A real-time, unsupervised neural network for the low-level control of a mobile robot in a nonstationary environment

This paper presents the modeling and robust low-level control design of a redundant mobile robot with four omnidirectional wheels, the iSense Robotic (iSRob) platform, that was designed to test safe control algorithms. iSRob is a multivariable nonlinear system subject to parameter uncertainties mainly due to friction forces. A multilinear model is proposed to approximate the behavior of the system, and the parameters of these models are estimated from closed-loop experimental data applying Gauss–Newton techniques. A robust control technique, quantitative feedback theory (QFT), is applied to design a proportional–integral (PI) controller for robust low-level control of the iSRob system, being this the main contribution of the paper. The designed controller is implemented, tested, and compared with a gain-scheduling PI-controller based on pole assignment. The experimental results show that robust stability and control effort margins against system uncertainties are satisfied and demonstrate better performance than the other controllers used for comparison.

Download Full-text

Real-time navigation of a mobile robot using Kohonen's topology conserving neural network

1997 8th International Conference on Advanced Robotics Proceedings ICAR 97 ICAR-97 ◽

10.1109/icar.1997.620222 ◽

2002 ◽

Cited By ~ 8

Author(s):

I.J. Nagrath ◽

L. Behera ◽

K.M. Krishna ◽

K.D. Rajasekar

Keyword(s):

Neural Network ◽

Mobile Robot ◽

Real Time

Download Full-text

Real-Time Neural Network Based Camera Localization and its Extension to Mobile Robot Control

International Journal of Neural Systems ◽

10.1142/s012906579700029x ◽

1997 ◽

Vol 08 (03) ◽

pp. 279-293 ◽

Cited By ~ 3

Author(s):

Doo-Hyun Choi ◽

Se-Young Oh

Keyword(s):

Neural Network ◽

Neural Networks ◽

Mobile Robot ◽

Real Time ◽

Robot Control ◽

Imaging System ◽

System Modeling ◽

Hybrid Approach ◽

Camera Localization ◽

Mobile Robot Control

The feasibility of using neural networks for camera localization and mobile robot control is investigated here. This approach has the advantages of eliminating the laborious and error-prone process of imaging system modeling and calibration procedures. Basically, two different approaches of using neural networks are introduced of which one is a hybrid approach combining neural networks and the pinhole-based analytic solution while the other is purely neural network based. These techniques have been tested and compared through both simulation and real-time experiments and are shown to yield more precise localization than analytic approaches. Furthermore, this neural localization method is also shown to be directly applicable to the navigation control of an experimental mobile robot along the hallway purely guided by a dark wall strip. It also facilitates multi-sensor fusion through the use of multiple sensors of different types for control due to the network's capability of learning without models.

Download Full-text

Convolutional Neural Networks Refitting by Bootstrapping for Tracking People in a Mobile Robot

Applied Sciences ◽

10.3390/app112110043 ◽

2021 ◽

Vol 11 (21) ◽

pp. 10043

Author(s):

Claudia Álvarez-Aparicio ◽

Ángel Manuel Guerrero-Higueras ◽

Luis V. Calderita ◽

Francisco J. Rodríguez-Lera ◽

Vicente Matellán ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Mobile Robot ◽

Convolutional Neural Network ◽

Real Time ◽

Convolutional Neural Networks ◽

Large Datasets ◽

Lidar Data ◽

Labelling Process ◽

Real Time Location System

Convolutional Neural Networks are usually fitted with manually labelled data. The labelling process is very time-consuming since large datasets are required. The use of external hardware may help in some cases, but it also introduces noise to the labelled data. In this paper, we pose a new data labelling approach by using bootstrapping to increase the accuracy of the PeTra tool. PeTra allows a mobile robot to estimate people’s location in its environment by using a LIDAR sensor and a Convolutional Neural Network. PeTra has some limitations in specific situations, such as scenarios where there are not any people. We propose to use the actual PeTra release to label the LIDAR data used to fit the Convolutional Neural Network. We have evaluated the resulting system by comparing it with the previous one—where LIDAR data were labelled with a Real Time Location System. The new release increases the MCC-score by 65.97%.

Download Full-text

Real-time Continuous Hand Motion Myoelectric Decoding by Automated Data Labeling

10.1101/801985 ◽

2019 ◽

Author(s):

Xuhui Hu ◽

Hong Zeng ◽

Dapeng Chen ◽

Jiahang Zhu ◽

Aiguo Song

Keyword(s):

Neural Network ◽

Real Time ◽

Coefficient Of Determination ◽

Residual Limb ◽

Training Set ◽

Real Motion ◽

Motion Measurement ◽

Hand Motion ◽

Fitts Law ◽

Unsupervised Neural Network

AbstractIn this paper an automated data labeling (ADL) neural network was proposed to streamline dataset collecting for real-time predicting the continuous motion of hand and wrist, these gestures are only decoded from a surface electromyography (sEMG) array of eight channels. Unlike collecting both the bio-signals and hand motion signals as samples and labels in supervised learning, this algorithm only collects the unlabeled sEMG into an unsupervised neural network, in which the hand motion labels are auto-generated. The coefficient of determination (r2) for three DOFs, i.e. wrist flex/extension, wrist pro/supination, hand open/close, was 0.86, and 0.87 respectively. The comparison between real motion labels and auto-generated labels shows that the latter has earlier response than former. The results of Fitts’ law test indicate that ADL has capability of controlling multi-DOFs simultaneously even though the training set only contains sEMG data from single DOF gesture. Moreover, no more hand motion measurement needed which greatly helps upper-limb amputee imagine the gesture of residual limb to control a dexterous prosthesis.

Download Full-text