Robotic Learning and Applications

Mechatronics ◽  
2015 ◽  
pp. 544-581
Keyword(s):  
Robotic Learning

scholarly journals Robotic Learning from Advisory and Adversarial Interactions using a Soft Wrist

2021 ◽  
pp. 1-1
Author(s):  
Masashi Hamaya ◽  
Kazutoshi Tanaka ◽  
Yoshiya Shibata ◽  
Felix Wolf Hans Erich Von Drigalski ◽  
Chisato Nakashima ◽  
...  
Keyword(s):  
Robotic Learning

scholarly journals Hyperparameter Auto-tuning in Self-Supervised Robotic Learning

2021 ◽  
pp. 1-1
Author(s):  
Jiancong Huang ◽  
Juan Rojas ◽  
Matthieu Zimmer ◽  
Hongmin Wu ◽  
Yisheng Guan ◽  
...  
Keyword(s):  
Auto Tuning ◽  
Robotic Learning

Dual exploration strategies using artificial spiking neural networks in a robotic learning task

2020 ◽  
pp. 105971232092474
Author(s):  
André Cyr ◽  
Julie Morand-Ferron ◽  
Frédéric Thériault
Keyword(s):  
Risk Taking ◽  
Spatial Information ◽  
Autonomous Robots ◽  
Visual Learning ◽  
Learning Task ◽  
Conditioning Procedure ◽  
Neural Architecture ◽  
The Common ◽  
Multiple Levels ◽  
Robotic Learning

Spatial information can be valuable, but new environments may be perceived as risky and thus often evoke fear responses and risk-averse exploration strategies such as thigmotaxis or wall-following behavior. Individual differences in risk-taking (boldness) and thigmotaxis have been reported in natural taxa, which may benefit their survival. In neurorobotic, the common approach is to reproduce cognitive phenomena with multiple levels of bio-inspiration into robotic scenarios. Since autonomous robots may benefit from these different behaviors in exploration tasks, this study aims at simulating two exploration strategies in a virtual robot controlled by a spiking neural network. The experimental context consists in a visual learning task solved through an operant conditioning procedure. Results suggest that the proposed neural architecture sustains both behaviors, switching from one to the other by external cues. This original bio-inspired model could be used as a first step toward further investigations of neurorobotic personality modulated by learning and complex exploration contexts.

Acquisition of Behavioral Patterns Depends on Self-Embodiment Based on Robot Learning Under Multiple Instructors

2007 ◽  
Vol 11 (8) ◽  
pp. 989-997 ◽  
Author(s):  
Masato Kotake ◽  
◽  
Daisuke Katagami ◽  
Katsumi Nitta ◽  
Keyword(s):  
Robot Learning ◽  
Behavioral Patterns ◽  
Teaching Approaches ◽  
Task Accomplishment ◽  
Robotic Learning

We focus on robotic learning under multiple instructors. Even when their goal is the same, different instructors inevitably was different approaches. We propose incorporating DP matching and clustering, classifying the teaching demonstrations of instructors into groups of similar ones. Experiments in which an AIBO robot was taught to walk forward demonstrated that our proposal acquired appropriate teaching approaches based on AIBO’s different embodiments and maximizing task accomplishment.

scholarly journals The The Application of Virtual Reality to (Mechatronics Engineering) by Creating an Articulated Robotic Work Cell Using EON Reality V9.22.24.24477

2021 ◽  
Vol 17 (2) ◽  
pp. 18-30
Author(s):  
Aiman Al- Allaq ◽  
Nebojsa Jaksic ◽  
Hussein Ali Al-Amili ◽  
Dhuha Mohammed Mahmood
Keyword(s):  
Virtual Reality ◽  
Learning Styles ◽  
Virtual Manufacturing ◽  
Robotic Cell ◽  
The Third ◽  
Guided Exploration ◽  
Cell Components ◽  
Manufacturing Platform ◽  
Active Channels ◽  
Robotic Learning

Virtual reality, VR, offers many benefits to technical education, including the delivery of information through multiple active channels, the addressing of different learning styles, and experiential-based learning. This paper presents work performed by the authors to apply VR to engineering education, in three broad project areas: virtual robotic learning, virtual mechatronics laboratory, and a virtual manufacturing platform. The first area provides guided exploration of domains otherwise inaccessible, such as the robotic cell components, robotic kinematics and work envelope.  The second promotes mechatronics learning and guidance for new mechatronics engineers when dealing with robots in a safe and interactive manner. And the third provides valuable guidance for industry and robotic based manufacturing, allowing a better view and simulating conditions otherwise inaccessible.

Sign in / Sign up

Export Citation Format

Share Document