the operator to choose the most comfortable force combmaOf several possible forms of human-robot collaborative manipulation, we focus on the case where the human and the robot jointly manipulate a common load. In our formulation, the robot’s role is to provide a constraint surface to guide the motion of the load. The value of this form of interaction, in terms of ergonomics, accuracy, or speed,...

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain-machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, ...

Humans are often able to generalize knowledge learned from a single exemplar. In this paper, we present a novel integration of mental simulation and analogical generalization algorithms into a cognitive robotic architecture that enables a similarly rudimentary generalization capability in robots. Specifically, we show how a robot can generate variations of a given scenario and then use the resu...

Existing approaches for learning to control a robot arm rely on supervised methods where correct behavior is explicitly given. It is di cult to learn to avoid obstacles using such methods, however, because examples of obstacle avoidance behavior are hard to generate. This paper presents an alternative approach that evolves neural network controllers through genetic algorithms. No input/output e...

The octopus arm presents peculiar features, like the capability of bending in all directions, producing fast elongations, and varying its stiffness. Such features are very attractive from a robotics point of view. In the octopus, these unique motor capabilities are given by the peculiar muscular structure of the octopus arm, named muscular hydrostat, that creates a sort of antagonistic mechanis...

This paper describes the development of a chess-playing robot called MarineBlue. This robot consists of three components: a computer vision component to recognize chess board situations, a chess engine component to compute new moves and a robot control component to execute these moves by means of a robot arm. In the paper, we focus on the algorithms that have been used to implement the computer...

This paper describes the implementation of reex action for the arm of the humanoid robot Cog [5]. A set of biologically inspired postural primitives are used to create the arm motion. The primitives are combined in di erent ways to achieve reaching with grasping and withdrawal reexes, allowing the arm to interact safely with both objects and people. This paper describes the re exes, the biologi...

This paper presents strategies for point-to-point reactionless manipulation of a satellite mounted dual-arm robotic system for capture of tumbling orbiting objects, such as out-ofcommission satellites and space debris. Use of the dual-arm robot could be more effective than the single arm when there is no provision for a grapple fixture or the object is tumbling. The dual arms can also provide d...

Robotic manipulators are becoming a very common tool in modern industries and research laboratories. In order to successfully execute a given task a control software is necessary that sends and tracks appropriate orders to the robot arm. This paper presents the design principles of a general software framework capable to control any robot arm with any set of sensors. A possible implementation o...

In traditional teleoperation systems, the operator is saddled with two distinct tasks: 1) move the robot arm to its desired position, and 2) avoid obstacles that can obstruct the robot arm manipulator. To accomplish these tasks, an area of current teleoperation research is involved with providing the operator with as much input information about the task site as possible using, for example, ste...