scholarly journals Robot Imitation Learning of Social Gestures with Self-Collision Avoidance Using a 3D Sensor

Sensors ◽  
2018 ◽  
Vol 18 (7) ◽  
pp. 2355 ◽  
Author(s):  
Tan Zhang ◽  
Wing-Yue Louie ◽  
Goldie Nejat ◽  
Beno Benhabib
Keyword(s):  
Social Communication ◽  
Learning System ◽  
Imitation Learning ◽  
High Dimensionality ◽  
Human Behaviors ◽  
Bounding Volumes ◽  
Communication Modes ◽  
Robot Configuration ◽  
Kinematical Approach ◽  
Dual Arm

To effectively interact with people, social robots need to perceive human behaviors and in turn display their own behaviors using social communication modes such as gestures. The modeling of gestures can be difficult due to the high dimensionality of the robot configuration space. Imitation learning can be used to teach a robot to implement multi-jointed arm gestures by directly observing a human teacher’s arm movements (for example, using a non-contact 3D sensor) and then mapping these movements onto the robot arms. In this paper, we present a novel imitation learning system with robot self-collision awareness and avoidance. The proposed method uses a kinematical approach with bounding volumes to detect and avoid collisions with the robot itself while performing gesticulations. We conducted experiments with a dual arm social robot and a 3D sensor to determine the effectiveness of our imitation system in being able to mimic gestures while avoiding self-collisions.

Analyzing the Functions and Benefits of Using Mobile Facebook as a Supplemental LMS in Higher Education

2017 ◽  
Vol 21 (6) ◽  
pp. 971-979 ◽  
Author(s):  
Dian-Fu Chang ◽  
Yu-Lan Huang ◽  
Berlin Wu ◽  
◽  
◽  
...  
Keyword(s):  
Social Communication ◽  
Social Networking Sites ◽  
Social Groups ◽  
Mobile App ◽  
Learning System ◽  
Learning Performance ◽  
Management Systems ◽  
University Administrators ◽  
National Organizations ◽  
Learning Management

The wide implementation of social networking sites (SNS) in many fields, for instance, government, celebrities, schools, social groups, events promoted by national organizations or private enterprises, NPOs, businesses, etc., attests to its popularity. Currently more and more educators and students have integrated these online social communication platforms into their learning environment. Learning Management Systems (LMS) also have great features and functions that may serve as a bridge between learners and educators leading to better communication, in addition to helping students increase their learning engagement and teachers in evaluating learning performance. Although many studies have investigated the effects of adopting Facebook as an additional learning management system (LMS), its functions and benefits differing from the LMS have hardly been systematically analyzed. Besides, due to the increasing popularity of mobile devices among the younger generation, university students are obviously likely to use their smart phones to access both Facebook Mobile App and school LMS. Therefore, the first purpose of this study is to determine students’ opinions on mobile Facebook course groups and a mobile LMS course group, through a survey conducted after a 2-semester experiment. The other objective of this study is to evaluate the benefits of each function of mobile FB course groups that may strengthen the current weaknesses of LMS. In addition, regression analysis and t-test were used to reveal the relationships among variables: the FB functions and its benefits for FB course group. The findings might provide a clear notion for teachers regarding the functions and advantages contributed by a mobile FB course group which can be implemented as a supplemental learning system. The results of the research will provide university administrators with more detailed information for improving the LMS’ features or developing new LMS Apps.

scholarly journals Imitation learning for agile autonomous driving

2019 ◽  
Vol 39 (2-3) ◽  
pp. 286-302 ◽  
Author(s):  
Yunpeng Pan ◽  
Ching-An Cheng ◽  
Kamil Saigol ◽  
Keuntaek Lee ◽  
Xinyan Yan ◽  
...  
Keyword(s):  
High Speed ◽  
Low Cost ◽  
Control Policy ◽  
Autonomous Driving ◽  
Network Control ◽  
Learning System ◽  
Imitation Learning ◽  
Predictive Controller ◽  
Autonomous Driving System ◽  
Better Than

We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw, high-dimensional observations to continuous steering and throttle commands. Compared with recent approaches to similar tasks, our method requires neither state estimation nor on-the-fly planning to navigate the vehicle. Our approach relies on, and experimentally validates, recent imitation learning theory. Empirically, we show that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policies trained with batch imitation learning. Built on these insights, our autonomous driving system demonstrates successful high-speed off-road driving, matching the state-of-the-art performance.

Boosting Innovation in an Italian Online University

2013 ◽  
Vol 3 (4) ◽  
pp. 29-43
Author(s):  
Francesca Pozzi ◽  
Manuela Delfino ◽  
Stefania Manca ◽  
Donatella Persico ◽  
Immacolata Scancarello
Keyword(s):  
Qualitative Data ◽  
Video Communication ◽  
Learning System ◽  
University Staff ◽  
Training Initiative ◽  
Telecommunication Infrastructure ◽  
Communication Modes ◽  
E Learning ◽  
The University ◽  
Trend Reversal

This paper describes the process of boosting an innovative e-learning system in an online university in Italy. The system relies on a satellite-terrestrial telecommunication infrastructure and allows for different interaction types, including synchronous, asynchronous, textual, audio and video communication modes. The adoption of this infrastructure was preceded by a training initiative proposed to the university staff to favor its intake. The paper analyses the effects of both the training initiative and the technological innovation based on qualitative data derived from the observed differences between the pre-existing courses and their re-design and quantitative data tracked by the system during a pilot test that lasted eleven months. These data show a trend reversal in the e-learning approach, from a prevalence of transmissive mode to a more interactive one, although there is still a long way to go before more radical changes can take place.

Developmental Approach for Behavior Learning Using Primitive Motion Skills

2018 ◽  
Vol 28 (04) ◽  
pp. 1750038 ◽  
Author(s):  
Farhan Dawood ◽  
Chu Kiong Loo
Keyword(s):  
Humanoid Robot ◽  
Automatic Segmentation ◽  
Kinematic Model ◽  
Developmental Model ◽  
Learning System ◽  
Imitation Learning ◽  
Developmental Approach ◽  
Motion Primitives ◽  
Efficient Retrieval ◽  
Spatio Temporal

Imitation learning through self-exploration is essential in developing sensorimotor skills. Most developmental theories emphasize that social interactions, especially understanding of observed actions, could be first achieved through imitation, yet the discussion on the origin of primitive imitative abilities is often neglected, referring instead to the possibility of its innateness. This paper presents a developmental model of imitation learning based on the hypothesis that humanoid robot acquires imitative abilities as induced by sensorimotor associative learning through self-exploration. In designing such learning system, several key issues will be addressed: automatic segmentation of the observed actions into motion primitives using raw images acquired from the camera without requiring any kinematic model; incremental learning of spatio-temporal motion sequences to dynamically generates a topological structure in a self-stabilizing manner; organization of the learned data for easy and efficient retrieval using a dynamic associative memory; and utilizing segmented motion primitives to generate complex behavior by the combining these motion primitives. In our experiment, the self-posture is acquired through observing the image of its own body posture while performing the action in front of a mirror through body babbling. The complete architecture was evaluated by simulation and real robot experiments performed on DARwIn-OP humanoid robot.

Few-experiential learning system of robotic picking task with selective dual-arm grasping

2020 ◽  
Vol 34 (18) ◽  
pp. 1171-1189
Author(s):  
Shingo Kitagawa ◽  
Kentaro Wada ◽  
Shun Hasegawa ◽  
Kei Okada ◽  
Masayuki Inaba
Keyword(s):  
Experiential Learning ◽  
Learning System ◽  
Dual Arm
Sign in / Sign up

Export Citation Format

Share Document