Performing bimanual tasks with dual robotic setups can drastically increase the impact on industrial and daily life applications. However, performing a bimanual task brings many challenges, such as synchronization and coordination of the single-arm policies. This article proposes the safe, interactive movement primitives learning (SIMPLe) algorithm, to teach and correct single or dual arm impedance policies directly from human kinesthetic demonstrations. Moreover, it proposes a novel graph encoding of the policy based on Gaussian process regression where the single-arm motion is guaranteed to converge close to the trajectory and then toward the demonstrated goal. Regulation of the robot stiffness according to the epistemic uncertainty of the policy allows for easily reshaping the motion with human feedback and/or adapting to external perturbations. We tested the SIMPLe algorithm on a real dual-arm setup where the teacher gave separate single-arm demonstrations and then successfully synchronized them only using kinesthetic feedback or where the original bimanual demonstration was locally reshaped to pick a box at a different height.

@en

In order for off-Earth top surface structures built from regolith to protect astronauts from radiation, they need to be several metres thick. In a feasibility study, funded by the European Space Agency, Technical University Delft (TUD aka TU Delft) explored the possibility of building in empty lava tubes to create rhizomatic subsurface habitats. With this approach natural protection from radiation is achieved as well as thermal insulation because the temperature is more stable underground. It involves a swarm of autonomous mobile robots that survey the areas and mine for materials such as regolith in order to create cement-based concrete reproducible on Mars through in-situ resource utilisation (ISRU). The concrete is 3D printed by means of additive Design-to-Robotic-Production (D2RP) methods developed at TUD for on-Earth applications with the 3D printing system of industrial partner, Vertico. The printed components are assembled using a Human--Robot Interaction (HRI) supported approach. The 3D printed and HRI-supported assembled structures are structurally optimised porous material systems with increased insulation properties. In order to regulate the indoor pressurised environment a Life Support System (LSS) is integrated, which in this study is only conceptually developed. The habitat and the D2RP production system are powered by an automated kite power system and solar panels developed at TUD. The long-term goal is to develop an autarkic, automated and HRI-supported D2RP system for building autarkic habitats from locally obtained materials.@en

Real-world applications of Artificial Intelligence (AI) in architecture have been explored more recently at Technical University (TU) Delft by integrating AI in Design-to-Robotic-Production-Assembly and -Operation (D2RPA&O) methods. These embed robotics into building processes and buildings by linking computational design with robotic construction and/ or operation of building components and buildings. This paper presents two case studies in which AI-supported D2RA is implemented in a multidisciplinary approach that requires the integration of research domains such as architecture, robotics, computer and material science.@en

During the learning of a new sensorimotor task, individuals are usually provided with instructional stimuli and relevant information about the target task. The inclusion of haptic devices in the study of this kind of learning has greatly helped in the understanding of how an individual can improve or acquire new skills. However, the way in which the information and stimuli are delivered has not been extensively explored. We have designed a challenging task with nonintuitive visuomotor perturbation that allows us to apply and compare different motor strategies to study the teaching process and to avoid the interference of previous knowledge present in the naïve subjects. Three subject groups participated in our experiment, where the learning by repetition without assistance, learning by repetition with assistance, and task Segmentation Learning techniques were performed with a haptic robot. Our results show that all the groups were able to successfully complete the task and that the subjects’ performance during training and evaluation was not affected by modifying the teaching strategy. Nevertheless, our results indicate that the presented task design is useful for the study of sensorimotor teaching and that the presented metrics are suitable for exploring the evolution of the accuracy and precision during learning.

@en

In the original version of the book, on page xi, one of the authors listed for Chapter 2 is “R. Schnmehl”, which should be “R. Schmehl”. On page 21, the same correction needs to be made twice, in the listed authors at the top of the page and also in the footnotes. “Schnmehl” should become “Schmehl” in both the cases. This has now been rectified and the author’s name has been corrected. The correction to this book have been updated with the changes.@en

In recent years, providing additional visual feedback about the interaction forces has been found to offer benefits to haptic-assisted teleoperation. However, there is limited insight into the effects of the design of force feedback-related visual cues and the type of visual display on the performance of teleoperation of robotic arms executing industrial tasks. In this study, we provide new insights into this interaction by extending these findings to the haptic assistance teleoperation of a simulated robotic arm in a virtual environment, in which the haptic assistance is comprised of a set of virtual fixtures. We design a novel method for providing visual cues about the interaction forces to complement the haptic assistance and augment visual feedback in virtual reality with a head-mounted display. We evaluate the visual cues method and head-mounted display method through human factors experiments in a teleoperated dross removal use case. The results show that both methods are beneficial for task performance, each of them having stronger points in different aspects of the operation. The visual cues method was found to significantly improve safety in terms of peak collision force, whereas the head-mounted display additionally improves the performance significantly. Furthermore, positive scores of the subjective analysis indicate an increased user acceptance of both methods. This work provides a new study on the importance of visual feedback related to (interaction) forces and spatial information for haptic assistance and provides two methods to take advantage of its potential benefits in the teleoperation of robotic arms.@en

Many daily tasks exhibit a periodic nature, necessitating that robots possess the ability to execute them either alone or in collaboration with humans. A widely used approach to encode and learn such periodic patterns from human demonstrations is through periodic Dynamic Movement Primitives (DMPs). Periodic DMPs encode cyclic data independently across multiple dimensions of multi-degree of freedom systems. This method is effective for simple data, like Cartesian or joint position trajectories. However, it cannot account for various geometric constraints imposed by more complex data, such as orientation and stiffness. To bridge this gap, we propose a novel periodic DMP formulation that enables the encoding of periodic orientation trajectories and varying stiffness matrices while considering their geometric constraints. Our geometry-aware approach exploits the properties of the Riemannian manifold and Lie group to directly encode such periodic data while respecting its inherent geometric constraints. We initially employed simulation to validate the technical aspects of the proposed method thoroughly. Subsequently, we conducted experiments with two different real-world robots performing daily tasks involving periodic changes in orientation and/or stiffness, i.e., operating a drilling machine using a rotary handle and facilitating collaborative human–robot sawing.

@en

Collaborative robots (cobots) have the potential to augment the productivity and life quality of human operators in the context of Industry 4.0 by providing them with physical assistance. For this reason, it is necessary to define the relationship between humans and cobots and to study how the two agents adapt to each other. However, to the best of our knowledge, literature is still missing insight into how humans perceive and react to changes in the cobot behavior (e.g. changes in the learned trajectory and in the role the robot assumes). Specifically, a study of how humans adapt to changing roles and control strategies of collaborating robots is missing. To fill this gap, we propose a human study in which 16 participants executed a collaborative human–robot sawing task where the cobot altered between three different control strategies. We examined human adaptation when cobot suddenly changed the control strategy from one to another, resulting in six experimental conditions. The experiments were performed on a setup involving Kuka LBR iiwa robotic arm. The results suggest that transition influences movement performance in the early stages and at steady state, subjects prefer to abandon modes that require more effort and they adapt faster to energy-demanding modes. Finally, for the specific task we studied, subjects tend to prefer collaborative modes to ones in which the robot assumes a fixed role.

@en

This paper studies non-physical feedback mechanisms to guide human workers toward ergonomic body postures. Specifically, the focus is to solve the tasks that involve no direct physical interaction between the human and the robotic system, therefore tactile guidance by the robot body is not feasible. We propose a multi-modal ergonomic posture guidance system that comprises visual feedback and speech-based audio feedback. We hypothesise that the proposed multi-modal system leads to better performance compared to uni-modal feedback systems when trying to guide users from one pose to another. To test the hypothesis we conducted an experiment that compared conditions with only audio feedback, only visual feedback and multi-modal feedback. In addition, we examined speech-based audio guidance in joint space and in endpoint space. The results showed that the speech-based feedback in joint space came out as the preferred audio feedback due to its ability to allow users to carry out efficient and coordinated inter-joint movements, especially in cases of high redundancy. Furthermore, the proposed multi-modal feedback system was superior compared to the other feedback modalities both in terms of objective measures and subjective measures.

@en

In this research, we propose a novel method to estimate and monitor rotator cuff tendon strains during active robotic-assisted rehabilitation. This is a significant step forward from our previous work which estimated these tendon strains during passive exercises (i.e., no muscle activity). Physiotherapists adopt a cautious approach to rehabilitation treatment to prevent (re-) injury given the limited available information about the shoulder's internal condition. By leveraging a robotic device and a musculoskeletal model, our approach provides quantitative information on the risk of re-injury by monitoring the strains of the rotator cuff tendons during shoulder movements with the application of external loads. Muscle strains depend on the shoulder kinematic state and muscle activations, which makes it crucial to obtain physiologically realistic joint kinematics to estimate real-time muscle function. To obtain the strains, we utilize our muscle redundancy solver that incorporates constraints on model accelerations, the glenohumeral joint reaction forces, and active muscle dynamics. Using this algorithm along with force and pose data from a collaborative robotic arm, we demonstrate the ability to update our tendon strain estimates based on muscle activation during robotic-assisted rehabilitation exercises. The findings of our research pave the way for establishing improved therapy that considers the risk of injury to individual muscles and explores a broader and more personalized range of motion. By providing physiotherapists with valuable quantitative information on rotator cuff tendon strains, our method empowers them to optimize rehabilitation protocols and deliver more personalized and effective care. In addition, the system and method presented here comprise a tool capable of offering new insights into the relationship between the rotator cuff muscles, external forces, and shoulder kinematics.@en

Robotic tasks which involve uncertainty – due to variation in goal, environment configuration, or confidence in task model – may require human input to instruct or adapt the robot. In tasks with physical contact, several existing methods for adapting robot trajectory or impedance according to individual uncertainties have been proposed, e.g., realizing intention detection or uncertainty-aware learning from demonstration. However, isolated methods cannot address the wide range of uncertainties jointly present in many tasks. To improve generality, this paper proposes a model predictive control (MPC) framework which plans both trajectory and impedance online, can consider discrete and continuous uncertainties, includes safety constraints, and can be efficiently applied to a new task. This framework can consider uncertainty from: contact constraint variation, uncertainty in human goals, or task disturbances. An uncertainty-aware task model is learned from a few (≤3) demonstrations using Gaussian Processes. This task model is used in a nonlinear MPC problem to optimize robot trajectory and impedance according to belief in discrete human goals, human kinematics, safety constraints, contact stability, and frequency-domain disturbance rejection. This MPC formulation is introduced, analyzed with respect to convexity, and validated in co-manipulation with multiple goals, a collaborative polishing task, and a collaborative assembly task.

@en

Skill propagation among robots without human involvement can be crucial in quickly spreading new physical skills to many robots. In this respect, it is a good alternative to pure reinforcement learning, which can be time-consuming, or learning from human demonstration, which requires human involvement. In the latter case, there may not be enough humans to quickly spread skills to many robots. However, propagation among robots without direct human supervision can result in robotic skills mutating from the original source. This can be beneficial when better skills might emerge or when a new skill is obtained to be used for other similar tasks. However, it can also be dangerous in terms of task execution safety. This letter studies the mutation of a robotic skill when it is propagated from one robot to another during a physically collaborative task. We chose the collaborative sawing task as a study case since it involves complex two-agent physical interaction/coordination and because its periodic nature can facilitate repetitive learning. The study employs periodic Dynamic Movement Primitives and Locally Weight Regression to encode and learn the motion and impedance required to execute the task. To explore what influences mutation, we varied several control and environment conditions such as the maximum stiffness, robot base position, friction coefficient of the sawed object, and movement period. The results showed that the skill varied over propagation steps and we identified several key aspects of mutation such as movement length, movement offset, and trajectory shape. Based on the results we identified possible benefits (skill mutations useful for different settings or different tasks, and energy efficiency) and dangers (high forces and skill mutations becoming useless for the original task) of the mutation.

@en

Humans can effortlessly grasp various objects when the fingers are in direct physical interaction with the object. However, the same actions become complicated when grasping has to be performed via a teleoperated remote robot due to a lack of direct contact and reduced sensory information. Having a fully autonomous remote robot can eliminate the problem of lack of proper feedback to the human operator, nevertheless, it also prevents human control over the remote robot's grasping actions. In this paper, we propose a semi-autonomous controller for a teleoperated robot grasping where the human operator controls the grasping aperture while the robot controls the impedance of the gripper. When the operator grasps an object with the remote robot, the semi-autonomous controller maintains the grip force by adjusting stiffness. The developed stiffness adjustment approach derives from the concept of grip force safety margin, which is the central regulation principle humans use to maintain a light grasp yet prevent object slippage. To detect incipient slippage, we use a tactile sensor that captures the local deformations due to the contact and interprets them to determine the proximity to the object's slip. To validate the proposed method, we performed experiments on a teleoperation system composed of Force Dimension sigma.7 haptic interface and a KUKA LBR iiwa collaborative robot equipped with a custom-built gripper. The results show that the proposed controller is robust to external perturbations while it adapts to the operator's commands to prevent grasped object slippage.@en

The advancement and development of human modeling have greatly benefited from principles used in robotics, for instance, multibody dynamics laid the foundations for physics engines of human movement simulation, and the robotics and control theory were used to contextualize human sensorimotor control. There are many common interests and interconnections between the fields of human modeling and robotics. In recent years, as robots have become safer and smarter, they actively participate in our lives and help us in various scenarios. Roboticists need tools and data from human modeling to build next-generation robots that better assist humans. In this survey, we focus on the connections between physical human-robot interaction and human modeling. On one hand, human neuromusculoskeletal and sensorimotor control models provide novel insights into the human response that robots can utilize to improve human performance. On the other hand, robots are becoming instrumental in quantifying the performance of the (neuro)musculoskeletal system. Thus, the combined use of human modeling and robotic methods in physical human-robot interaction can lead to both improved human understanding and functional assistance.

@en

The complexity of the human shoulder girdle enables the large mobility of the upper extremity, but also introduces instability of the glenohumeral (GH) joint. Shoulder movements are generated by coordinating large superficial and deeper stabilizing muscles spanning numerous degrees-of-freedom. How shoulder muscles are coordinated to stabilize the movement of the GH joint remains widely unknown. Musculoskeletal simulations are powerful tools to gain insights into the actions of individual muscles and particularly of those that are difficult to measure. In this study, we analyze how enforcement of GH joint stability in a musculoskeletal model affects the estimates of individual muscle activity during shoulder movements. To estimate both muscle activity and GH stability from recorded shoulder movements, we developed a Rapid Muscle Redundancy (RMR) solver to include constraints on joint reaction forces (JRFs) from a musculoskeletal model. The RMR solver yields muscle activations and joint forces by minimizing the weighted sum of squared-activations, while matching experimental motion. We implemented three new features: first, computed muscle forces include active and passive fiber contributions; second, muscle activation rates are enforced to be physiological, and third, JRFs are efficiently formulated as linear functions of activations. Muscle activity from the RMR solver without GH stability was not different from the computed muscle control (CMC) algorithm and electromyography of superficial muscles. The efficiency of the solver enabled us to test over 3600 trials sampled within the uncertainty of the experimental movements to test the differences in muscle activity with and without GH joint stability enforced. We found that enforcing GH stability significantly increases the estimated activity of the rotator cuff muscles but not of most superficial muscles. Therefore, a comparison of shoulder model muscle activity to EMG measurements of superficial muscles alone is insufficient to validate the activity of rotator cuff muscles estimated from musculoskeletal models.@en

Biological systems, including human beings, have the innate ability to perform complex tasks in a versatile and agile manner. Researchers in sensorimotor control have aimed to comprehend and formally define this innate characteristic. The idea, supported by several experimental findings, that biological systems are able to combine and adapt basic units of motion into complex tasks finally leads to the formulation of the motor primitives’ theory. In this respect, Dynamic Movement Primitives (DMPs) represent an elegant mathematical formulation of the motor primitives as stable dynamical systems and are well suited to generate motor commands for artificial systems like robots. In the last decades, DMPs have inspired researchers in different robotic fields including imitation and reinforcement learning, optimal control, physical interaction, and human–robot co-working, resulting in a considerable amount of published papers. The goal of this tutorial survey is two-fold. On one side, we present the existing DMP formulations in rigorous mathematical terms and discuss the advantages and limitations of each approach as well as practical implementation details. In the tutorial vein, we also search for existing implementations of presented approaches and release several others. On the other side, we provide a systematic and comprehensive review of existing literature and categorize state-of-the-art work on DMP. The paper concludes with a discussion on the limitations of DMPs and an outline of possible research directions.

@en

Humans often demonstrate diverse behaviors due to their personal preferences, for instance, related to their individual execution style or personal margin for safety. In this paper, we consider the problem of integrating both path and velocity preferences into trajectory planning for robotic manipulators. We first learn reward functions that represent the user path and velocity preferences from kinesthetic demonstration. We then optimize the trajectory in two steps, first the path and then the velocity, to produce trajectories that adhere to both task requirements and user preferences. We design a set of parameterized features that capture the fundamental preferences in a pick-and-place type of object transportation task, both in the shape and timing of the motion. We demonstrate that our method is capable of generalizing such preferences to new scenarios. We implement our algorithm on a Franka Emika 7-DoF robot arm and validate the functionality and flexibility of our approach in a user study. The results show that non-expert users are able to teach the robot their preferences with just a few iterations of feedback.@en

Daily household tasks involve manipulation in cluttered and unpredictable environments and service robots require complex skills and adaptability to perform such tasks. To this end, we developed a teleoperated online learning approach with a novel skill refinement method, where the operator can make refinements to the initially trained skill by a haptic device. After a refined trajectory is formed, it is used to update a probabilistic trajectory model conditioned to the environment state. Therefore, the initial model can be adapted when unknown variations occur and the method is able to deal with different object positions and initial robot poses. This enables human operators to remotely correct or teach complex robotic manipulation skills. Such an approach can help to alleviate shortages of caretakers in elderly care and reduce travel time between homes of different elderly to reprogram the service robots whenever they get stuck. We performed a human factors experiment on 18 participants teaching a service robot how to empty a dishwasher, which is a common daily household task performed by caregivers. We compared the developed method against three other methods. The results show that the proposed method performs better in terms of how much time it takes to successfully adapt a model and in terms of the perceived workload.

@en

Despite the significant progress made in making robots more intelligent and autonomous, today, teleoperation remains a dominant robot control paradigm for the execution of complex and highly unpredictable tasks. Attempts have been made to make teleoperation systems stable, easy to use, and efficient in terms of physical interactions between the follower remote robot and the environment. In particular, the emergence of torque-controlled robots has permitted to regulate the interaction forces from a distance through direct force or impedance control, enabling them to engage in complex interaction tasks. Exploiting this feature, the concept of teleimpedance control was introduced as an alternative method to bilateral force-reflecting teleoperation. The aim was to create a feed-froward yet contact-efficient teleoperation by enriching the leader commands with desired impedance profiles while executing a task. Since then, the teleimpedance concept has found its way into a wide range of interface and controller designs, as well as application domains. Accordingly, after a decade of research progress, this survey aims to provide: first, a convenient introduction of the concept to new researchers in the field, second, consolidate the existing state-of-the-art for active researchers, third, and discuss the pros and cons of different methods in terms of interface and force feedback to provide guidelines for different applications and future developments.

@en

Robotic teleoperation is used in various applications, including the nuclear industry, where the experience and intelligence of a human operator are necessary for making complex decisions that are beyond the autonomy of robots. Human-robot interfaces that help strengthen an operators situational awareness without inducing excessive cognitive load are crucial to the success of teleoperation. This paper presents a novel visual interface that allows operators to simultaneously control a 6-DoF camera platform and a robotic manipulator whilst experiencing the remote environment through a virtual reality head-mounted display (HMD). The proposed system, Orbital Head-Mounted Display (OHMD), utilizes head rotation tracking to command camera movement in azimuth and elevation directions around a fixation point located at a robot's end-effector. A human factor study was conducted to compare the interface acceptance, perceived workload, and task performance of OHMD with a conventional interface utilizing multiple fixed cameras (Array) and a standard head-mounted display implementation (HMD). Results show that both the OHMD and HMD interfaces significantly improve task performance, reduce perceived workload and increase interface acceptance compared to the Array interface. Participants reported they preferred OHMD due to the increased assistance and freedom in viewpoint selection. Whilst OHMD excelled in usefulness, the standard HMD interface allowed operators to perform robotic welding tasks significantly faster.@en