The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The high degree of complexity associated with humanoid robotic platforms significantly hinders the definition of accurate models. Robot learning based on human teleoperation provides suitable ways and means of meeting this challenge. Teleoperating the robot in different motion and balance tasks through a haptic interface, endows the user with the ability to "feel" the dynamics of the system...
In this paper, we develop a mechanism to detect and model the shape of a contaminant cloud boundary using air borne sensor swarms. The UAV sensors detect discrete points on the boundary of a contaminant cloud, which is used for cloud modeling. The shape of the cloud evolves with the measurement data from the UAV sensors, which in turn indicates the region where the UAVs should explore for better approximation...
Soft robotic peristaltic sorting tables are a new class of industrial robots that move objects on their surface by producing moving surface deformations. To realise such deformations, the surface layer is made of a soft material with an embedded array of actuators. In industrial automation, the array must be controlled in a way that objects on the surface of the table are transported and realigned...
Robots have been traditionally in operation away from people, for instance in industrial environments. More recently, there has been a trend for bringing robots to market for helping people. In particular, children constitute a challenging group for robot interaction, due to their curiosity and energy, as well as safety concerns. This paper describes the construction process of an external structure...
This report describes a problem involved with use of Kinect depth maps for robot picking of randomly stacked components, and also a solution to this problems. When Kinect is installed above stacked parts and processing is performed using only the obtained Kinect depth map information, there are cases when individual small metal components cannot be separately identified. So that the robot can reliably...
A number of efforts have been applied on human activity recognition such as face recognition and motion analysis. The major problems in recognition are: 1. Scale. 2. Shift. 3. Projection. Human Activities are identified by the pose of the body such as standing, sitting etc. and some of the activities are like the emotions, facial expressions etc. Generally, human activity recognition is achieved by...
The traditional six-dimensional force/torque sensor calibration method requires a lot of precision loading force and can only be off-line calibration. In this paper, to solve the problem, an online calibration and decoupling method based on the shape from motion combined with complex algorithm is proposed. It does not require accurate and redundant loading force information, and have better noise...
The paper presents a novel reactive algorithm for safe navigation of mobile robots in uncertain complex dynamic environments. The proposed law is computationally non-demanding, directly converts the current observation into the current control, and does not require measurements of the velocities, shapes, or orientations of the obstacles. It is applicable to scenes with time-varying and deforming obstacles...
Tool-use is one of the most complex object manipulation abilities of humans and robots. In this paper, we present strategies for implementing tool-use with anthropomorphic service robots. Based on the observation that human tools are specifically designed for the human body, we augment tools with handles that adapt the tool to the specifics of our robot. We develop methods for perceiving the tools...
We present a probabilistic learning framework to form object hypotheses through interaction with the environment. A robot learns how to manipulate objects through pushing actions to identify how many objects are present in the scene. We use a segmentation system that initializes object hypotheses based on RGBD data and adopt a reinforcement approach to learn the relations between pushing actions and...
This paper introduces a semantic synthesis method that enables robots to generate human-like gestures by recognizing cognitive and emotional behaviors based on a given situation. Assuming that the human cognitive process is represented as a series of associated events, we proposed a virtually touchable space associated with robotic hands. Additionally, in a humanoid robot, the motions of two arms...
This paper describes the design of a new 1-axis torque sensor that consists of two different type spokes. The sensor has three trapezoidal shape spokes and three support spokes. It serves a double purpose that the sensitivity and stiffness for driving torque. We suggest trapezoid-typed spokes rather than conventional rectangular-typed spoke for sensitivity, and support spokes are used to tolerate...
In this paper we focus on a perception system for cognitive interaction between robots and humans especially for learning to recognize objects in household environments. Therefore we propose a novel three layered framework for object learning to bridge the gap between the robot's recognition capabilities at lower neural level to the higher cognitive level of humans using the weighted fusion of multimodal...
This paper presents an object shape estimation algorithm using a sparse IR sensor array which is installed in a wheeled array system. The system is in a modular shape and each module consists of three omni wheels and an IR sensor in a triangular configuration. A flat object with unknown shape is placed on top of the wheeled array and it is transported in a certain way that the sparse sensor array...
The aim of this paper is to propose a system where complex affordance learning is bootstrapped through using pre-learned basic-affordances as additional inputs of the complex affordance predictors or as cues in selecting the next objects to explore during learning. In the first stage, the robot learns affordances in the form of developing classifiers that predict effect categories given object features...
In this paper, we study the learning mechanisms that facilitate autonomous discovery of an effective affordance prediction structure with multiple actions of different levels of complexity. A robot can benefit from a hierarchical structure where pre-learned basic affordances are used as inputs to bootstrap learning of complex affordances. In a developmental setting, links from basic affordances to...
We present a neural dynamics architecture for robotic grasping of novel objects. It closes the perception-action loop by integrating perceptual processes such as scene exploration, pose estimation, and shape classification with movement generation to reach and grasp a target object. Inspired by theories of human embodied cognition, this is achieved by interconnected dynamical systems, whose dynamical...
Previous research showed that young children sometimes fail to use information about object size and make a serious attempt to perform impossible actions on miniature objects. Such scale errors have been hypothesized to result from immaturity in the interaction of the two visual streams, namely the visual stream for action and the visual stream for perception, coupled to a lack of inhibitory control...
Robots are expected to operate autonomously in unconstrained, real-world environments. Therefore, they cannot rely on access to models of all objects in their environment, in order to parameterize object-directed actions. The robot must estimate the shape of objects in such environments, based on their perception. How to estimate an object's shape based on distal sensors, such as color- or depth cameras,...
In this paper, we present a conceptual design for a context-influenced Long-Term Memory architecture. The notion of context is used as a means to organize the information flow between the Working Memory and Long-Term Memory components. In particular, we discuss the major influence of the notion of context within the Episodic Memory on the Semantic and Procedural Memory, respectively. In other words,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.