Detail Cantuman

Haptic tele-driving of wheeled mobile robot over the internet via PSPM approach:
theory and experiment
Hyunsoo Yanga, Zhiyuan Zuob and Dongjun Leea
aDepartment of Mechanical & Aerospace Engineering and IAMD, Seoul National University, Seoul, Korea; bRobotics Graduate Program, University of Michigan, Ann Arbor, MI, USA
ABSTRACT
We propose novel haptic tele-driving control frameworks of a wheeled mobile robot (WMR) over the imperfect Internet communication network with varying delay and packet loss. We consider both the dynamic and kinematic WMRs and their various tele-driving modes. By utilizing passive set-positio modulation framework, we can guarantee two-port passivity or passivity/stability combination of the closed-loop tele-driving system with some theoretical performance measures. Experiments
are performed to show the efficacy of the proposed frameworks using the Internet-emulated communication and a custom-built dynamic/kinematic WMR.
KEYWORDS
Haptic feedback; Internet communication; passivity; teleoperation; wheeled mobile robot

Personalized teleoperation via intention recognition
Serge Mghabghaba, Imad H. Elhajja and Daniel Asmarb
adepartment of electrical and computer engineering, American University of beirut, beirut, Lebanon; bdepartment of Mechanical engineering, American University of beirut, beirut, Lebanon
ABSTRACT
One of the challenges of teleoperation is the recognition of a user’s intended commands, particularly in the manning of highly dynamic systems such as drones. In this paper, we present a solution to this problem by developing a generalized scheme relying on a Convolutional Neural Network (CNN) that is trained to recognize a user’s intended commands, directed through a haptic device. Our proposed method allows the interface to be personalized for each user, by pre-training the CNN diffrently according to the input data that is specifi to the intended end user. Experiments were conducted using two haptic devices and classifiation results demonstrate that the proposed system outperforms geometric-based approaches by nearly 12%. Furthermore, our system also lends itself to other human–machine interfaces where intention recognition is required.
KEYWORDS
Quadrotor; personalized teleoperation; cnn; intention recognition