Learning Navigation Tasks from Demonstration for Semi-Autonomous Remote Operation of Mobile Robots

Moridian, Barzin; Kamal, Anurag; Mahmoudian, Nina

doi:10.1109/ssrr.2018.8468640

Cited by 5 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By straightforwardly feeding the robot with demonstrations related to specific tasks, a controller implicating the human control strategy can be automatically learned, which benefits the amateur users without professional knowledge of how to design a controller. Additionally, the learned model has generalization capacity to guarantee that the robot can adapt to similar tasks, therefore avoiding the trouble of controller redesigning [12,13].…”

Section: Introductionmentioning

confidence: 99%

A Wheeled Inverted Pendulum Learning Stable and Accurate Control from Demonstrations

Jin

2019

Applied Sciences

View full text Add to dashboard Cite

In order to enable robots to be more intelligent and flexible, one way is to let robots learn human control strategy from demonstrations. It is a useful methodology, in contrast to traditional preprograming methods, in which robots are required to show generalizing capacity in similar scenarios. In this study, we apply learning from demonstrations on a wheeled, inverted pendulum, which realizes the balance controlling and trajectory following simultaneously. The learning model is able to map the robot position and pose to the wheel speeds, such that the robot regulated by the learned model can move in a desired trajectory and finally stop at a target position. Experiments were undertaken to validate the proposed method by testing its capacity of path following and balance guaranteeing.

show abstract

Section: Introductionmentioning

confidence: 99%