Human–robot interaction (HRI) is one of the most rapidly growing research fields in robotics and promising for the future of robotics technology. Despite the fact that numerous significant research results in HRI have been presented during the last years, there are still challenges in several critical topics of HRI, which could be summarized as: (i) collision and safety, (ii) virtual guides, (iii) cooperative manipulation, (iv) teleoperation and haptic interfaces, and (v) learning by observation or demonstration. In physical HRI research, the complementarity of the human and the robot capabilities is carefully considered for the advancement of their cooperation in a safe manner. New advanced control systems should be developed so the robot will acquire the ability to adapt easily to the human intentions and to the given task. The possible applications requiring co-manipulation are cooperative transportation of bulky and heavy objects, manufacturing processes such as assembly and surgery.

This paper presents a non-model-based collision detection algorithm for robots without external sensors and with closed control architecture. A reference signal of repetitive motion is recorded from the robot operation. To detect collisions, the reference is compared with measurements from the robot. One of the key contributions is a novel approach to optimal matching of compared signals, which is ensured by the newly developed modified Dynamic Time Warping (mDTW) method presented in this paper. One of the main improvements of the mDTW is that it enables comparing a signal with the most similar section of the other signal. Partial matching also enables online application of time warping principles and reduces the time and computation resources needed to perform matching. In addition to mDTW, two complementary decision rules are developed to identify collisions. The first rule, based on the absolute difference between compared matched samples, uses statistically determined thresholds to perform rapid detection of unambiguous collisions. The second rule is based on Eigen values of the covariance matrix of matched samples, and it employs its higher sensitivity to detect collisions with lower intensity. Results from experimental validation of the proposed collision algorithm on two industrial robots are shown.

In this paper, a multilayer feedforward neural network (NN) is designed and trained, for human–robot collisions detection, using only the intrinsic joint position sensors of a manipulator. The topology of one NN is designed considering the coupled dynamics of the robot and trained, with and without external contacts, by Levenberg–Marquardt algorithm to detect unwanted collisions of the human operator with the manipulator and the link that is collided. The proposed approach could be applied to any industrial robot, where only the joint position signals are available. The designed NN is compared quantitatively and qualitatively with an NN, where both the intrinsic joint position and the torque sensors of the manipulator are used. The proposed method is evaluated experimentally with the KUKA LWR manipulator, which is considered as an example of the collaborative robots, using two of its joints in a planar horizontal motion. The results illustrate that the developed system is efficient and fast to detect the collisions and identify the collided link.

With the increasing demand for humans and robots to collaborate in a joint workspace, it is essential that robots react and adapt instantaneously to unforeseen events to ensure safety. Constraining robot dynamics directly on SE(3), that is, the group of 3D translation and rotation, is essential to comply with the emerging Human–Robot Collaboration (HRC) safety standard ISO/TS 15066. We argue that limiting coordinate-independent magnitudes of physical dynamic quantities at the same time allows more intuitive constraint definitions. We present the first real-time capable online trajectory generator that constrains translational and rotational magnitude values of 3D translation and 3D rotation dynamics in a singularity-free formulation. Simulations as well as experiments on a hardware platform show the utility in HRC contexts.

In human–robot comanipulation, virtual guides are an important tool used to assist the human worker as they constrain the movement of the robot to improve the task accuracy and to avoid undesirable effects, such as collisions with the environment. Consequently, the physical effort and cognitive overload are reduced during accomplishment of comanipulative tasks. However, the construction of virtual guides often requires expert knowledge and modeling of the task, which restricts the usefulness of virtual guides to scenarios with fixed constraints. Moreover, few approaches have addressed the implementation of virtual guides enforcing orientation constraints and, when done, these approaches have treated translation and orientation separately, and consequently there is no synchronization of the translational and rotational motions. To overcome these challenges and enhance the programming flexibility of virtual guides, we present a new framework that allows the user to create 6D virtual guides through XSplines which we define as a combination of Akima splines for the translation component and spherical cubic interpolation of quaternions for the orientation component. For complex tasks, the user is able to initially define a 3D virtual guide and then use this assistance in translational motion to concentrate only on defining the orientations along the path. It is also possible for the user to modify a particular point or portion of a guide while being assisted by it. We demonstrate in an industrial scenario that these innovations provide an intuitive solution to extend the use of virtual guides to 6 degrees of freedom and increase the human worker’s comfort during the programming phase of these guides in an assisted human–robot comanipulation context.

In this paper, we propose a novel unified framework for virtual guides. The human–robot interaction is based on a virtual robot, which is controlled by the admittance control. The unified framework combines virtual guides, control of the dynamic behavior, and path tracking. Different virtual guides and active constraints can be realized by using dead-zones in the position part of the admittance controller. The proposed algorithm can act in a changing task space and allows selection of the tasks-space and redundant degrees-of-freedom during the task execution. The admittance control algorithm can be implemented either on a velocity or on acceleration level. The proposed framework has been validated by an experiment on a KUKA LWR robot performing the Buzz-Wire task.

The progressive automation framework allows the seamless transition of a robot from kinesthetic guidance to autonomous operation mode during programming by demonstration of discrete motion tasks. This is achieved by the synergetic action of dynamic movement primitives (DMPs), virtual fixtures, and variable impedance control. The proposed DMPs encode the demonstrated trajectory and synchronize with the current demonstration from the user so that the reference generated motion follows the human’s demonstration. The proposed virtual fixtures assist the user in repeating the learned kinematic behavior but allow penetration so that the user can make modifications to the learned trajectory if needed. The tracking error in combination with the interaction forces and torques is used by a variable stiffness strategy to adjust the progressive automation level and transition the leading role between the human and the robot. An energy tank approach is utilized to apply the designed controller and to prove the passivity of the overall control method. An experimental evaluation of the proposed framework is presented for a pick and place task and results show that the transition to autonomous mode is achieved in few demonstrations.

Cooperative transportation by human and robotic coworkers constitutes a challenging research field that could lead to promising technological achievements. Toward this direction, the present work demonstrates that, under a leader–follower architecture, where the human determines the object’s desired trajectory, complex cooperative object manipulation with minimal human effort may be achieved. More specifically, the robot estimates the object’s desired motion via a prescribed performance estimation law that drives the estimation error to an arbitrarily small residual set. Subsequently, the motion intention estimation is utilized in the object dynamics to determine the interaction force between the human and the object. Human effort reduction is then achieved via an impedance control scheme that employs the aforementioned estimations. The feedback relies exclusively on the robot’s force/torque, position as well as velocity measurements at its end effector, without incorporating any other information on the task. Moreover, an adaptive control scheme is adopted to relax the need for exact knowledge of the object dynamics. Finally, an extension for multiple robotic coworkers is studied and verified via simulation, while extensive experimental results for the single robot case clarify the proposed method and corroborate its efficiency.

Performing actions in a timely manner is an indispensable aspect in everyday human activities. Accordingly, it has to be present in robotic systems if they are going to seamlessly interact with humans. The current work addresses the problem of learning both the spatial and temporal characteristics of human motions from observation. We formulate learning as a mapping between two worlds (the observed and the action ones). This mapping is realized via an abstract intermediate representation termed “Latent Space.” Learned actions can be subsequently invoked in the context of more complex human–robot interaction (HRI) scenarios. Unlike previous learning from demonstration (LfD) methods that cope only with the spatial features of an action, the formulated scheme effectively encompasses spatial and temporal aspects. Learned actions are reproduced under the high-level control of a time-informed task planner. During the implementation of the studied scenarios, temporal and physical constraints may impose speed adaptations in the reproduced actions. The employed latent space representation readily supports such variations, giving rise to novel actions in the temporal domain. Experimental results demonstrate the effectiveness of the proposed scheme in the implementation of HRI scenarios. Finally, a set of well-defined evaluation metrics are introduced to assess the validity of the proposed approach considering the temporal and spatial consistency of the reproduced behaviors.

The enhanced dexterity and manipulability offered by master–slave teleoperated surgical systems have significantly improved the performance and safety of minimally invasive surgeries. However, effective manipulation of surgical robots is sometimes limited due to the mismatch between the slave and master robots’ kinematics and workspace. The purpose of this paper is first to formulate a quantifiable measure of the combined master–slave system manipulability. Next, we develop a null-space controller for the redundant master robot that employs the proposed manipulability index to enhance the performance of teleoperation tasks by matching the kinematics of the redundant master robot with the kinematics of the slave robot. The null-space controller modulates the redundant degrees of freedom of the master robot to reshape its manipulability ellipsoid (ME) towards the ME of the slave robot. The ME is the geometric interpretation of the kinematics of a robot. By reshaping the master robot’s manipulability, we match the master and slave robots’ kinematics. We demonstrate that by using a redundant master robot, we are able to enhance the master–slave system manipulability and more intuitively transfer the slave robot’s dexterity to the user. Simulation and experimental studies are performed to validate the performance of the proposed control strategy. Results demonstrate that by employing the proposed manipulability index, we can enhance the user’s control over the force/velocity of a surgical robot and minimize the user’s control effort for a teleoperated task.