of multi-modal properties relevant to manipulation that can be hard to distinguish visually. Our key insight is that we can leverage the haptic context we collect during and after manipulation (i.e., "post hoc") to learn some of these properties and more quickly adapt our visual model to previously unseen food. In general, we propose a modified linear contextual bandit framework augmented with post hoc context observed after action selection to empirically increase learning speed and reduce cumulative regret. Experiments on synthetic data demonstrate that this effect is more pronounced when the dimensionality of the context is large relative to the post hoc context or when the post hoc context model is particularly easy to learn. Finally, we apply this framework to the bite acquisition problem and demonstrate the acquisition of 8 previously unseen types of food with 21% fewer failures across 64 attempts., Comment: 6 pages + references, 5 figures, to appear in ICRA 2021

Robot-assisted feeding (RAF) systems offer enormous potential benefits to community-centered care-giving environments. However, developers of RAF technologies often focus on evaluating their standard transactional functionality, omitting the impact of such technologies in contexts that extend past the interaction of the robot and food receiver. RAF technologies have complex social, cultural and self-identity implications, since a "meal" extends well beyond the simple provisioning of nourishment. To better understand these implications we conducted a contextual inquiry in an assisted-living community with five potential care recipients and five caregivers, as well as interviews with fifteen domain experts including occupational therapists and feeding specialists. Based on our findings from these studies, we developed a new framework for RAF technologies that formulates this vital task as a community-centered relational service. We then use this framework to qualitatively and quantitatively assess three existing feeding systems and identify areas of improvement. Our work reveals new insights about stakeholders of RAF technologies and provides a roadmap for technology developers to better serve the needs of these stakeholders.

A successful robot-assisted feeding system requires bite acquisition of a wide variety of food items. It must adapt to changing user food preferences under uncertain visual and physical environments. Different food items in different environmental conditions require different manipulation strategies for successful bite acquisition. Therefore, a key challenge is how to handle previously unseen food items with very different success rate distributions over strategy. Combining low-level controllers and planners into discrete action trajectories, we show that the problem can be represented using a linear contextual bandit setting. We construct a simulated environment using a doubly robust loss estimate from previously seen food items, which we use to tune the parameters of off-the-shelf contextual bandit algorithms. Finally, we demonstrate empirically on a robot-assisted feeding system that, even starting with a model trained on thousands of skewering attempts on dissimilar previously seen food items, $\epsilon$-greedy and LinUCB algorithms can quickly converge to the most successful manipulation strategy., Comment: To appear in IROS 2020; 8 pages incl. references, 8 figures; Abstract presented in IJCAI 2019 AIxFood Workshop; v3: Added simulation and experimental results for conference submission; v4: Added extra results to Experiment 2 for camera-ready submission

Autonomous assistive feeding systems need to acquire deformable food items of varying physical characteristics to be able to feed users. However, bite acquisition of these deformable food items is challenging without force feedback of appropriate range and sensitivity. We developed custom solutions using two widely-used shear sensing fingertip tactile sensors and calibrated them to the range of forces needed for manipulating food items. We compared their performance with traditional force/torque sensors and showed the trade-off between the range and the sensitivity of the fingertip tactile sensors in detecting potential bite acquisition successes for food items with widely varying weights and compliance. We then developed a control policy, using which a robotic gripper equipped with the fingertip tactile sensors can autonomously regulate the sensing range and the sensitivity to be able to skewer food items of different compliance and detect their bite acquisition success attempts.

Passivity analysis provides a convenient measure to assess the stability of haptic systems interacting with virtual environments. Passivity analysis of haptic sampled-data systems coupled with virtual environments requires knowledge of parameters of the employed environment model. Kelvin–Voigt models have been popularly used to describe viscoelastic behavior of soft tissues being simulated in a virtual environment. This paper employs a standard linear solid model that has been recently shown to be better suited to represent the behavior of the actual soft tissues, and provides passivity analysis of the haptic systems interacting with virtual viscoelastic soft tissues based on the standard linear solid model. The analysis results in a new criterion for design and control of passive haptic interfaces. The effect of the employed discretization method on passivity is also discussed. Experimental results show that the new passivity criterion is less conservative. This criterion increases the domain of soft-tissue environments that can be interacted with passively by the haptic interface.

By briefly heating the local environment with a heat lamp and observing what happens with a thermal camera, robots could potentially infer properties of their surroundings. However, this form of active thermography introduces large signal variations compared to traditional active thermography, which has typically been used to characterize small regions of materials in carefully controlled settings. We demonstrate that a data-driven approach with modern machine learning methods can be used to classify material samples over relatively large surface areas and variable distances. We also introduce the use of z-normalization to improve material classification and reduce variation due to distance and heating intensity. Our best performing algorithm achieved an overall accuracy of 77.7% for multi-class classification among 12 materials placed at varying distances (20 cm, 30 cm, and 40 cm). The observations were made for 5 seconds with 1s of heating and 4s of cooling. We also provide a demonstration of performance with a multi-material scene.

This paper focuses on the human perception capabilities for haptic interaction with remote environments. The perception capabilities are compared for two well-known control methods with two kinds of haptic cues. Analytical and psychophysical methods are used to analyze the performance. The first control method aims at maximizing the transparency of the remote interactions (i.e., transparency-based method ), whereas the second one aims at maximizing the detection and discrimination abilities of the human operator (i.e., perception-based method ). For each of these two control methods, two kinds of haptic cues are studied, which use position and force cues from remote environments. Hybrid matrix formulation is employed, and it is analyzed in the frequency domain for these studies. Psychophysical experiments are then conducted for human-centered evaluation and comparison of the control methods. Analytical and experimental results clearly show that the perception-based method, when compared with the transparency-based method, enhances the human operator's perceptual capabilities of remote environments irrespective of force cues. For each of the two control methods, the force cues always contribute more to the increase in perceptual sensitivity when compared with the case of position cues.

Background Physical interactions between two people are ubiquitous in our daily lives, and an integral part of many forms of rehabilitation. However, few studies have investigated forces arising from physical interactions between humans during a cooperative motor task, particularly during overground movements. As such, the direction and magnitude of interaction forces between two human partners, how those forces are used to communicate movement goals, and whether they change with motor experience remains unknown. A better understanding of how cooperative physical interactions are achieved in healthy individuals of different skill levels is a first step toward understanding principles of physical interactions that could be applied to robotic devices for motor assistance and rehabilitation. Methods Interaction forces between expert and novice partner dancers were recorded while performing a forward-backward partnered stepping task with assigned “leader” and “follower” roles. Their position was recorded using motion capture. The magnitude and direction of the interaction forces were analyzed and compared across groups (i.e. expert-expert, expert-novice, and novice-novice) and across movement phases (i.e. forward, backward, change of direction). Results All dyads were able to perform the partnered stepping task with some level of proficiency. Relatively small interaction forces (10–30N) were observed across all dyads, but were significantly larger among expert-expert dyads. Interaction forces were also found to be significantly different across movement phases. However, interaction force magnitude did not change as whole-body synchronization between partners improved across trials. Conclusions Relatively small interaction forces may communicate movement goals (i.e. “what to do and when to do it”) between human partners during cooperative physical interactions. Moreover, these small interactions forces vary with prior motor experience, and may act primarily as guiding cues that convey information about movement goals rather than providing physical assistance. This suggests that robots may be able to provide meaningful physical interactions for rehabilitation using relatively small force levels.

Partner dance has been shown to be beneficial for the health of older adults. Robots could potentially facilitate healthy aging by engaging older adults in partner dance-based exercise. However, partner dance involves physical contact between the dancers, and older adults would need to be accepting of partner dancing with a robot. Using methods from the technology acceptance literature, we conducted a study with 16 healthy older adults to investigate their acceptance of robots for partner dance-based exercise. Participants successfully led a human-scale wheeled robot with arms (i.e., a mobile manipulator) in a simple, which we refer to as the Partnered Stepping Task (PST). Participants led the robot by maintaining physical contact and applying forces to the robot's end effectors. According to questionnaires, participants were generally accepting of the robot for partner dance-based exercise, tending to perceive it as useful, easy to use, and enjoyable. Participants tended to perceive the robot as easier to use after performing the PST with it. Through a qualitative data analysis of structured interview data, we also identified facilitators and barriers to acceptance of robots for partner dance-based exercise. Throughout the study, our robot used admittance control to successfully dance with older adults, demonstrating the feasibility of this method. Overall, our results suggest that robots could successfully engage older adults in partner dance-based exercise.

Robots could benefit from maps that represent haptic properties of their surroundings. By touching locations with tactile sensors, robots can infer haptic properties of their surroundings, but touching all locations would be prohibitive. We present an algorithm that uses touch and vision to efficiently produce a dense haptic map. Our approach assumes that surfaces near a robot that are visually similar are more likely to have similar haptic properties. Given an image and sparse haptic labels, our algorithm uses a dense conditional random field (CRF) to produce a haptic map with labels for all image pixels. In an evaluation using images with idealized haptic labels, our algorithm substantially outperformed a previous algorithm. It also enabled a real robot to label leaves and trunks after reaching into artificial foliage. In addition, we show that our algorithm can use a convolutional neural network (CNN) for material recognition from Bell et al. [1] that we modified and fine-tuned. This CNN provides estimated probabilities for haptic labels using vision alone, which enables the algorithm to infer haptic labels before the robot makes contact with anything. In our evaluation, using this CNN further improved performance.

Dressing is an important activity of daily living (ADL) with which many people require assistance due to impairments. Robots have the potential to provide dressing assistance, but physical interactions between clothing and the human body can be complex and difficult to visually observe. We provide evidence that data-driven haptic perception can be used to infer relationships between clothing and the human body during robot-assisted dressing. We conducted a carefully controlled experiment with 12 human participants during which a robot pulled a hospital gown along the length of each person's forearm 30 times. This representative task resulted in one of the following three outcomes: the hand missed the opening to the sleeve; the hand or forearm became caught on the sleeve; or the full forearm successfully entered the sleeve. We found that hidden Markov models (HMMs) using only forces measured at the robot's end effector classified these outcomes with high accuracy. The HMMs' performance generalized well to participants (98.61% accuracy) and velocities (98.61% accuracy) outside of the training data. They also performed well when we limited the force applied by the robot (95.8% accuracy with a 2N threshold), and could predict the outcome early in the process. Despite the lightweight hospital gown, HMMs that used forces in the direction of gravity substantially outperformed those that did not. The best performing HMMs used forces in the direction of motion and the direction of gravity.

Online detection of anomalous execution can be valuable for robot manipulation, enabling robots to operate more safely, determine when a behavior is inappropriate, and otherwise exhibit more common sense. By using multiple complementary sensory modalities, robots could potentially detect a wider variety of anomalies, such as anomalous contact or a loud utterance by a human. However, task variability and the potential for false positives make online anomaly detection challenging, especially for long-duration manipulation behaviors. In this paper, we provide evidence for the value of multimodal execution monitoring and the use of a detection threshold that varies based on the progress of execution. Using a data-driven approach, we train an execution monitor that runs in parallel to a manipulation behavior. Like previous methods for anomaly detection, our method trains a hidden Markov model (HMM) using multimodal observations from non-anomalous executions. In contrast to prior work, our system also uses a detection threshold that changes based on the execution progress. We evaluated our approach with haptic, visual, auditory, and kinematic sensing during a variety of manipulation tasks performed by a PR2 robot. The tasks included pushing doors closed, operating switches, and assisting able-bodied participants with eating yogurt. In our evaluations, our anomaly detection method performed substantially better with multimodal monitoring than single modality monitoring. It also resulted in more desirable ROC curves when compared with other detection threshold methods from the literature, obtaining higher true positive rates for comparable false positive rates.

Many tactile sensors can readily detect physical contact with an object, but tactile recognition of the type of object remains challenging. In this paper, we provide evidence that data-driven thermal tactile sensing can be used to recognize contact with people and objects in real-world settings. We created a portable handheld device with three tactile sensing modalities: a heat-transfer sensor that is actively heated, a small thermally-isolated temperature sensor, and a force sensor to detect the onset of contact. Using this device, we collected data from contact with the arms of 10 people (3 locations on the right arm) and contact with 80 objects relevant to robotic assistance (8 object types in 10 residential bathrooms). We then used support vector machines (SVMs) to perform binary classifications relevant to assistive robots. When classifying contact as person vs. object, classifiers that only used the temperature sensor performed best (average accuracy of 98.75% for 3.65s of contact, 93.13% for 1.0s, and 82.13% for 0.5s). When classifying contact into two task-relevant object types (e.g., towel vs. towel rack), classifiers that used the heat-transfer sensor together with the temperature sensor performed best. Performance was good when generalizing to new contact locations in the same environment (average accuracy of 92.14% for 3.65s of contact, 91.43% for 1.0s, and 84.29% for 0.5s), but weaker when generalizing to new environments (average accuracy of 84% for 3.65s of contact, 71% for 1.0s, and 65% for 0.5s).

This paper develops a control algorithm to show the human-like reaching movements in humanoid redundant systems involving the trunk. This algorithm neither requires the computation of pseudo-inverse of Jacobian nor does it need the optimization of any artificial performance index. The control law accommodates the time-varying temporal properties of the muscle stiffness and damping as well as low-pass filter characteristics of human muscles. It uses a time-varying damping shaping matrix and a bijective joint muscle mapping function to describe the spatial characteristics of human reaching motion like quasi-straight line trajectory of the end-effector and symmetric bell shaped velocity profile as well as the temporal characteristics like the occurrence of the peak velocity of the trunk motion after the peak velocity of the arm motion. The aspect of self-motion is also analyzed using the null-space motion of the manipulator Jacobian. The effects of the control parameters on the motion pattern are analyzed in detail and some basic guidelines have been provided to select their proper values. Simulation results show the efficacy of the newly developed algorithm in describing humanmotion characteristics.

Whole-arm tactile sensing enables a robot to sense contact and infer contact properties across its entire arm. Within this paper, we demonstrate that using data-driven methods, a humanoid robot can infer mechanical properties of objects from contact with its forearm during a simple reaching motion. A key issue is the extent to which the performance of data-driven methods can generalize to robot actions that differ from those used during training. To investigate this, we developed an idealized physics-based lumped element model of a robot with a compliant joint making contact with an object. Using this physics-based model, we performed experiments with varied robot, object and environment parameters. We also collected data from a tactile-sensing forearm on a real robot as it made contact with various objects during a simple reaching motion with varied arm velocities and joint stiffnesses. The robot used 1-nearest-neighbor (1-NN) classifiers, hidden Markov models (HMMs), and long short-term memory (LSTM) networks to infer two object properties (hard versus soft and moved versus unmoved) based on features of time-varying tactile sensor data (maximum force, contact area, and contact motion). We found that, in contrast to 1-NN, the performance of LSTMs (with sufficient data availability) and multivariate HMMs successfully generalized to new robot motions with distinct velocities and joint stiffnesses. Compared to single features, using multiple features gave the best results for both experiments with physics-based models and a real-robot.

We consider the problem of enabling a robot to efficiently obtain a dense haptic map of its visible surroundings using the complementary properties of vision and tactile sensing. Our approach assumes that visible surfaces that look similar to one another are likely to have similar haptic properties. We present an iterative algorithm that enables a robot to infer dense haptic labels across visible surfaces when given a color-plus-depth (RGB-D) image along with a sequence of sparse haptic labels representative of what could be obtained via tactile sensing. Our method uses a color-based similarity measure and connected components on color and depth data. We evaluated our method using several publicly available RGBD image datasets with indoor cluttered scenes pertinent to robot manipulation. We analyzed the effects of algorithm parameters and environment variation, specifically the level of clutter and the type of setting, like a shelf, table top, or sink area. In these trials, the visible surface for each object consisted of an average of 8602 pixels, and we provided the algorithm with a sequence of haptically-labeled pixels up to a maximum of 40 times the number of objects in the image. On average, our algorithm correctly assigned haptic labels to 76.02% of all of the object pixels in the image given this full sequence of labels. We also performed experiments with the humanoid robot DARCI reaching in a cluttered foliage environment while using our algorithm to create a haptic map. Doing so enabled the robot to reach goal locations using a single plan after a single greedy reach, while our previous tactile-only mapping method required 5 or more plans to reach each goal.

Robots are ever more present in human environments and effective physical human-robot interactions are essential to many applications. But to a person, these interactions rarely feel biological or equivalent to a human-human interactions. It is our goal to make robots feel more human-like, in the hopes of allowing more natural human-robot interactions. In this paper, we examine a novel biologically-inspired control method, emulating antagonistic muscle pairs based on a nonlinear Hill model. The controller captures the muscle properties and dynamics and is driven solely by muscle activation levels. A human-robot experiment compares this approach to PD and PID controllers with equivalent impedances as well as to direct human-human interactions. The results show the promise of driving motors like muscles and allowing users to experience robots much like humans.

We demonstrate that data-driven methods can be used to rapidly categorize objects encountered through incidental contact on a robot arm. Allowing incidental contact with surrounding objects has benefits during manipulation such as increasing the workspace during reaching tasks. The information obtained from such contact, if available online, can potentially be used to map the environment and help in manipulation tasks. In this paper, we address this problem of online categorization using incidental contact during goal-oriented motion. In cluttered environments, the detailed internal structure of clutter can be difficult to infer, but the environment type is often apparent. In a randomized cluttered environment of known object types and “outliers”, our approach uses Hidden Markov Models to capture the dynamic robot-environment interactions and to categorize objects based on the interactions. We combined leaf and trunk objects to create artificial foliage as a test environment. We collected data using a skin-sensor on the robot's forearm while it reached into clutter. Our algorithm classifies the objects rapidly with low computation time and few data-samples. Using a taxel-by-taxel classification approach, we can successfully categorize simultaneous contacts with multiple objects and can also identify outlier objects in the environment based on the prior associated with an object's likelihood in the given environment.

Biological organisms benefit from tactile sensing across the entire surfaces of their bodies. Robots may also be able to benefit from this type of sensing, but fully covering a robot with robust and capable tactile sensors entails numerous challenges. To date, most tactile sensors for robots have been used to cover rigid surfaces. In this paper, we focus on the challenge of tactile sensing across articulated joints, which requires sensing across a surface whose geometry varies over time. We first demonstrate the importance of sensing across joints by simulating a planar arm reaching in clutter and finding the frequency of contact at the joints. We then present a simple model of how much a tactile sensor would need to stretch in order to cover a 2 degree-of-freedom (DoF) wrist joint. Next, we describe and characterize a new tactile sensor made with stretchable fabrics. Finally, we present results for a stretchable sleeve with 25 tactile sensors that covers the forearm, 2 DoF wrist, and end effector of a humanoid robot. This sleeve enabled the robot to reach a target in instrumented clutter and reduce contact forces.

Surgical teleoperation systems are being increasingly deployed recently. There are, however, some unsolved issues such as nonlinear characteristics of the interaction between the slave robot and soft tissues and difficulty in employing force sensors in the surgical end-effectors of the slave. These issues make it difficult to generalize any approach to develop a control for the system. This paper addresses these issues by proposing a H∞ suboptimal controller preserving robust stability and performance. The environment, i.e., soft tissues, is characterized with the nonlinear Hunt-Crossley model. This nonlinear characteristics of soft tissues are expressed with an affine combination of linear models within a predefined parameter polytope. For this linear parameter-varying system, a gain-scheduling control scheme is employed to design a suboptimal controller while guaranteeing its stability. To avoid using any force measurement in slave, we used position-position (PP) control architecture. The developed gain-scheduling control is validated with quantitative experimental results. The developed gain-scheduling PP control scheme shows good tracking capacity and high transparency for varied experimental conditions. Error of the transmitted impedance is significantly lower compared with other conventional control schemes for frequencies less than 2 Hz, which is frequently recommended for surgical teleoperation.

In this paper, we demonstrate data-driven inference of mechanical properties of objects using a tactile sensor array (skin) covering a robot's forearm. We focus on the mobility (sliding vs. fixed), compliance (soft vs. hard), and identity of objects in the environment, as this information could be useful for efficient manipulation and search. By using the large surface area of the forearm, a robot could potentially search and map a cluttered volume more efficiently, and be informed by incidental contact during other manipulation tasks. Our approach tracks a contact region on the forearm over time in order to generate time series of select features, such as the maximum force, contact area, and contact motion. We then process and reduce the dimensionality of these time series to generate a feature vector to characterize the contact. Finally, we use the k-nearest neighbor algorithm (k-NN) to classify a new feature vector based on a set of previously collected feature vectors. Our results show a high cross-validation accuracy in both classification of mechanical properties and object recognition. In addition, we analyze the effect of taxel resolution, duration of observation, feature selection, and feature scaling on the classification accuracy.

This paper aims at analyzing the effect of widely known impedance-shaping control method on the perception of soft-tissues in tele-microsurgical applications. The generalized teleoperation control architecture has been modified to include the impedance-shaping term. New performance index has been defined based on the two proposed indices for the detection and the discrimination of the soft environments to analyze the effect of this modified control on the kinesthetic perception of soft-tissues. The effect is then theoretically analyzed on the conventional position-position, force-position, and four-channel control architectures based on the newly defined index. The effectiveness of this newly proposed kinesthetic perception index is also verified using psychophysics experiments. The theoretical analysis of the effects of the impedance-shaping method on the perception of soft tissues is then validated using the proposed index by experiments with phantom soft tissues for conventional teleoperation architectures.

There is generally a tradeoff between stability and performance in haptic control systems. Teleoperation systems with haptic feedback are no exception. Scaling in these systems used in applications such as telemicrosurgical systems has further effects on the stability and performance. This paper focuses on those applications interacting with soft tissues and analyzes the effects of the scaling in an effort to increase the performance of these systems while maintaining the stability. Position tracking and kinesthetic perception are especially important in the tele-surgical systems and, hence, are used as the performance criteria. Quantitatively defined stability robustness, which is based on Llewellyn's absolute stability criterion, is used as a metric for stability analysis. Various choices of scaling factors, and human and environment impedances are then investigated. The proposed kinesthetic perception concept is validated using psychophysical experiments. Widely used bilateral control architectures such as the two-channel position-position, two-channel force-position and four-channel controls are specifically analyzed and evaluated using simulations and experiments with phantom soft tissues. Results also show that the force-position control architecture shows the best position tracking performance irrespective of the scaling factors while the four-channel controller shows the best kinesthetic perception capability.

In this paper, we have developed a novel control law to exhibit human-motion characteristics in redundant robot arm-trunk systems for reaching tasks. This newly developed method nullifies the need for the computation of pseudo-inverse of Jacobian while the formulation and optimization of any artificial performance index is not necessary. The time-varying properties of the muscle stiffness and damping as well as the low-pass filter characteristics of human muscles have been modeled by the proposed control law. The newly developed control law uses a time-varying damping shaping matrix and a bijective joint muscle mapping function to describe the human-motion characteristics for reaching motion like quasi-straight line trajectory of the end-effector and symmetric bell shaped velocity profile. The aspect of self-motion and repeatability, which are inherent in human-motion, are also analyzed and successfully modeled using the proposed method. Simulation results show the efficacy of the newly developed algorithm in describing the human-motion characteristics.

This paper focuses on psychophysical evaluation of the control scheme developed to optimize the kinesthetic perception during the scaled teleoperation. The control problem is formulated as a multi-objective constrained optimization. The objective function is a metric which quantifies the detection and discrimination capacity of the human operator. The constraints are position tracking accuracy and absolute stability of the scaled teleoperation. Two popular control architectures, i.e., the position-position and the force-position control architectures are considered in this paper. The method of limits is employed in this paper to conduct the psychophysical experiments and evaluation. Results show that the developed control scheme is more effective in increasing the detection and discrimination capacity of human subjects as compared to the traditional transparency-optimized control laws.

Success of telesurgical operations depends on better position tracking ability of the slave device. Improved position tracking of the slave device can lead to safer and less strenuous telesurgical operations. The two-channel force-position control architecture is widely used for better position tracking ability. This architecture requires force sensors for direct force feedback. Force sensors may not be a good choice in the telesurgical environment because of the inherent noise, and limitation in the deployable place and space. Hence, environment force estimation is developed using the concept of the robot function parameter matrix and a recursive least squares method. Simulation results show efficacy of the proposed method. The slave device successfully tracks the position of the master device, and the estimation error quickly becomes negligible.

Our long-term goal is to enable a robot to engage in partner dance for use in rehabilitation therapy, assessment, diagnosis, and scientific investigations of two-person whole-body motor coordination. Partner dance has been shown to improve balance and gait in people with Parkinson's disease and in older adults, which motivates our work. During partner dance, dance couples rely heavily on haptic interaction to convey motor intent such as speed and direction. In this paper, we investigate the potential for a wheeled mobile robot with a human-like upper-body to perform partnered stepping with people based on the forces applied to its end effectors. Blindfolded expert dancers (N=10) performed a forward/backward walking step to a recorded drum beat while holding the robot's end effectors. We varied the admittance gain of the robot's mobile base controller and the stiffness of the robot's arms. The robot followed the participants with low lag (M=224, SD=194 ms) across all trials. High admittance gain and high arm stiffness conditions resulted in significantly improved performance with respect to subjective and objective measures. Biomechanical measures such as the human hand to human sternum distance, center-of-mass of leader to center-of-mass of follower (CoM-CoM) distance, and interaction forces correlated with the expert dancers' subjective ratings of their interactions with the robot, which were internally consistent (Cronbach's α=0.92). In response to a final questionnaire, 1/10 expert dancers strongly agreed, 5/10 agreed, and 1/10 disagreed with the statement "The robot was a good follower." 2/10 strongly agreed, 3/10 agreed, and 2/10 disagreed with the statement "The robot was fun to dance with." The remaining participants were neutral with respect to these two questions.