In this paper, we propose a new approach to compliant taskspace control for high degree-of-freedom manipulators driven by positioncontrolled actuators. The actuators in our approach are back-drivable and allow to limit the torque used for position control. Traditional approaches frequently achieve compliance through redundancy resolution. Our approach not only allows to adjust compliance in the...

We extend the task-space multi-objective controllers that write as quadratic programs (QP) to handle multi-robot systems as a single centralized control. The idea is to assemble all the ‘robots’ models and their interaction task constraints into a single QP formulation. By multi-robot we mean that whatever entities a given robot will interact with (solid or articulated systems, actuated or not ...

A scheme for dynamic hybrid control of robot manipulators is presented. The design is directly achieved in task space coordinates. In this way, the inherent orthogonality between force and velocity description of tasks is preserved and overspecification is avoided in the control synthesis. A nonlinear decoupling and linearizing feedback law is obtained which yields invariant control performance...

We present an anytime algorithm that generates a collision-free configuration-space path that closely follows a desired path in task space, according to the discrete Fréchet distance. By leveraging tools from computational geometry, we approximate the search space using a cross-product graph. We use a variant of Dijkstra’s graph-search algorithm to efficiently search for and iteratively improve...

We present a manipulation planning framework that allows robots to plan in the presence of constraints on end-effector pose, as well as other common constraints. The framework has three main components: constraint representation, constraintsatisfaction strategies, and a general planning algorithm. These components come together to create an efficient and probabilistically complete manipulation ...

New definitions of force and velocity manipulability ellipsoids for multiple-arm systems are given in this paper. A suitable kinetostatic formulation for multiple cooperating arms is adopted that allows a global task space description of external and internal forces as well as absolute and relative velocities at the object level. The well-known concept of a force manipulability ellipsoid for a ...

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks and overcomes data scarcity limitations by co-learning all these tasks simultaneously to offer improved performance. We propose a novel Multi-Task Multiple K...

We describe an integrated strategy for planning, perception, state-estimation and action in complex mobile manipulation domains based on planning in the belief space of probability distributions over states using hierarchical goal regression (pre-image back-chaining). We develop a vocabulary of logical expressions that describe sets of belief states, which are goals and subgoals in the planning...

This paper presents a methodology for observing human skill by using a virtual task space constructed by the haptic virtual reality technology. First a haptic simulator developed for a 2-dimensional pegin-hole assembly operation in the virtual environment is presented. To examine the validity of the simulator, a comparison study between the peg-in-hole task using the simulator and that in the r...

To have a robot actively supporting a human during a collaborative task, it is crucial that robots are able to identify the current action in order to predict the next one. Common approaches make use of high-level knowledge, such as object affordances, semantics or understanding of actions in terms of preand post-conditions. These approaches often require hand-coded a priori knowledge, timeand ...