Learning and position estimation of a mobile robot in an indoor environment using FuzzyART neural network

2009 ◽  
Author(s):  
Petre Lameski ◽  
Andrea Kulakov ◽  
Danco Davcev
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Indoor Environment ◽  
Position Estimation

scholarly journals Convolutional neural network-based coarse initial position estimation of a monocular camera in large-scale 3D light detection and ranging maps

2019 ◽  
Vol 16 (6) ◽  
pp. 172988141989351
Author(s):  
Manhui Sun ◽  
Shaowu Yang ◽  
Hengzhu Liu
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Convolutional Neural Network ◽  
Initial Position ◽  
Position Estimation ◽  
Light Detection And Ranging ◽  
Depth Image ◽  
Depth Information ◽  
Light Detection ◽  
Monocular Camera

Initial position estimation in global maps, which is a prerequisite for accurate localization, plays a critical role in mobile robot navigation tasks. Global positioning system signals often become unreliable in disaster sites or indoor areas, which require other localization methods to help the robot in searching and rescuing. Many visual-based approaches focus on estimating a robot’s position within prior maps acquired with cameras. In contrast to conventional methods that need a coarse estimation of initial position to precisely localize a camera in a given map, we propose a novel approach that estimates the initial position of a monocular camera within a given 3D light detection and ranging map using a convolutional neural network with no retraining is required. It enables a mobile robot to estimate a coarse position of itself in 3D maps with only a monocular camera. The key idea of our work is to use depth information as intermediate data to retrieve a camera image in immense point clouds. We employ an unsupervised learning framework to predict the depth from a single image. Then we use a pretrained convolutional neural network model to generate depth image descriptors to construct representations of the places. We retrieve the position by computing similarity scores between the current depth image and the depth images projected from the 3D maps. Experiments on the publicly available KITTI data sets have demonstrated the efficiency and feasibility of the presented algorithm.

A position estimation system for mobile robots using a monocular image of a 3-D landmark

Robotica ◽  
1994 ◽  
Vol 12 (5) ◽  
pp. 431-441 ◽  
Author(s):  
Kyoung C. Koh ◽  
Jae S. Kim ◽  
Hyung S. Cho
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Estimation Algorithm ◽  
Position Estimation ◽  
Camera System ◽  
System A ◽  
The Neural Network ◽  
Monocular Image ◽  
Estimation System ◽  
Learning Data

SUMMARYThis paper presents an absolute position estimation system for a mobile robot moving on a flat surface. In this system, a 3-D landmark with four coplanar points and a non-coplanar point is utilized to improve the accuracy of position estimation and to guide the robot during navigation. Applying theoretical analysis, we investigate the image sensitivity of the proposed 3-D landmark compared with the conventional 2-D landmark. In the camera calibration stage of the experiments, we employ a neural network as a computational tool. The neural network is trained from a set of learning data collected at various points around the mark so that the extrinsic and intrinsic parameters of the camera system can be resolved. The overall estimation algorithm from the mark identification to the position determination is implemented in a 32-bit personal computer with an image digitizer and an arithmetic accelerator. To demonstrate the effectiveness of the proposed 3-D landmark and the neural network-based calibration scheme, a series of navigation experiments were performed on a wheeled mobile robot (LCAR) in an indoor environment. The results show the feasibility of the position estimation system applicable to mobile robot's real-time navigation.

scholarly journals Convolutional Neural Network Based Path Navigation of a Differential Drive Robot in an Indoor Environment

2019 ◽  
Vol 8 (2S3) ◽  
pp. 547-549
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mobile Robot ◽  
Indoor Environment ◽  
Robot Navigation ◽  
Differential Drive ◽  
Multiple Datasets ◽  
Computation Process ◽  
Differential Drive Robot ◽  
Path Navigation

The current work illustrates a vision-guided approach to a real-time robot navigation system and the implementation of Faster Convolutional Neural Networks (FCNN) to train and detect objects with multiple datasets of the mobile robot and obstacles. The algorithm keeps monitoring the distance between the obstacles and generates way points inbetween the obstacles in such a way that a path is created towards the target. Thus, the shortest path for navigation is created which checks for possible errors and update the path during execution, making it an AI system. This approach reduces the need for incorporating multiple EMU sensors on the mobile robot and transfers the computation process to a remote processor. The processor and mobile robot communicate wirelessly for simultaneous localization and path planning. While the algorithm is being executed, trained objects are detected from each frame captured by the camera which is used to develop path by avoiding the obstacles. The performance of the system is evaluated by conducting multiple experiments with different mapping regions

scholarly journals Predicting the Energy Consumption of a Robot in an Exploration Task Using Optimized Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 920
Author(s):  
Liesle Caballero ◽  
Álvaro Perafan ◽  
Martha Rinaldy ◽  
Winston Percybrooks
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Mobile Robot ◽  
Energy Budget ◽  
Dynamic Models ◽  
Pearson Correlation ◽  
Experimental Conditions ◽  
Grid Map ◽  
Proposed Model ◽  
Exploration Task

This paper deals with the problem of determining a useful energy budget for a mobile robot in a given environment without having to carry out experimental measures for every possible exploration task. The proposed solution uses machine learning models trained on a subset of possible exploration tasks but able to make predictions on untested scenarios. Additionally, the proposed model does not use any kinematic or dynamic models of the robot, which are not always available. The method is based on a neural network with hyperparameter optimization to improve performance. Tabu List optimization strategy is used to determine the hyperparameter values (number of layers and number of neurons per layer) that minimize the percentage relative absolute error (%RAE) while maximize the Pearson correlation coefficient (R) between predicted data and actual data measured under a number of experimental conditions. Once the optimized artificial neural network is trained, it can be used to predict the performance of an exploration algorithm on arbitrary variations of a grid map scenario. Based on such prediction, it is possible to know the energy needed for the robot to complete the exploration task. A total of 128 tests were carried out using a robot executing two exploration algorithms in a grid map with the objective of locating a target whose location is not known a priori by the robot. The experimental energy consumption was measured and compared with the prediction of our model. A success rate of 96.093% was obtained, measured as the percentage of tests where the energy budget suggested by the model was enough to actually carry out the task when compared to the actual energy consumed in the test, suggesting that the proposed model could be useful for energy budgeting in actual mobile robot applications.

Sign in / Sign up

Export Citation Format

Share Document