Efficient, adaptive and reliable visuomotor control system is crucial to enable robots to display flexibility in the face of changes in the environment. This paper takes inspiration in human eye-arm-hand coordination ...
详细信息
Efficient, adaptive and reliable visuomotor control system is crucial to enable robots to display flexibility in the face of changes in the environment. This paper takes inspiration in human eye-arm-hand coordination pattern to develop an equivalently robust robot controller. We recorded gaze, arm, hand, and trunk data from human subjects in reaching and grasping scenarios with/without obstacle in the workspace. An eye-arm-hand controller is developed, based on our extension of Coupled Dynamical systems (CDS). We exploit the time-invariant properties of the CDS to allow fast adaptation to spatial and temporal perturbations during task completion. CDS global stability guarantees that the eye, the arm and the hand will reach the target in retinal, operational and grasp space respectively. When facing perturbations, the system can re-plan its actions almost instantly, without the need for an additional planning module. Coupling profiles for eye-arm and arm-hand systems can be modulated allowing to adjust the behavior of each slave system with respect to control signals flowing from the corresponding master system. We show how the CDS eye-arm-hand control framework can be used to handle the presence of obstacles in the workspace. The eye-arm-hand controller is validated in a series of experiments conducted with the iCub robot.
Programming by Demonstration offers an intuitive framework for teaching robots how to perform various tasks without having to preprogram them. It also offers an intuitive way to provide corrections and refine teaching...
详细信息
Programming by Demonstration offers an intuitive framework for teaching robots how to perform various tasks without having to preprogram them. It also offers an intuitive way to provide corrections and refine teaching during task execution. Previously, mostly position constraints have been taken into account when teaching tasks from demonstrations. In this work, we tackle the problem of teaching tasks that require or can benefit from varying stiffness. This extension is not trivial, as the teacher needs to have a way of communicating to the robot what stiffness it should use. We propose a method by which the teacher can modulate the stiffness of the robot in any direction through physical interaction. The system is incremental and works online, so that the teacher can instantly feel how the robot learns from the interaction. We validate the proposed approach on two experiments on a 7-Dof Barrett WAM arm.
Non-linear dynamical systems (DS) have been used extensively for building generative models of human behavior. Their applications range from modeling brain dynamics to encoding motor commands. Many schemes have been p...
详细信息
ISBN:
(纸本)9781627480031
Non-linear dynamical systems (DS) have been used extensively for building generative models of human behavior. Their applications range from modeling brain dynamics to encoding motor commands. Many schemes have been proposed for encoding robot motions using dynamical systems with a single attractor placed at a predefined target in state space. Although these enable the robots to react against sudden perturbations without any re-planning, the motions are always directed towards a single target. In this work, we focus on combining several such DS with distinct attractors, resulting in a multi-stable DS. We show its applicability in reach-to-grasp tasks where the attractors represent several grasping points on the target object. While exploiting multiple attractors provides more flexibility in recovering from unseen perturbations, it also increases the complexity of the underlying learning problem. Here we present the Augmented-SVM (A-SVM) model which inherits region partitioning ability of the well known SVM classifier and is augmented with novel constraints derived from the individual DS. The new constraints modify the original SVM dual whose optimal solution then results in a new class of support vectors (SV). These new SV ensure that the resulting multi-stable DS incurs minimum deviation from the original dynamics and is stable at each of the attractors within a finite region of attraction. We show, via implementations on a simulated 10 degrees of freedom mobile robotic platform, that the model is capable of real-time motion generation and is able to adapt on-the-fly to perturbations.
In this paper, we derive a probabilistic registration algorithm for object modeling and tracking. In many robotics applications, such as manipulation tasks, nonvisual information about the movement of the object is av...
详细信息
In this paper, we derive a probabilistic registration algorithm for object modeling and tracking. In many robotics applications, such as manipulation tasks, nonvisual information about the movement of the object is available, which we will combine with the visual information. Furthermore we do not only consider observations of the object, but we also take space into account which has been observed to not be part of the object. Furthermore we are computing a posterior distribution over the relative alignment and not a point estimate as typically done in for example Iterative Closest Point (ICP). To our knowledge no existing algorithm meets these three conditions and we thus derive a novel registration algorithm in a Bayesian framework. Experimental results suggest that the proposed methods perform favorably in comparison to PCL [1] implementations of feature mapping and ICP, especially if nonvisual information is available.
We address the problem of representations for anthropomorphic robot hands and their suitability for use in methods for learning or control. We approach hand configuration from the perspective of ultimate hand function...
详细信息
We address the problem of representations for anthropomorphic robot hands and their suitability for use in methods for learning or control. We approach hand configuration from the perspective of ultimate hand function and propose 2 parameterizations based on the ability of the hand to engage oppositional forces. These parameters can be extracted from grasp examples making them suitable for use in practical learning-from-demonstration frameworks. We propose a qualitative method to span hand functional space in a principled manner. This is used to construct a grasp set for evaluation and a qualitative baseline metric derived from human experience. Our results from human grasp data show that hand representations based on shape are not able to disambiguate hand-function. However, those based on hand-opposition primitives result in the widest separations among grasps that have radically different functions and can even clearly separate grasps whose functions overlap a great degree. We trust that these “functional parameterizations” can bridge the contrasting goals of task-oriented robotic grasping, that of controlling a dexterous robot hand to manifest hand-shape but with the ability to exercise specific hand-function.
We integrate software components that allow efficient and successful grasping of kitchenware objects. The contributed components include: The object pose detector, the gripper reaching motion and the grasp hypothesis ...
详细信息
We integrate software components that allow efficient and successful grasping of kitchenware objects. The contributed components include: The object pose detector, the gripper reaching motion and the grasp hypothesis selection. The object pose detector of Drost et. al. [10] is improved, considering rotationally symmetric objects. The reaching motion execution combines two independent dynamical systems: The approach direction system and its tangent space [21]. The coupling provides a robust reaching component that copes with several gripper configurations. The grasp hypothesis selection filters the object poses by considering the table orientation.
In the canonical Robot learning from Demonstration scenario a robot observes performances of a task and then develops an autonomous controller. Current work acknowledges that humans may be suboptimal demonstrators and...
详细信息
ISBN:
(纸本)9781450305617
In the canonical Robot learning from Demonstration scenario a robot observes performances of a task and then develops an autonomous controller. Current work acknowledges that humans may be suboptimal demonstrators and refines the controller for improved performance. However, there is still an assumption that the demonstrations are successful examples of the task. We here consider the possibility that the human has failed, and propose a model to minimize the possibility of the robot making the same mistakes.
The canonical Robot learning from Demonstration scenario has a robot observing human demonstrations of a task or behavior in a few situations, and then developing a generalized controller. Current work further refines...
详细信息
The canonical Robot learning from Demonstration scenario has a robot observing human demonstrations of a task or behavior in a few situations, and then developing a generalized controller. Current work further refines the learned system, often to perform the task better than the human could. However, the underlying assumption is that the demonstrations are successful, and are appropriate to reproduce. We, instead, consider the possibility that the human has failed in their attempt, and their demonstration is an example of what not to do. Thus, instead of maximizing the similarity of generated behaviors to those of the demonstrators, we examine two methods that deliberately avoid repeating the human’s mistakes.
Nowadays, programming by demonstration (PbD) has become an important paradigm for policy learning in robotics [3]. The idea of having robots capable of learning from humans through natural communication means is indee...
详细信息
Nowadays, programming by demonstration (PbD) has become an important paradigm for policy learning in robotics [3]. The idea of having robots capable of learning from humans through natural communication means is indeed fascinating. As an extension of the traditional PbD learning scheme, where robots only learn by observing a human teacher, our work follows the recently suggested principle of policy refinement and reuse through interactive corrective feedback [1].
A current trend in robotics is to define robot tasks using a combination of superimposed motion patterns. For maximum versatility of such motion patterns, they should be easily and efficiently adaptable for situations...
详细信息
A current trend in robotics is to define robot tasks using a combination of superimposed motion patterns. For maximum versatility of such motion patterns, they should be easily and efficiently adaptable for situations beyond those for which the motion was originally designed. In this work, we show how a challenging minigolf-like task can be efficiently learned by the robot using a basic hitting motion model and a task-specific adaptation of the hitting parameters: hitting speed and hitting angle. We propose an approach to learn the hitting parameters for a minigolf field using a set of provided examples. This is a non-trivial problem since the successful choice of hitting parameters generally represent a highly non-linear, multi-valued map from the situation-representation to the hitting parameters. We show that by limiting the problem to learning one combination of hitting parameters for each input, a high-performance model of the hitting parameters can be learned using only a small set of training data. We compare two statistical methods, Gaussian Process Regression (GPR) and Gaussian Mixture Regression (GMR) in the context of inferring hitting parameters for the minigolf task. We validate our approach on the 7 degrees of freedom Barrett WAM robotic arm in both a simulated and real environment.
暂无评论