A Common-Neural-Pattern Based Reasoning for Mobile Robot Cognitive Mapping

Obstacles for solar photovoltaic (PV) system to be a reliable energy source is its intermittent and stochastic output power. The randomness output power could trigger power fluctuation event. Subsequently, more power quality issues such as frequency fluctuation, voltage variation and harmonic distortion could happen. Thus, this paper introduces a Self-Organizing Incremental Neural Network (SOINN) to predict the output power and subsequently detect the power fluctuation events in order to enhance the reliability of a PV grid-tied system. The SOINN is developed from the growing neural gas and competitive hebbian learning. It could be trained without predefined the structure of the network. To train the SOINN, input data to the PV system such as irradiance and temperature are used. The trained SOINN will be compared with the Self-Organizing Map (SOM) network. Results show that the SOINN prediction engine achieves an accuracy of 100 % in identifying power fluctuation event through predicted output power.

A fast nearest neighbor classifier based on self-organizing incremental neural network

This paper firstly analyzes the shortcoming of a self-organizing incremental neural network (SOINN), then proposes a novel online similarity metric and online adaptive kernel density estimator to handle 2 basic problems of unsupervised learning: clustering and density estimation. Our approach is an extension of the standard Gaussian process, online density estimator and SOINN; not only does it fully consider the local structure (the local distribution around each node), but also the learning of parameters is adjusted to make it feasible to online learning. The experiment results show that our method is more accurate and robust to multiscale, multimodal and multivariate data.

Temporal neural networks such as Temporal Kohonen Map (TKM) and Recurrent Self-Organizing Map (RSOM) are popular for their incremental and explicit learning abilities. However, for sub-sequence clustering TKM and RSOM may generate many fragments whose classification membership is hard to decide. Besides they have stability issues in multivariate time series processing because they model the historical neuron activities on each variable independently. To overcome the drawbacks, we propose an adaptive sub-sequence clustering method based on single layered Self-Organizing Incremental Neural Network (SOINN). A recurrent filter is proposed to model the quantizations of neuron activations each as a scalar instead of a vector like in TKM and RSOM. Then it is integrated with the single layered SOINN for adaptive clustering where fragmented clusters in TKM and RSOM is replaced by a smoothed clustering result. Experiments are carried out on two datasets, namely a traffic flow dataset from open Caltrans performance measurement systems and a part of the KDD Cup 99 intrusion detection dataset. Experimental results show that the proposed method outperforms the conventional methods by 21.3% and 9.1% on the two datasets respectively.

An improved self-organizing incremental neural network model for short-term time-series load prediction

A Self-Organizing Incremental Neural Network based on local distribution learning

Long-term human-robot interaction requires the continuous acquisition of knowledge. This ability is referred to as lifelong learning (LL). LL is a long-standing challenge in machine learning due to catastrophic forgetting, which states that continuously learning from novel experiences leads to a decrease in the performance of previously acquired knowledge. Two recently published LL approaches are the Growing Dual-Memory (GDM) and the Self-organizing Incremental Neural Network+ (SOINN+). Both are growing neural networks that create new neurons in response to novel sensory experiences. The latter approach shows state-of-the-art clustering performance on sequentially available data with low memory requirements regarding the number of nodes. However, classification capabilities are not investigated. Two novel contributions are made in our research paper: (I) An extended SOINN+ approach, called associative SOINN+ (A-SOINN+), is proposed. It adopts two main properties of the GDM model to facilitate classification. (II) A new LL object recognition dataset (v-NICO-World-LL) is presented. It is recorded in a nearly photorealistic virtual environment, where a virtual humanoid robot manipulates 100 different objects belonging to 10 classes. Real-world and artificially created background images, grouped into four different complexity levels, are utilized. The A-SOINN+ reaches similar state-of-the-art classification accuracy results as the best GDM architecture of this work and consists of 30 to 350 times fewer neurons, evaluated on two LL object recognition datasets, the novel v-NICO-World-LL and the well-known CORe50. Furthermore, we observe an approximately 268 times lower training time. These reduced numbers result in lower memory and computational requirements, indicating higher suitability for autonomous social robots with low computational resources to facilitate a more efficient LL during long-term human-robot interactions.

In this paper, we present a feasible solution to the problem of autonomous navigation in initially unknown environments using a pure vision-based approach. The mobile robot performs range sensing with a unique omnidirectional stereovision system, estimates its motion using visual odometry and detects loop closures via a place recognition system as it performs topological map building and localization concurrently. Owing to the importance of performing loop closing regularly, the mobile robot is equipped with an active loop closure detection and validation system that assists it to return to target loop closing locations, validates ambiguous loop closures and provides it with the ability to overturn the decision of an incorrectly committed loop closure. A refined incremental probabilistic framework for an appearance-based place recognition system is fully described and the final system is validated in multiple experiments conducted in indoor, semi-outdoor and outdoor environments. Lastly, the performance of the probabilistic framework is compared with the rank-based framework with additional experiments conducted in the semi-autonomous mode, where the mobile robot, provided with a priori information in the form of a topological map that is built in a separate occasion in an offline manner, is required to reach its target destination.

Goal-oriented navigation is widely understood to depend upon internal maps. Although this may be the case in many settings, humans tend to rely on vision in complex, unfamiliar environments. To study the nature of gaze during visually-guided navigation, we tasked humans to navigate to transiently visible goals in virtual mazes of varying levels of difficulty, observing that they took near-optimal trajectories in all arenas. By analyzing participants’ eye movements, we gained insights into how they performed visually-informed planning. The spatial distribution of gaze revealed that environmental complexity mediated a striking trade-off in the extent to which attention was directed towards two complimentary aspects of the world model: the reward location and task-relevant transitions. The temporal evolution of gaze revealed rapid, sequential prospection of the future path, evocative of neural replay. These findings suggest that the spatiotemporal characteristics of gaze during navigation are significantly shaped by the unique cognitive computations underlying real-world, sequential decision making.

A novel approach to robot guidance in an unfamiliar environment is presented. In previous guiding methods, a preinstalled map or predefined path is required for a robot navigating in its working space. The present method uses an indication post (IP) to provide the information on the destination, the direction, and the distance from the source point to the destination point, assuming that the mobile robot has no information concerning its workplace. To realize the concept, many IPs depicting simple information were designed. The content of IPs can be described by using a finite-state grammar. Image-processing, statistical, and syntactic pattern recognition approaches are integrated to solve the problems of IP finding, robot location determination, IP identification, and understanding. Experiments simulating practical environments were performed. The results verify that the IP candidates can be automatically found and the depicted information can be extracted and understood correctly, so that the mobile robot is able to plan a global optimal path from an arbitrary start point to an arbitrary end point.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Map building and localization are essential to an autonomous mobile robot system. A global topological map is commonly constructed from a global grid map using a Voronoi diagram. In this hierarchical method, however, the advantage of a topological map such as compactness may not be fully utilized. In this paper sensor data are used to build a local grid map from which a local topological map is created using a thinning method. The thinning method is an alternative of the Voronoi diagram. The local topological map is then updated to the global one. Localization based on the topological map is usually difficult, but additional nodes created by the thinning method can improve localization performance. Various experiments with a laser scanner demonstrate validity and feasibility of the proposed algorithms for map building and localization.

Mobile robot localization and map building are very important for a mobile robot to perform a navigation-based service task to aid the aged or disabled in an indoor environment (office, facilities or at home). In order to enable mobile robot to perform service tasks autonomously, the information of environment in which the mobile robot moves is needed. To obtain the accurate map, many different sensors system and techniques have been developed. Approaches of mapping can roughly be classified according to the kind of sensor data processed and the matching algorithms [S. Thrun et al., 1996, 1998, 2000, 2004; Chong, K.S et al., 1996; C.-C. Wang et al., 2002; G. Dissanayake et al., 2000; B. barshan et al., 1995; Weimin Shen et al., 2005]. In this paper, we proposed a method of map building using interactive GUI for a mobile robot. The reason we proposed this method is that it is difficult for a mobile robot to generate an accurate map although many kinds of sensors are used. The proposed method enables the operator to modify map built by sensors, compared with the real-time video from web camera by using modification tool in interactive GUI. Laser Range Finder (LRF) was used to get the information of the environment in which mobile robot moving. In order to improve self-localization of mobile robot, Extended Kalman Filter (EKF) was introduced. By the results of simulation and experiments, the developed EKF is effective in self-localization of mobile robot. This paper introduces the architecture of the system and gives some experimental results to verify the effectiveness of the developed system. The rest of the paper consists of 5 sections. Section 2 describes the structure of the proposed system. Section 3 presents the developed algorithm of self-localization of mobile robot and gives some simulation and experimental results to verify the effectiveness of the EKF in improving precision of positioning of mobile robot. Section 4 details the developed LRF data processing algorithm. Section 5 introduces the developed interactive GUI. The experimental results are given in Section 6. Section 7 concludes the paper. 13

For a set of Mobile Sensor Network, a precise localization is required in order to maximize the utilization of Mobile Sensor Network. As well, mobile robots also need a precise localization mechanism for the same reason. In this paper, we showed a combination of various localization mechanisms. Localization can be classified in three big categories: long distance localization with low accuracy, medium distance localization with medium accuracy, and short distance localization with high accuracy. In order to present localization methods, traditional map building technologies such as grid maps or topological maps can be used. We implemented mobile sensor vehicles and composed mobile sensor network with them. Each mobile sensor vehicles act as a mobile sensor node with the facilities such as autonomous driving, obstacle detection and avoidance, map building, communication via wireless network, image processing and extensibility of multiple heterogeneous sensors. For localization, each mobile sensor vehicle has abilities of the location awareness by mobility trajectory based localization, RSSI based localization and computer vision based localization. With this set of mobile sensor network, we have the possibility to demonstrate various localization mechanisms and their effectiveness. In this paper, the preliminary result of sensor mobility trail based localization and RSSI based localization will be presented.

A blind traveler walking through an unfamiliar environment and a mobile robot navigating through a cluttered environment have an important feature in common: both have the kinematic ability to perform the motion, but they are dependent on a sensory system to detect and avoid obstacles. The paper describes the use of a mobile robot obstacle avoidance system as a guidance device for blind and visually impaired people. Just as electronic signals are sent to a mobile robot's motion controllers, auditory signals can guide the blind traveler around obstacles, or alternatively, they can provide an "acoustic image" of the surroundings. The concept has been implemented and tested in a new travel aid for the blind, called the Navbelt. The Navbelt introduces two new concepts to electronic travel aids (ETA's) for the blind: it provides information not only about obstacles along the traveled path, but also assists the user in selecting the preferred travel path. In addition, the level of assistance can be automatically adjusted according to changes in the environment and the user's needs and capabilities. Experimental results conducted with the Navbelt simulator and a portable experimental prototype are presented.

Mobile robot is an important developing direction in the field of robotics, it is widely used in Industrial Internet of Things (IIoT) environment, agriculture, military, transportation, services with the coming of 5G wireless communication technology. Automatic navigation control technology is the core in these research areas, which is also the key technology for mobile robot to achieve intelligentization and autonomation.The article discusses and researches the neural network technology and its application in mobile robot navigation control. For the characteristics and research of mobile robot navigation problem, it finds the way to improve the mobile robot intelligentization, level of the self-organization, self-learning and adaptive capability. The combination of neural network with other intelligent algorithms solves autonomous navigation problem of the mobile robot in the complex uncertain environments and unknown variable environments. The mobile robot navigation control problem using fuzzy neural network can achieve a more effective real-time navigation control performance through amending the network weights by self-study according to the navigation priori knowledge of human experts.