This paper proposes a novel method of utilising guide policies in Reinforcement Learning problems; Contextual Online Imitation Learning (COIL). This paper demonstrates that COIL can offer improved performance over both offline Imitation Learning methods such as Behavioral Cloning, and also Reinforcement Learning algorithms such as Proximal Policy Optimisation which do not take advantage of existing guide policies. An important characteristic of COIL is that it can effectively utilise guide policies that exhibit expert behavior in only a strict subset of the state space, making it more flexible than classical methods of Imitation Learning. This paper demonstrates that through using COIL, guide policies that achieve good performance in sub-tasks can also be used to help Reinforcement Learning agents looking to solve more complex tasks. This is a significant improvement in flexibility over traditional Imitation Learning methods. After introducing the theory and motivation behind COIL

This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor intentions by using data from inertial measurement units. The deep neural network architectures are convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The input to the architectures are features in the time domain, which have been derived either from one inertial measurement unit placed on the upper right leg of ten healthy subjects, or two inertial measurement units placed on both the upper and lower right leg of ten healthy subjects. The study shows that a WaveNet, i.e., a full convolutional neural network, achieves a peak F1-score of 87.17% in the case of one IMU, and a peak of 97.88% in the case of two IMUs, with a 5-fold cross-validation.

This paper presents the autonomous battery exchange operation for small scale UAVs, using a mobile ground base that carries a robotic arm and a service station containing the battery exchange mechanism. The goal of this work is to demonstrate the means to increase the autonomy and persistence of robotic systems without requiring human intervention. The design and control of the system and its components are presented in detail, as well as the collaborative software framework used to plan and execute complex missions. Finally, the results of autonomous outdoor experiments are presented, in which the ground rover successfully localizes, retrieves, services, and deploys the landed UAV, proving its capacity to extend and enhance autonomous operations.

Duchenne muscular dystrophy leaves patients with severe dependency on health care. In an effort to increase independence and quality of life, active exoskeletons are developed to support activities of daily living. This study is dedicated to the development and assessment of three different admittance control algorithms for a trunk supporting robot; a law with constant parameters, a law with added feed-forward force, and a law with variable parameters. A Fitts'-like experiment with 12 healthy subjects was performed to compare the control laws. The results show decreased movement times for the feedforward and variable admittance controllers with respect to the standard admittance.

This paper presents the mechatronic design of a robotic arm that is mounted on a ground rover and used to deploy and recover small-scale unmanned aerial vehicles. The arm and rover are part of a network of collaborative robotic agents aiming to enhance current rescue operations by supporting human operators without burdening them with servicing tasks. The robust autonomy of the system, guaranteed in part through the addition of this robotic arm, is a main contributing factor. Design requirements are derived from the context of the rescue mission and a kinematic analysis is provided that leads to a customized design, including variable stiffness joints for compliant interaction with the environment. Experiments demonstrate the system's ability to perform the required Cartesian trajectory control and manipulation tasks, and to achieve a desired variable end-effector compliance.

The paper presents a control method to catch a moving object with a joint actuated by means of a variable stiffness actuator. The controller is designed such that the variable stiffness joint acts as a virtual damper that absorbs the kinetic energy of the moving object. The virtual damping and the output stiffness of the variable stiffness actuator are the control variables. To obtain a critically damped system, the damping coefficient is scheduled on both the output stiffness and the inertia of the system. Experiments on the rotational variable stiffness actuator vsaUT-II validate the control method.

This paper proposes a modeling method for generic compliant robotic manipulators. It is based on graph theory and the port-Hamiltonian formalism, which allows a modular approach to the interconnection of rigid bodies with compliant actuators by means of kinematic pairs. This modularity enables a simple and straight-forward adaption the model when a manipulator's actuator morphology is changed. An example of a spatial three degree-of-freedom manipulator shows that this modeling method is more suitable for modeling changes in actuator placement than the traditional Euler-Lagrange method.

This paper proposes a control architecture for a fleet of unmanned aerial vehicles that is responsible for handling the events that take place in a given area. The architecture guarantees that each event is handled by the required number of vehicles in the shortest time, while the rest of the fleet is optimally distributed in order to achieve an optimal coverage of the area. Each vehicle is steered to the specified location by a path planner that follows the shortest path while avoiding collisions. The control architecture has been validated both in simulations and in experiments on a fleet of three vehicles.

In this paper a robust PID controller for quadrotor unmanned aerial vehicles is proposed that uses the parameter space approach. Stability and robustness analyses are carried out in the controller parameter space to determine a set of stable controller gains that guarantee also robustness against system parameter uncertainties. Additionally, the trade-off between robustness and performance is included in the control gain choice. Experimental results validate the proposed approach, where the robust behavior of a quadrotor is shown for step response and path following.

The increasing use of Variable Stiffness Actuators (VSAs) in robotic joints is helping robots to meet the demands of human-robot interaction, requiring high safety and adaptability. The key feature of a VSA is the ability to exploit internal elastic elements to obtain a variable output stiffness. These allow the joints to store mechanical energy supplied through interaction with the environment and make the system more robust, efficient, and safe. This paper discusses the design of leaf springs for a sub-class of VSAs that use variable lever arm ratios as means to change their output stiffness. Given the trade-off between compactness and the maximum energy storage capacity, the internal springs' dimensions and material choice are assessed through a theoretical analysis and practical experiments.

The paper focuses on the mechatronic design of a robotic manipulator that is meant to be mounted on an Unmanned Aerial Vehicle (UAV) and to be used in industrial applications, for both aerial inspection by contact and aerial manipulation. The combination of an UAV and the robotic manipulator realizes the aerial manipulator. The robotic manipulator is designed to be versatile so that the aerial manipulator can perform both trajectory tracking in free flight and physical interaction. Moreover, the robotic manipulator can be mounted on commercially available UAVs a modular way without interfering with the existing onboard control architecture. Experimental test are validating the overall mechatronic design.

This paper proposes a modeling method for generic serial-chain compliant robotic manipulators. It is based on graph theory and port-Hamiltonian systems, which allows a modular approach to the interconnection of rigid bodies with compliant actuators by means of kinematic pairs. This modularity allows a very simple and straight-forward change in a manipulator's actuator morphology. An example of a two degree of freedom planar manipulator shows that this modeling method is more suitable for modeling changes in actuator placement than traditional Euler-Lagrange models.

This paper proposes a semi-autonomous bilateral control architecture for unmanned aerial vehicles. During autonomous navigation, a human operator is allowed to assist the autonomous controller of the vehicle by actively changing its navigation parameters to assist it in critical situations, such as navigating through narrow paths. The overall goal of the controller is to combine the stability and precision of an autonomous control with the cognitive abilities of a human operator, only when strictly required for the accomplishment of a task. The control architecture has been validated through simulations and experiments.

In robotics, differential mechanisms are widely used when lightweightness and compactness are a requisite for the robot design. Moreover, the last decades have seen the rise of (variable) compliant acuators as important elements to perform safe interaction and dynamic tasks. This paper introduces a Variable Stiffness Differential Drive (VSDD), i.e., a differential transmissions with variable stiffness actuators (VSAs), and presents a dynamic analysis. The analysis shows that, when variable stiffness actuators are used in coupled differential transmissions, the allowable stiffness range at the output of the system depends on the position of the springs inside the device. In particular, independent output joint stiffness can be obtained by dislocating the actuation from the elastic elements.

This paper presents a new free-flight controller for aerial manipulators, unmanned aerial vehicles endowed with a robotic manipulator. The control strategy exploits the dynamics of the manipulator to improve the tracking performance and maneuverability of the UAV by expanding its flight envelop. The controller increases the spectrum of deployable manipulators, which otherwise are limited to be light-weighted manipulators and with a dynamics that do not significantly affect the UAV. The effectiveness and applicability of the proposed controller is verified through simulations and experiments.

In this paper, a modular method of modeling compliant robotic systems using graph theory is treated. Graph theoretic analyses ensure a structured way of describing a system and allow a straightforward extension to more complex systems. The graph models of a series elastic actuator, a variable stiffness actuator and a multi degrees of freedom compliant system are derived. These systems are controlled using an optimal control law that is able to find the optimal stiffness setting and distribution to accomplish a certain task. A case study shows a multi degrees of freedom compliant system which is required to resonate at the output and to accomplish a back-and-forth motion. It is shown that a constant optimal stiffness is found in the resonance simulation, and a varying optimal stiffness in case of the back-and-forth task. This indicates that this methodology can assist in finding an optimal stiffness distribution of complex robotic systems for a given task.

This paper presents a versatile control architecture for aerial robots in interactive tasks. The control architecture is characterized by its unique capability of varying the apparent impedance of the controlled aerial robot as well as the interaction force, when in contact. This work finds its way in various applications where different impedance and interaction force controllers provide high task performances as well as safety. The feasibility and effectiveness of the proposed controller are demonstrated by experimental results preformed on a quadrotor aerial robot.

In this study, we present the implementation of the controller for adapting the energy storage capacity of the WalkMECH according to the different walking speeds and gait characteristics of an amputee. Since the main aim is to keep the design both mechanically and metabolically energy-efficient, the actuation system is designed based on the minimal actuation principle. The overall system, called WalkMECHadapt, is evaluated with the experimental test set-up with a healthy subject. Test results show that the system is working sufficiently for adapting the energy storage capacity of the WalkMECHadapt thanks to the simple nature of the controller architecture.

This paper presents a generic hierarchical passive teleoperation control architecture that effectively addresses the issues of workspace incompatibility and precision, as well as other classical and peculiar challenges. More specifically, the control scheme consists of a user-defined variable scale mapping, a variable impedance master controller, and a virtual slave system. The port-based modeling framework has been extensively used in our formulation, providing more insight about energetic flows in the system that are particularly useful for the design of a passive controlled system. Moreover, various practical considerations that are required for the effective usage of the control architecture are discussed. The achieved better precision and overall task performance have been validated and verified by elaborate simulations and experiments.

The bipedal spring-loaded inverted pendulum (SLIP) model captures characteristic properties of human locomotion, and it is therefore often used to study human-like walking. The extended variable spring-loaded inverted pendulum (V-SLIP) model provides a control input for gait stabilization and shows robust and energy-efficient walking patterns. This work presents a control strategy that maps the conceptual V-SLIP model on a realistic model of a bipedal robot. This walker implements the variable leg compliance by means of variable stiffness actuators in the knees. The proposed controller consists of multiple levels, each level controlling the robot at a different level of abstraction. This allows the controller to control a simple dynamic structure at the top level and control the specific degrees of freedom of the robot at a lower level. The proposed controller is validated by both numeric simulations and preliminary experimental tests.

In this paper, we present the design, simulation and experimental validation of a control architecture for an unmanned aerial vehicle endowed with a manipulation system and interacting with a remote environment. The goal of this work is to show that the interaction control allows the manipulator to track a desired force, normal to a vertical wall, while still maintaining the possibility of moving on the wall. The control strategy has been implemented and validated in simulations and experiments on the manipulator standalone, i.e., attached to a fixed base, and on the manipulator attached to the aerial vehicle.

In this work, we propose a hybrid model for a bipedal walker with controlled variable leg stiffness, and a control strategy for stable gait control. The control reference is a passive gait of the limit-case bipedal spring-loaded inverted pendulum model with massless feet, ensuring that the gait is close to the ideal passive gait and thus aiming for energy efficiency. The effectiveness of the controller is demonstrated with numerical simulation results. From the results a theoretical cost of transport is calculated, showing that the control strategy is indeed energy efficient.

This paper proposes a modified impedance control strategy for a generic robotic system that can interact with an unknown environment or can be moved by a human. The controller makes use of a virtual mass, coupled to the robotic system, which allows for stable interaction. The focus is mainly on unmanned aerial vehicles that are required to get into contact with the environment to perform a specific task on it and that can be shifted by humans. The control architecture is validated both in simulations, on a 1-dimensional benchmark, and in experiments on a real quadrotor flying vehicle.

This video presents experiments conducted within the final review meeting demonstration session of the AIRobots project. AIRobots started at 2010 and the final review meeting took place on 22 of March, 2013. The presented experiments cover a wide area of the challenges related with aerial industrial inspection. In particular, multiple test-cases related with both vision-based and contact-based inspection and in general physical interaction are shown. It is highlighted that these experiments were recorded live during the project demonstration and evaluation process.

This paper describes the theory and practice for a stable haptic teleoperation of a flying vehicle. It extends passivity-based control framework for haptic teleoperation of aerial vehicles in the longest intercontinental setting that presents great challenges. The practicality of the control architecture has been shown in maneuvering and obstacle-avoidance tasks over the internet with the presence of significant time-varying delays and packet losses. Experimental results are presented for teleoperation of a slave quadrotor in Australia from a master station in the Netherlands. The results show that the remote operator is able to safely maneuver the flying vehicle through a structure using haptic feedback of the state of the slave and the perceived obstacles.

In this paper, the vsaUT-II, a novel rotational variable stiffness actuator, is presented. As the other designs in this class of actuation systems, the vsaUT-II is characterized by the property that the output stiffness can be changed independently of the output position. It consists of two internal elastic elements and two internal actuated degrees of freedom. The mechanical design of the vsaUT-II is such that the apparent output stiffness can be varied by changing the transmission ratio between the elastic elements and the output. This kinematic structure guarantees that the output stiffness can be changed without changing the potential energy stored internally in the elastic elements. This property is validated in simulations with the port-based model of the system and in experiments, through a proper control law design, on the prototype.

In this paper, we present the mechanical design and modeling of a manipulation system for unmanned aerial vehicles, which have to physically interact with environments and perform ultrasonic non-destructive testing experiments and other versatile tasks at unreachable locations for humans. The innovation of the prototype lies in the use of a three degrees of freedom Delta robotic manipulator together with a nondestructive testing end-effector, realized by a Cardan gimbal that allows the ultrasonic sensor to compliantly interact with the remote environment. The Cardan gimbal is endowed with a small actuator for the roll motion of the end-effector, a compliant element in the direction of interaction and two passive rotational degrees of freedom with defined equilibria to overcome gravity and to define a stable zero reference. Simulation results of a ducted-fan unmanned aerial vehicle interacting with a wall validate the overall mechanical design.

In this paper, we present haptic teleoperation of underactuated unmanned aerial vehicles by providing a multidimensional generalization of the virtual slave concept. The proposed control architecture is composed of high-level and low-level controllers. The high-level controller commands the vehicle to accomplish specific tasks and renders both the state and the environment of the vehicle to the operator through haptic feedback. The low-level controller interprets the command signals from the operator, regulates the dynamics of the vehicle and feeds back its state to the high-level loop. Passivity of the teleoperation loop is always ensured independently of the choice of implementation of the low-level controller and the configuration of the flying hardware by a passivity-enforcing supervisor, which associates every action of the slave with an energy expense that can only be made available from a multi-state energy tank. The effectiveness of the proposed algorithm is illustrated with simulations and experimental tests.

In this paper, we present a haptic teleoperation control algorithm for unmanned aerial vehicles, applying a kinetic scrolling-based position mapping. The proposed algorithm overcomes the master workspace limitations and enables to teleoperate the aerial vehicle in unbounded workspace in a fast and intuitive manner. Moreover, it provides high precision to teleoperation tasks. Simulation and experimental results validating the applicability and effectiveness of the proposed algorithm are also presented.

Variable stiffness actuators realize highly dynamic systems, whose inherent mechanical compliance can be properly exploited to obtain a robust and energy-efficient behavior. The paper presents a control strategy for variable stiffness actuators with the primarily goal of tracking a limit cycle trajectory and a desired stiffness, which is a function of the output position of the actuator. The proposed controller guarantees that the load, attached at the output of the actuation system, asymptotically tracks the desired cyclic motion and the desired stiffness even in presence of external disturbances. Experimental tests on the rotational variable stiffness actuator vsaUT-II validate the control strategy.

This paper focuses on the modeling and control of a flying robot. The complete system, composed of a quadrotor unmanned aerial vehicle and a custom-made manipulator, has been designed for remote inspection by contact of industrial plants. The goal of this paper is to show the dynamical characteristics of the flying robot during tasks that require physical interaction, and to determine a control strategy that allows to safely interact with unknown environments. The methodology has been implemented on a real prototype and tested in an indoor area. Experimental results validate the proposed controller and show its effectiveness.

This video presents practical realizations and comparison between three different haptic tele-control algorithms of aerial vehicles. These strategies, besides addressing the classical issues of stability and transparency, provide different alternatives for overcoming challenges that are peculiar to haptic teleoperation of aerial vehicles. The experimental results show the performance and effectiveness of the proposed control algorithms even in the presence of significant time delays.

This paper deals with the bilateral teleoperation of underactuated aerial robots by means of a haptic interface. In particular, we propose a switching-based state mapping and control algorithm between a rate-based passive controller, which addresses the workspace incompatibility between the master and slave systems, and a pose-based passive controller, which is required for precise operation. The overall control architecture provides the possibility of changing the scaling factor of the mapping online, while preserving the passivity of the complete system. In our formulation, we use the port-Hamiltonian framework, in which energetic considerations play a determinant role for passivity and, thereby stability of the overall system. Simulation and experimental results illustrating the effectiveness of the proposed algorithm are also presented.

Most of today's robots have rigid structures and actuators requiring complex software control algorithms and sophisticated sensor systems in order to behave in a compliant and safe way adapted to contact with unknown environments and humans. By studying and constructing variable impedance actuators and their control, we contribute to the development of actuation units which can match the intrinsic safety, motion performance and energy efficiency of biological systems and in particular the human. As such, this may lead to a new generation of robots that can co-exist and co-operate with people and get closer to the human manipulation and locomotion performance than is possible with current robots.

Variable stiffness actuators realize a novel class of actuators, which are capable of changing the apparent output stiffness independently of the output position. This is mechanically achieved by the internal introduction of a number of elastic elements and a number of actuated degrees of freedom (DOFs), which determine how the elastic elements are sensed at the output. During the nominal behavior of these actuators, the power flow from the internal actuated DOFs can be such that energy is undesirably stored in the elastic elements because of the specific kinematic structure of the actuator. In this study, we focus on the analysis of the power flow in variable stiffness actuators. More specifically, the analysis is restricted to the kinematic structure of the actuators, in order to show the influence of the topological structure on the power flow, rather than on the realization choices. We define a measure that indicates the ratio between the total amount of power that is injected by the internal actuated DOFs and the power that is captured by the internal elastic elements which, therefore, cannot be used to do work on the load. In order to define the power-flow ratio, we exploit a generic port-based model of variable stiffness actuators, which highlights the kinematic properties of the design and the power flows in the actuator structure.

In this paper, we propose a generic model and a controller design for a class of underactuated aerial vehicles, namely for unmanned aerial vehicles whose primary support against gravity is thrust. The approach followed is based on energetic consideration and uses the formalisms of port-Hamiltonian systems and bond graphs. The controller is designed for both stabilization during hovering and for trajectory tracking tasks. The competency of the model and the performance of the controller are validated in simulation.

In this work, we present the design and the implementation of an innovative knee locking mechanism for a dynamically walking robot. The mechanism consists of a four-bar linkage that realizes a mechanical singularity for locking the knee when the leg is in the extended position. Once extended, the knee remains locked without energy consumption, while unlocking it only costs a small amount of energy. Tests showed that the robot walks robustly and that the energy consumption of the new system is low.

Variable stiffness actuators are a particular class of actuators that is characterized by the property that the apparent output stiffness can be changed independent of the output position. To achieve this, variable stiffness actuators consist of a number of elastic elements and a number of actuated degrees of freedom, which determine how the elastic elements are perceived at the actuator output. Changing the apparent output stiffness is useful for a broad range of applications, which explains the increasing research interest in this class of actuators. In this paper, a generic, port-based model for variable stiffness actuators is presented, with which a wide variety of designs can be modeled and analyzed. From the analysis of the model, it is possible to derive kinematic properties that variable stiffness actuator designs should satisfy in order to be energy efficient. More specifically, the kinematics should be such that the apparent output stiffness can be varied without changing the potential energy that is stored in the internal elastic elements. A concept design of an energy-efficient variable stiffness actuator is presented and implemented. Simulations of the model and experiments on the realized prototype validate the design principle.

In this paper, a metric for comparing different designs of variable stiffness actuators is introduced. For the formulation of this metric, we focus on the energy efficiency of the actuators. In particular, we propose a metric that is a measure of how much energy is used by the actuator for changing the output stiffness. In order to facilitate the analysis of the energy usage, we present a port-based modeling framework, from which design criteria are derived for the optimization of the metric. Finally, the metric is interpreted in a comparison between existing actuators.

In this paper, we provide a port-based mathematical framework for analyzing and modeling variable stiffness actuators. The framework provides important insights in the energy requirements and, therefore, it is an important tool for the design of energy efficient variable stiffness actuators. Based on new insights gained from this approach, a novel conceptual actuator is presented. Simulations show that the apparent output stiffness of this actuator can be dynamically changed in an energy efficient way.

This paper introduces a novel robotic finger concept for variable impedance grasping in unstructured tasks. A brief literature survey reveals the need for minimal component designs and the benefits of impedance control schemes for interaction tasks such as grasping. The novel robotic finger concept supports these insights by combining three key features: minimal actuation, variable mechanical compliance and full manipulability. This combination of features allows for a minimal component design, while reducing control complexity and still providing required dexterity and grasping capabilities. The conceptual properties (such as variable compliance) are studied in a port-Hamiltonian framework. The framework proved to be suitable in analyzing and understanding the finger properties, which will be used for future controller design.

In this paper, we present a port-Hamiltonian model of a multi-fingered robotic hand, with soft-pads, while grasping and manipulating an object. The algebraic constraints of the interconnected systems are represented by a geometric object, called Dirac structure. This provides a powerful way to describe the non-contact to contact transition and contact viscoelasticity, by using the concepts of energy flows and power preserving interconnections. Using the port based model, an Intrinsically Passive Controller (IPC) is used to control the internal forces. Simulation results validate the model and demonstrate the effectiveness of the port-based approach.

In this study, we present the conceptual design of a fully-passive transfemoral prosthesis. The design is inspired by the power flow in human gait in order to have an energy efficient device. The working principle of the conceptual mechanism is based on three storage elements, which are responsible of the energetic coupling between the knee and the ankle joints. Design parameters of the prosthesis have been determined according to the energy absorption intervals of the human gait. Simulation results shows that the power flow of the system is comparable with human data. Finally, an initial prototype is presented as proof of concept.

This video shows the results of the project on the mechatronic development of the Twente humanoid head. The mechanical structure consists of a neck with four degrees of freedom (DOFs) and two eyes (a stereo pair system) which tilt on a common axis and rotate sideways freely providing a three more DOFs. The motion control algorithm is designed to receive, as an input, the output of a biological-inspired vision processing algorithm and to exploit the redundancy of the joints for the realization of the movements. The expressions of the humanoid head are implemented by projecting light from the internal part of the translucent plastic cover.

This paper describes the design of a motion control algorithm for a humanoid robotic head, which consists of a neck with four degrees of freedom and two eyes (a stereo pair system) that tilt on a common axis and rotate sideways freely. The kinematic and dynamic properties of the head are analyzed and modeled using screw theory. The motion control algorithm is designed to receive, as an input, the output of a vision processing algorithm and to exploit the redundancy of the system for the realization of the movements. This algorithm is designed to enable the head to focus on and to follow a target, showing human-like motions. The performance of the control algorithm has been tested in a simulated environment and, then, experimentally applied to the real humanoid head.

This paper presents a method to utilize a port-based multibody contact model for simulating dynamic interaction between irregular surfaces. The existing compliant contact model requires an analytic parametrization of the surfaces involved in the interaction, the definition of a Gauss frame in each of the contact points and initialization of the candidate contact points. The authors intend to apply this contact model for cases in which the surfaces of the 3D interacting bodies can not be described (easily) by a geometrically defined surface. Such surfaces are often represented by 3D point meshes. This implies that the surfaces of the bodies have to be reconstructed from 3D point meshes where initialization of the candidate contact points is not arbitrary. This paper proposes the reconstruction of such surfaces by means of polynomial interpolation. With the aim of having a computationally efficient simulator, the surface interpolation is restricted to small patches around the candidate contact points. To select these candidates, the proposed simulation approach is completed by using a fast (existing) collision detection algorithm. Simulation results are validating the effectiveness of the proposed modeling and simulation approach.

In robotics, the manipulation ofa prioriunknown objects involves several steps and problems that must be carefully considered and solved by proper planning and control algorithms. For example, once suitable contact points have been computed, the control system should be able to track them in the approach phase, i.e., while the relative position/orientation of the object and the gripper of the robotic system change due to the approaching movement of the robot toward the object. This correspondence paper proposes a practical method for the tracking of grasp points in image space that is based on transferring previously computed grasp points from an initial image to subsequent ones and on the analysis of the new grasp configuration. Three different options are proposed for this transference. Experimental results show the interesting practical performance of the general procedure.

The visual tracking of grasp points is an essential operation for the execution of an approaching movement of a robot arm to an object: the grasp points are used as features for the definition of the control law. This work describes a strategy for tracking grasps on planar objects based on the use of a homography. In particular, the homography is used for transferring (translating) a grasp from a view of an object to a second one, providing in this way a correspondence in the second view. The grasp tracking procedure combines the search of a new grasp with the translation and the evaluation of that grasp between object views. Results of the proposed grasp tracking strategy are shown in case of grasps computed for a two-finger and a three-finger gripper.