scholarly journals MODELING SIMULATION AND ANALYSIS OF ROBOT GRASPING POSE FOR NOVEL OBJECTS

2021 ◽  
Vol 9 (2) ◽  
pp. 195-206
Author(s):  
Dhanasekar.J, Sengottuvel. P
Keyword(s):  
Center Of Mass ◽  
End Effector ◽  
Novel Object ◽  
Modeling Simulation ◽  
Control Signals ◽  
Novel Objects ◽  
Motor Dexterity ◽  
Robot Grasping ◽  
Program Data ◽  
Unknown Object

Modern day robotics aims at bringing precision and motor dexterity of humans to machines. Many scientists are working on mimicking the attributes of a human in order to grasp different object. Initially, the robots were preprogrammed to hold different object but this method is not as effective against a novel object because the image of a novel object does not match with the pre-stored program data. Hence end effector will not be able to pick up the object or it may get damaged. In this paper, a new method is discussed on the dimension and the center of mass. The robot automatically calculates the grasping point and finds the suitable pose of the gripper to grasp the desired object. This proposed work of robot simulation is achieved using MATLAB 8.2 and Creo parametric 2.0. The robot model designed using Creo is fed as input into the MATLAB to generate control signals for the robot to grasp novel objects. By this the robot will automatically grasp a new unknown object by comparing the database already created and be able to handle the object dynamically.

scholarly journals Disfluencies signal reference to novel objects for adults but not children

2017 ◽  
Vol 45 (3) ◽  
pp. 581-609 ◽  
Author(s):  
Sarah J. OWENS ◽  
Justine M. THACKER ◽  
Susan A. GRAHAM
Keyword(s):  
Young Children ◽  
Spoken Language ◽  
The Novel ◽  
Novel Object ◽  
Filled Pauses ◽  
Novel Objects ◽  
Novel Targets ◽  
The Way ◽  
Familiar Objects

AbstractSpeech disfluencies can guide the ways in which listeners interpret spoken language. Here, we examined whether three-year-olds, five-year-olds, and adults use filled pauses to anticipate that a speaker is likely to refer to a novel object. Across three experiments, participants were presented with pairs of novel and familiar objects and heard a speaker refer to one of the objects using a fluent (“Look at the ball/lep!”) or disfluent (“Look at thee uh ball/lep!”) expression. The salience of the speaker's unfamiliarity with the novel referents, and the way in which the speaker referred to the novel referents (i.e., a noun vs. a description) varied across experiments. Three- and five-year-olds successfully identified familiar and novel targets, but only adults’ looking patterns reflected increased looks to novel objects in the presence of a disfluency. Together, these findings demonstrate that adults, but not young children, use filled pauses to anticipate reference to novel objects.

Sequential Trajectory Generation for Dynamic Multi-Contact Locomotion Synchronizing Contact

2020 ◽  
Vol 17 (01) ◽  
pp. 2050003
Author(s):  
Mitsuharu morisawa ◽  
Rafael Cisneros ◽  
Mehdi Benallegue ◽  
Iori Kumagai ◽  
Adrien Escande ◽  
...  
Keyword(s):  
Center Of Mass ◽  
Computation Method ◽  
Force Distribution ◽  
Fast Computation ◽  
Dynamic Changes ◽  
End Effector ◽  
Dynamic Simulator ◽  
Climbing Stairs ◽  
New Framework ◽  
Support Phase

This paper proposes a new framework to generate 3D multi-contact locomotion with low computation cost. The proposed framework consists of (a) the derivation of the prospect centroidal dynamics by introducing a force distribution ratio, where it can be represented with a formulation similar to the inverted pendulum’s one, and (b) the development of a fast computation method for generating a 3D center-of-mass (CoM) trajectory. Then (c) the ZMP reference is modified so that feasible contact wrench can be generated by a force distribution using the centroidal dynamics with the approximated friction cone. The proposed method allows to generate a trajectory sequentially and to change the locomotion parameters at any time even under variable CoM height. Then, the contact timing of each end-effector can be adjusted to synchronize with the actual contact with the environment by shortening or extending the desired duration of the support phase. This can be used to improve the robustness of the locomotion. The validity of the proposed method is confirmed by several numerical results in dynamic simulator: a CoM motion while changing the contact timing, a multi-contact locomotion considering a transition between biped and quadruped walking on an horizontal floor to move below obstacles. Finally, we also show a climbing stairs using handrail which requires dynamic changes of unilateral and bilateral contacts.

scholarly journals Feature Deformation Meta-Networks in Image Captioning of Novel Objects

2020 ◽  
Vol 34 (07) ◽  
pp. 10494-10501
Author(s):  
Tingjia Cao ◽  
Ke Han ◽  
Xiaomei Wang ◽  
Lin Ma ◽  
Yanwei Fu ◽  
...  
Keyword(s):  
Image Features ◽  
The Novel ◽  
Image Captioning ◽  
Novel Object ◽  
Detection Model ◽  
Novel Objects ◽  
Visual Concepts ◽  
Set Sharing ◽  
Ablation Study ◽  
Object Features

This paper studies the task of image captioning with novel objects, which only exist in testing images. Intrinsically, this task can reflect the generalization ability of models in understanding and captioning the semantic meanings of visual concepts and objects unseen in training set, sharing the similarity to one/zero-shot learning. The critical difficulty thus comes from that no paired images and sentences of the novel objects can be used to help train the captioning model. Inspired by recent work (Chen et al. 2019b) that boosts one-shot learning by learning to generate various image deformations, we propose learning meta-networks for deforming features for novel object captioning. To this end, we introduce the feature deformation meta-networks (FDM-net), which is trained on source data, and learn to adapt to the novel object features detected by the auxiliary detection model. FDM-net includes two sub-nets: feature deformation, and scene graph sentence reconstruction, which produce the augmented image features and corresponding sentences, respectively. Thus, rather than directly deforming images, FDM-net can efficiently and dynamically enlarge the paired images and texts by learning to deform image features. Extensive experiments are conducted on the widely used novel object captioning dataset, and the results show the effectiveness of our FDM-net. Ablation study and qualitative visualization further give insights of our model.

scholarly journals Novelty and Novel Objects Increase c-Fos Immunoreactivity in Mossy Cells in the Mouse Dentate Gyrus

2019 ◽  
Vol 2019 ◽  
pp. 1-16 ◽  
Author(s):  
Hannah L. Bernstein ◽  
Yi-Ling Lu ◽  
Justin J. Botterill ◽  
Helen E. Scharfman
Keyword(s):  
Protein Expression ◽  
Dentate Gyrus ◽  
Novelty Detection ◽  
Small Subset ◽  
Novel Object ◽  
Fos Protein ◽  
Novel Objects ◽  
Mossy Cell ◽  
Hilar Neurons

The dentate gyrus (DG) and its primary cell type, the granule cell (GC), are thought to be critical to many cognitive functions. A major neuronal subtype of the DG is the hilar mossy cell (MC). MCs have been considered to play an important role in cognition, but in vivo studies to understand the activity of MCs during cognitive tasks are challenging because the experiments usually involve trauma to the overlying hippocampus or DG, which kills hilar neurons. In addition, restraint typically occurs, and MC activity is reduced by brief restraint stress. Social isolation often occurs and is potentially confounding. Therefore, we used c-fos protein expression to understand when MCs are active in vivo in socially housed adult C57BL/6 mice in their home cage. We focused on c-fos protein expression after animals explored novel objects, based on previous work which showed that MCs express c-fos protein readily in response to a novel housing location. Also, MCs are required for the training component of the novel object location task and novelty-encoding during a food-related task. GluR2/3 was used as a marker of MCs. The results showed that MC c-fos protein is greatly increased after exposure to novel objects, especially in ventral DG. We also found that novel objects produced higher c-fos levels than familiar objects. Interestingly, a small subset of neurons that did not express GluR2/3 also increased c-fos protein after novel object exposure. In contrast, GCs appeared relatively insensitive. The results support a growing appreciation of the role of the DG in novelty detection and novel object recognition, where hilar neurons and especially MCs are very sensitive.

Cognitive, Developmental and Social Aspects of Responsiveness To Novel Objects in a Family Group of Marmosets (Sag Uinus Fuscicollis)

Behaviour ◽  
1979 ◽  
Vol 70 (3-4) ◽  
pp. 251-279 ◽  
Author(s):  
E.W. Menzel ◽  
Charles R. Menzel
Keyword(s):  
Home Environment ◽  
Cognitive Mapping ◽  
The Other ◽  
Social Aspects ◽  
Response Functions ◽  
Supplementary Data ◽  
Total N ◽  
Novel Object ◽  
Novel Objects ◽  
Test Objects

AbstractA breeding pair of S. fuscicollis and their young (total N=6 in the first experiment and 8 in the other three experiments) were housed in a relatively large and heavily vegetated greenhouse and tested on their reactions to novel, innocuous inanimate objects. Some supplementary data were obtained on another such group of four individuals. The animals seemed to know the nature and relative positions of objects in their home environment ; i.e. to be capable of "cognitive mapping". Thus, for example, they detected a single novel object among up to 30 simultaneously presented test objects; they discriminated changes in an object's location and orientation; they responded more to changes in two or more parameters than to changes in only one parameter; and they showed apparent object constancy. These discriminations could be made at almost any randomly-designated location in the greenhouse, and with inter-trial intervals of 23 hours or more. Many aspects of the animals' behavior, including the order in which the various individuals approached a given object, the amount of time they remained at the object, and the likelihood (and order) of their responding to it again on subsequent trials, were highly predictable from their ages. There was, however, no "true" single linear correlation value between age and responsiveness. With appropriate sampling of one's subjects, objects and stages of group habituation, one could in fact find any correlation one chooses, from + 1.00 to -1.00; and age-response functions (and changes therein) were orderly functions of other variables.

scholarly journals A LEARNING METHOD TO DETERMINE HOW TO APPROACH AN UNKNOWN OBJECT TO BE GRASPED

2011 ◽  
Vol 08 (03) ◽  
pp. 579-606 ◽  
Author(s):  
BENJAMIN D. BALAGUER ◽  
STEFANO CARPIN
Keyword(s):  
Learning Algorithm ◽  
Training Session ◽  
Training Data ◽  
Support Vector ◽  
The Novel ◽  
Learning Method ◽  
End Effector ◽  
Novel Object ◽  
Time Performance ◽  
Feature Based

We present a learning algorithm to determine the appropriate approaching pose to grasp a novel object. Our method focuses on the computation of valid end-effector orientations in order to make contact with the object at a given point. The system achieves this goal by generalizing from positive examples provided by a human operator during an offline training session. The technique is feature-based since it extracts salient attributes of the object to be grasped rather than relying on the availability of models or trying to build one. To compute the desired orientation, the robot performs three steps at run time. Using a multi-class Support Vector Machine (SVM), it first classifies the novel object into one of the object classes defined during training. Next, it determines its orientation, and, finally, based on the classification and orientation, it extracts the most similar example from the training data and uses it to grasp the object. The method has been implemented on a full-scale humanoid robotic torso equipped with multi-fingered hands and extensive results corroborate both its effectiveness and real-time performance.

Orienting to third-party conversations

2010 ◽  
Vol 38 (2) ◽  
pp. 273-296 ◽  
Author(s):  
CARMEN MARTÍNEZ-SUSSMANN ◽  
NAMEERA AKHTAR ◽  
GIL DIESENDRUCK ◽  
LORI MARKSON
Keyword(s):  
Third Party ◽  
The Novel ◽  
Novel Object ◽  
Neutral Information ◽  
The Third ◽  
Gaze Patterns ◽  
New Information ◽  
Novel Objects ◽  
The Third Party

ABSTRACTChildren as young as two years of age are able to learn novel object labels through overhearing, even when distracted by an attractive toy (Akhtar, 2005). The present studies varied the information provided about novel objects and examined which elements (i.e. novel versus neutral information and labels versus facts) toddlers chose to monitor, and what type of information they were more likely to learn. In Study 1, participants learned only the novel label and the novel fact containing a novel label. In Study 2, only girls learned the novel label. Neither girls nor boys learned the novel fact. In both studies, analyses of children's gaze patterns suggest that children who learned the new information strategically oriented to the third-party conversation.

INERTIA PARAMETERS ESTIMATION OF PLANAR OBJECT ON ROBOT PUSHING OPERATION

2009 ◽  
Vol 06 (04) ◽  
pp. 239-247 ◽  
Author(s):  
YONG YU ◽  
TETSU ARIMA ◽  
SHOWZOW TSUJIO
Keyword(s):  
Experimental Verification ◽  
Center Of Mass ◽  
Point Contact ◽  
Parameters Estimation ◽  
Moment Of Inertia ◽  
Inertia Parameters ◽  
Angular Velocities ◽  
Unknown Object

This paper proposes a technique that can estimate the inertia parameters of a graspless unknown object, which is pushed by robot fingers. Using the fingertip different accelerations (or angular accelerations), velocities (or angular velocities) and forces information measured in pushing operations, the algorithms to estimate the object mass (or moment of inertia) are described. Then, a line called C.M. Line, is defined in this paper. The line contains the center of mass and is between two fingertips which are in point-contact with an object side. By using two or more orientation-different C.M. lines, an algorithm to estimate the center of mass of the object is given. Lastly, experimental verification on the proposed approach is performed and its results are outlined.

Sign in / Sign up

Export Citation Format

Share Document