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

Author(s):  
Masato Kotake ◽  
◽  
Daisuke Katagami ◽  
Katsumi Nitta ◽  

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.

2021 ◽  
Vol 33 (5) ◽  
pp. 1063-1074
Author(s):  
Kei Kase ◽  
Noboru Matsumoto ◽  
Tetsuya Ogata ◽  
◽  

Deep robotic learning by learning from demonstration allows robots to mimic a given demonstration and generalize their performance to unknown task setups. However, this generalization ability is heavily affected by the number of demonstrations, which can be costly to manually generate. Without sufficient demonstrations, robots tend to overfit to the available demonstrations and lose the robustness offered by deep learning. Applying the concept of motor babbling – a process similar to that by which human infants move their bodies randomly to obtain proprioception – is also effective for allowing robots to enhance their generalization ability. Furthermore, the generation of babbling data is simpler than task-oriented demonstrations. Previous researches use motor babbling in the concept of pre-training and fine-tuning but have the problem of the babbling data being overwritten by the task data. In this work, we propose an RNN-based robot-control framework capable of leveraging targetless babbling data to aid the robot in acquiring proprioception and increasing the generalization ability of the learned task data by learning both babbling and task data simultaneously. Through simultaneous learning, our framework can use the dynamics obtained from babbling data to learn the target task efficiently. In the experiment, we prepare demonstrations of a block-picking task and aimless-babbling data. With our framework, the robot can learn tasks faster and show greater generalization ability when blocks are at unknown positions or move during execution.


Author(s):  
Joe Bonnell ◽  
Phil Copestake ◽  
David Kerr ◽  
Rowena Passy ◽  
Chris Reed ◽  
...  

2020 ◽  
Vol 10 (2) ◽  
pp. 192-200 ◽  
Author(s):  
Susan D. McMahon ◽  
Jacqueline O. Davis ◽  
Eric Peist ◽  
Kailyn Bare ◽  
Dorothy L. Espelage ◽  
...  

Author(s):  
Nusa FAIN ◽  
Michel ROD ◽  
Erik BOHEMIA

This paper explores the influence of teaching approaches on entrepreneurial mindset of commerce, design and engineering students across 3 universities. The research presented in this paper is an initial study within a larger project looking into building ‘entrepreneurial mindsets’ of students, and how this might be influenced by their disciplinary studies. The longitudinal survey will measure the entrepreneurial mindset of students at the start of a course and at the end. Three different approaches to teaching the courses were employed – lecture and case based, blended online and class based and fully project-based course. The entrepreneurial mindset growth was surprisingly strongest within the engineering cohort, but was closely followed by the commerce students, whereas the design students were slightly more conservative in their assessments. Future study will focus on establishing what other influencing factors beyond the teaching approaches may relate to the observed change.


1976 ◽  
Vol 42 (6) ◽  
pp. 1534-1540 ◽  
Author(s):  
G. L. Owen ◽  
F.A. Martz ◽  
J. R. Campbell ◽  
A. G. Matches ◽  
E. S. Hilderbrand

2017 ◽  
Vol 8 (1) ◽  
pp. 60
Author(s):  
Phd.Can Elsa Vula

Challenges of assessment might come up from different reasons or circumstances which generate huge obstacles and dissatisfactions for teachers and students in the same time. Meanwhile, teachers of foreign languages see them as barriers or complications due to an effective and reliable assessment. Firstly, this paper elaborates on theoretical part of assessment, as a crucial tool to measure students’ performance of speaking, as a significant English skill, and then it is presented the elaboration of challenge and its sub-challenges during my work as an English assistant at my tutorial classes on a specific course such as “Integrated English Skill III”, particularly focusing on speaking skill. After it, there is an expansion of others’ research done on this issue, supported by different teaching approaches, and relying on others’ work related to such issue. And at the end of this paper it can be found the summary and recommendations, which wereconducted from the empirical research.


Sign in / Sign up

Export Citation Format

Share Document