Slippage Estimation of a two wheeled Mobile Robot using Feedforward Deep Neural Network

Date

2018-11-09

Author

Özçil, İsmail
Konukseven, Erhan İlhan
Koku, Ahmet Buğra

Metadata

Show full item record

Item Usage Stats

42
views

0
downloads

URI

https://hdl.handle.net/11511/85074

Conference Name

ICCAMMEN 2018, 1st International Conference on Advances in Mechanical and Mechatronics Engineering, (8 - 09 Kasım 2018)

Collections

Department of Mechanical Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Slippage estimation of a two wheeled mobile robot using deep neural network Özçil, İsmail; Konukseven, Erhan İlhan; Koku, Ahmet Buğra; Department of Mechanical Engineering (2018) Mobile robot navigaiton is an important task for the operations of the mobile robots. Due to the wheel slippages, performance of the dead reckoning in estimating speed of the robot and the position of the robot is not sufficient. To overcome the errors in navigation estimates, usage of the recurrent deep neural networks is porposed. Neural networks are used to understand the behaviour of the linear and nonlinear systems. Since wheel-ground interaction will be modeled with non-linear models and the estimatin...
Slippage Estimation of Two Wheeled Mobile Robot Using Recurrent Deep Neural Network Özçil, Osmail; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (2019-12-14) Position, velocity and acceleration information are important for mobile robots. Due to the wheel slippages, encoder data may not be reliable and IMU data also contains a cumulative error. Errors of inertial measurements are accumulated over velocity and position estimates and as time increases, these errors grow higher. Due to robot hardware and the operating surface, ground truth may not be available. In this work recurrent deep neural network is proposed in order to reduce the error in speed and yaw angl...
Oversampling in One-Bit Quantized Massive MIMO Systems and Performance Analysis Üçüncü, Ali Bulut; Yılmaz, Ali Özgür (2018-12-01) Low-resolution analog-to-digital converters (ADCs) have attracted much attention lately for massive multiple-input multiple-output (MIMO) communication and systems with large bandwidth. Especially, 1-bit ADCs are suitable for such systems due to their low-power consumption and cast. In this paper, we illustrate the benefits of using faster than symbol rate (FTSR) sampling in an uplink massive MIMO system with 1-bit ADCs in terms of symbol error rate (SER). We show that the FTSR sampling provides about 5-dB ...
Slip suppression in prosthetic hands using a reflective optical sensor and MPI controller Nakagawa-Silva, Andrei; Sunkesula, Sai Praneeth Reddy; Prach, Anna; Cabibihan, John-John; Thakor, Nitish V.; Soares, Alcimar B. (2018-10-19) Prosthetic hands have greatly evolved in mechatronic, robotic and control aspects. However, occasional accidents might happen due to excessive grip force or the breaking of contact due to slip. Fast transient slip events can be properly handled by a low-level controller that can behave like a reflex to maintain grasp stability in a shared control manner between the user and the prosthetic hand itself. Here we propose the use of a reflective optic sensor to capture slip events and evaluate the performance of...
Fault tolerant estimation of autonomous underwater vehicle dynamics via robust UKF Hajiyev, Chingiz; Ata, Melih; Dinc, Mustafa; Söken, Halil Ersin (2012-07-30) This article is basically focused on application of the Unscented Kalman Filter (UKF) algorithm to the estimation of high speed an autonomous underwater vehicle (AUV) dynamics. In the normal operation conditions of AUV, conventional UKF gives sufficiently good estimation results. However, if the measurements are not reliable because of any kind of malfunction in the estimation system, UKF gives inaccurate results and diverges by time. This study, introduces Robust Unscented Kalman Filter (RUKF) algorithms w...

Citation Formats

İ. Özçil, E. İ. Konukseven, and A. B. Koku, “Slippage Estimation of a two wheeled Mobile Robot using Feedforward Deep Neural Network,” presented at the ICCAMMEN 2018, 1st International Conference on Advances in Mechanical and Mechatronics Engineering, (8 - 09 Kasım 2018), Ankara, Türkiye, 2018, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/85074.