Amira A. A. Elmagid, Rabie Α. Ramadan, Shahinaz M. Al-Tabbakh et al. · International Journal of Computer Applications · 2014
The recent increasing threat of radiological weapons technologies has highlighted the need for superior detection of hazardous emission sources. One promising area of technological development is radiation source detection using tracing mobile robot. In this paper, a novel algorithm based on GA is proposed for localization problem of such dangerous source using single robot. In which, if the estimated source location is gathered, the algorithm process is being terminated. The adaptive GA based on fuzzy logic is also introduced for comparison. Simulation results indicate that the proposed adaptive genetic algorithm have a better performance and faster than GA. In addition, the paper presents an investigation of radiation source localization by addressing the explanation of two novel algorithms that are assumed when considering group of autonomous mobile robots system.
Cited by 1Open access
Chee Kiat Seow, Winston K.G. Seah, Z. Liu · 2007
Although there has been much effort to improve localization in both wireless sensor networks and robotics, few have combined the localization techniques of both worlds so that they can cooperatively and mutually benefit each other. Therefore, we seek to design a localization algorithm based on statistical framework that can combine the localization methodology of both autonomous robotics and sensor networks, such that a two-way cooperative localization can be accomplished instead of the usual one-way only cooperation. To achieve this, we need to integrate three important research areas: wireless sensor networks, robotics and statistical filtering. In this paper, we will present the key elements of our approach and simulation results to validate the scheme. We prove that mobile robots and static sensor nodes can cooperatively help each other in their localization by first localizing the mobile robots with the static nodes, after which the mobile robots will provide feedback to the static nodes so that the static nodes can then refine their own location estimates.
Cited by 15
Guanghui Cen, Hideichi Nakamoto, Nobuto Matsuhira et al. · 2007
At indoor environment, a service robot must know where it is at any time. Thus, reliable position estimation is a basic and key problem. Probabilistic robotics techniques have become one of the dominant paradigms for algorithm design in robotics. Recent work on Monte Carlo Localization with particle-based density representation becomes popular. In this paper we introduce the multi-sensor based Monte Carlo localization (MCL) method which represents a robot's belief by a set of weighted samples and use the laser range finder (LRF) sensor to measurement update. The experiment results illustrate the effectivity and robust of MCL application for our service robot.
Cited by 9
Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2007
Learning-based localization in wireless and sensor networks by Junfeng Pan thesis 2007 xiii, 124 leaves : ill. ; 30 cm Accurately tracking mobile devices in wireless and sensor networks using received-signal-strength (RSS) values is a useful task in robotics and…Read more ›
Cited by 0
Alishba Imran, Keerthana Gopalakrishnan · Apress eBooks · 2025
This chapter explores mapping, localization, and navigation techniques in robotics, highlighting the role of deep learning in processing high-dimensional sensor data. It discusses various mapping representations - geometric, voxel-based, and semantic - with models like CLIP and NeRF. Additionally, it covers localization methods, diffusion-based navigation strategies like Mobility VLA, and advances in hierarchical learning that improve robot adaptability in complex environments.
Cited by 0
Inam Ullah, Yu Shen, Xin Su et al. · IEEE Access · 2019
Localization plays an important role in the field of Wireless Sensor Networks (WSNs) and robotics. Currently, localization is a very vibrant scientific research field with many potential applications. Localization offers a variety of services for the customers, for example, in the field of WSN, its importance is unlimited, in the field of logistics, robotics, and IT services. Particularly localization is coupled with the case of human-machine interaction, autonomous systems, and the applications of augmented reality. Also, the collaboration of WSNs and distributed robotics has led to the creation of Mobile Sensor Networks (MSNs). Nowadays there has been an increasing interest in the creation of MSNs and they are the preferred aspect of WSNs in which mobility plays an important role while an application is going to execute. To overcome the issues regarding localization, the authors developed a framework of three algorithms named Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF) and Particle Filter (PF) Localization algorithms. In our previous study, the authors only focused on EKF-based localization. In this paper, the authors present a modified Kalman Filter (KF) for localization based on UKF and PF Localization. In the paper, all these algorithms are compared in very detail and evaluated based on their performance. The proposed localization algorithms can be applied to any type of localization approach, especially in the case of robot localization. Despite the harsh physical environment and several issues during localization, the result shows an outstanding localization performance within a limited time. The robustness of the proposed algorithms is verified through numerical simulations. The simulation results show that proposed localization algorithms can be used for various purposes such as target tracking, robot localization, and can improve the performance of localization.
Cited by 174Open access
Ján Mikula, Miroslav Kulich · arXiv (Cornell University) · 2024
This paper studies the omnidirectional sensor-placement problem (OSPP), which involves placing static sensors in a continuous 2D environment to achieve a user-defined coverage requirement while minimizing sensor count. The problem is motivated by applications in mobile robotics, particularly for optimizing visibility-based route planning tasks such as environment inspection, target search, and region patrolling. We focus on omnidirectional visibility models, which eliminate sensor orientation constraints while remaining relevant to real-world sensing technologies like LiDAR, 360-degree cameras, and multi-sensor arrays. Three key models are considered: unlimited visibility, limited-range visibility to reflect physical or application-specific constraints, and localization-uncertainty visibility to account for sensor placement uncertainty in robotics. Our first contribution is a large-scale computational study comparing classical convex-partitioning and sampling-based heuristics for the OSPP, analyzing their trade-off between runtime efficiency and solution quality. Our second contribution is a new class of hybrid accelerated-refinement (HAR) heuristics, which combine and refine outputs from multiple sensor-placement methods while incorporating preprocessing techniques to accelerate refinement. Results demonstrate that HAR heuristics significantly outperform traditional methods, achieving the lowest sensor counts and improving the runtime of sampling-based approaches. Additionally, we adapt a specific HAR heuristic to the localization-uncertainty visibility model, showing that it achieves the required coverage for small to moderate localization uncertainty. Future work may apply HAR to visibility-based route planning tasks or explore novel sensor-placement approaches to achieve formal coverage guarantees under uncertainty.
Cited by 0Open access
Guoyu Fu, Jin Zhang, Wenyuan Chen et al. · International Journal of Advanced Robotic Systems · 2013
Precise localization of mobile robots in uncertain environments is a fundamental and crucial issue in robotics. In this paper, to deal with the unbounded accumulated errors of dead reckoning (DR)-based localization, wireless sensor network (WSN)-based localization is applied to calibrate the uncertainty of odometry using a Kalman filter (KF). In addition, to further aid in obtaining precise positions and reduce uncertainty, a novel backward dead reckoning (BDR) localization approach is proposed. The experimental results demonstrate the success and reliability of the proposed method.
Cited by 27Open access
K. Geetha, M. Deepika, M J Mrudhul et al. · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 2025
Custom silicon offers an untapped opportunity for addressing complex challenges in robotics by providing optimized performance and energy efficiency. RISC-V—a novel, open- source Instruction Set Architecture (ISA)—has been gaining rapid traction due to its flexibility and customizability. In this work, we explore the capabilities of RISC-V in the robotics do- main by implementing a complete localization and motion control solution on an FPGA. Leveraging the reconfigurability of FPGAs alongside the extensibility of a custom five-stage pipelined RISC- V processor, our approach demonstrates significant potential for real-time, efficient, and scalable robotic applications. Extensive testing reveals that hardware-level acceleration, particularly in sensor fusion and motor control, provides substantial improve- ments in latency and computational efficiency over traditional software-based systems. The results underscore the promise of RISC-V-based hardware acceleration for advanced robotic localization and pave the way for future innovations in embedded robotics. Index Terms—FPGA, RISC-V, Localization, Robotics, Custom Silicon, Instruction Set Architecture, Real-time Processing, Hard- ware Acceleration
Cited by 0Open access
Cedric Pradalier, Sepanta Sekhavat · 2001
One of the common ways of localization in robotics is the triangulation using a system composed of a sensor and some landmarks (which can be artificial or natural). This paper presents a framework, namely the Localization Space, in order to deal with problems such as the landmark placement and motion planning including the localization constraint. Based on this framework, we present general approaches to the optimal distribution of the landmarks or to the computation of reliable trajectories. The case
Cited by 0
Zhenyuan Yang · Applied and Computational Engineering · 2024
A sensor is a device that receives signals and responds to the signals or stimuli. The output of the sensors can be the voltage or current. The input of the sensors is very complex. For different types of sensors, there are different types of input. All sensors are categorized based on their applications and principles. In this article, there are mainly two major categories of sensors in the field of engineering included. One is the localization. The localization mainly includes visual sensors, infrared sensors, lidar and ultrasonic sensors. This paper discusses the application scenarios as well as the advantages and disadvantages of each kind of sensor. The SLAM control algorithm for robotics based on sensors will also be addressed. Another focus of this paper is robot control. It only includes a major type of sensor which is the inertial sensor. For this part, the article mainly discusses the applications and advantages & disadvantages of the gyroscope sensor. Also, the prevailing robotics control algorithm- PID control is illustrated. In a more complex environment in engineering, a single sensor may not meet the requirements of the engineers. So, the combination use of the sensors appears. This article also explores the use of machine learning for intelligent sensor design.
Cited by 0Open access
Ekaterina Nyrobtseva, Josef Černohorský, Nestor Arana-Arexolaleiba · Atlantis highlights in engineering/Atlantis Highlights in Engineering · 2024
Accurate localization in industrial robotics is one of the crucial attributes.One of the most popular localization approaches in robotics is localization with LiDAR.However, when a robot enters a rough environment with smoke, dust or fog, the LiDAR sensor may provide inaccurate measurements.This paper is aimed to confirm the influence of smoke of different densities on LiDAR-based localization and provide a possible solution to overcome the erroneous measurements of light detection sensors.A simulation environment was designed to analyze the level of smoke impact.It includes the simulation of warehouse premises, an industrial robotic platform equipped with Li-DAR together with smoke of different densities.Preliminary results from the simulation verify that smoke obfuscates the localization algorithm.It has also been observed that the simulator response time increases considerably when the number of particles increases.
Cited by 0Open access
Fakhreddine Ababsa, Nour-Eddine Bouguechal · 2002
This paper deals with theoretical and experimental aspects of mobile robotics. The theoretical aspect consists of developing an absolute localization technique based on measurements delivered by a rotating sonar. This technique allows one to localize a mobile robot evolving in an indoor environment (laboratory, factory, etc.). An environment model based on ultrasonic range readings is built (sensor based model) and then compared with the reference model, which is a priori known, using clustering techniques. Identification of specific elements in the sensor model (walls and corners) allows absolute localization of the robot. This technique has been successfully implemented on a built mobile robot with simple sensors and a simple data processing architecture. Experiments and their results are also presented.
Cited by 2
Gabriela Tonţ · 2011
Flexible and adaptive behavior of mobile robots is characterized by context-awareness and the ability to reason using uncertain and imprecise information. A coherent behaviour of mobile robots placed multiple real-time design requirements on the controller, sensors, and actuators, at both hardware and software levels. In the context of use, perceptual-oriented capabilities more dynamically adapt to robot resources are a principle that drives mobile robotics to plans its sensor and effectors actions. The unknown, hidden variables in the mobile robotics can be model by the means of probabilistic inference that take into account incomplete and uncertain information. A sensing plan for mobile robots is enviable based on sensor nodes that consist of sharing small, inexpensive, and robustly inter-networked sensors. The paper investigates the methodology of network for deployment of combined proximity sensors as a localization method for robotic systems in structured and dynamic environments.
Based on the property that Hall Effect sensors can detect the proximity of ferromagnetic objects a localization method for mobile robots in structured environment is studied. Using the deployment of combined proximity sensors as a localization method, the dynamic environments are explored by means of Bayesian belief network.
Cited by 1
Carolina Fany Andreoni Duarte, Israel Amaral, Lorran Pires Venetillo Dutra et al. · Anais do 14º Simpósio Brasileiro de Automação Inteligente · 2019
This paper presents a methodology for teaching mobile robotics for engineering courses at the Federal University of Minas Gerais (UFMG -Brazil).During the course "Mobile Robotics Laboratory", undergraduates use LEGO Mindstorms NXT robotics kits, sensors embedded in an Android cellular and the Robot Operating System (ROS) to implement and experimentally verify techniques regarding localization and mapping, sensory fusion and probabilistic filters.The activities are divided into three main practices based on a line follower robot, where students must: (i) calculate the path traveled using wheel odometry, (ii) fuse the results with cellular IMU data using Kalman filter (EKF), and (iii) perform the simultaneous localization and mapping (SLAM) combining data from a distance sensor through a Rao-Blackwellized particle filter.The article presents theories addressed during the course, describing the practices proposed using ROS and the results obtained so far.
Cited by 0Open access
Damien Vivet, Paul Checchin, Roland Chapuis · Sensors · 2013
Rotating radar sensors are perception systems rarely used in mobile robotics. This paper is concerned with the use of a mobile ground-based panoramic radar sensor which is able to deliver both distance and velocity of multiple targets in its surrounding. The consequence of using such a sensor in high speed robotics is the appearance of both geometric and Doppler velocity distortions in the collected data. These effects are, in the majority of studies, ignored or considered as noise and then corrected based on proprioceptive sensors or localization systems. Our purpose is to study and use data distortion and Doppler effect as sources of information in order to estimate the vehicle's displacement. The linear and angular velocities of the mobile robot are estimated by analyzing the distortion of the measurements provided by the panoramic Frequency Modulated Continuous Wave (FMCW) radar, called IMPALA. Without the use of any proprioceptive sensor, these estimates are then used to build the trajectory of the vehicle and the radar map of outdoor environments. In this paper, radar-only localization and mapping results are presented for a ground vehicle moving at high speed.
Cited by 98Open access
Tae Kyeong Jeong, Yong Jun Lee, Woo Jin Ahn et al. · Applied Sciences · 2025
Accurate vehicle localization remains a critical challenge due to the frequent loss or degradation of sensor data, such as from visual, inertial, and GPS sources. In this study, we present a novel localization algorithm that dynamically fuses data from heterogeneous sensors to achieve stable and precise positioning. The proposed algorithm integrates a deep learning-based visual-inertial odometry (VIO) module with a Kalman filter for global data fusion. A key innovation of the method is its adaptive fusion strategy, which adjusts feature weights based on sensor reliability, thereby ensuring optimal data utilization. Extensive experiments across varied scenarios demonstrate the algorithm’s superior performance, consistently achieving lower RMSE values and reducing position errors by 79–91% compared to four state-of-the-art baselines—even under adverse conditions such as sensor failures or missing data. This work lays the foundation for deploying robust localization systems in real-world applications, including autonomous vehicles, robotics, and navigation technologies.
Cited by 0Open access
Marin B. Marinov, Borislav Ganev, Georgi Nikolov · 2013
The localization of people and objects in different environments is an essential prerequisite for many applications in navigation, robotics, machine control and monitoring. The limiting factor for many applications is the indoor environment in which the Global Satellite Systems work only partially or cannot function at all. Currently radio frequency (RF) based methods are being increasingly implemented for indoor localization. They are relatively inexpensive to install, and are less subjected to the line-of-sight limitations affecting a significant number of other methods. The research presented in this paper aims to evaluate the possibility for using relatively low-cost and easily expandable RF-based localization techniques for lighting control in warehouse environments. The implementation of the localization system utilizes the RSS of a ZigBee-based sensor network.
Cited by 0Open access
Dominic Maggio, Marcus Abate, Jingnan Shi et al. · arXiv (Cornell University) · 2022
We present Loc-NeRF, a real-time vision-based robot localization approach that combines Monte Carlo localization and Neural Radiance Fields (NeRF). Our system uses a pre-trained NeRF model as the map of an environment and can localize itself in real-time using an RGB camera as the only exteroceptive sensor onboard the robot. While neural radiance fields have seen significant applications for visual rendering in computer vision and graphics, they have found limited use in robotics. Existing approaches for NeRF-based localization require both a good initial pose guess and significant computation, making them impractical for real-time robotics applications. By using Monte Carlo localization as a workhorse to estimate poses using a NeRF map model, Loc-NeRF is able to perform localization faster than the state of the art and without relying on an initial pose estimate. In addition to testing on synthetic data, we also run our system using real data collected by a Clearpath Jackal UGV and demonstrate for the first time the ability to perform real-time global localization with neural radiance fields. We make our code publicly available at https://github.com/MIT-SPARK/Loc-NeRF.
Cited by 1Open access
Boyang Xing, Quanmin Zhu, Feng Pan et al. · Sensors · 2018
A novel multi-sensor fusion indoor localization algorithm based on ArUco marker is designed in this paper. The proposed ArUco mapping algorithm can build and correct the map of markers online with Grubbs criterion and K-mean clustering, which avoids the map distortion due to lack of correction. Based on the conception of multi-sensor information fusion, the federated Kalman filter is utilized to synthesize the multi-source information from markers, optical flow, ultrasonic and the inertial sensor, which can obtain a continuous localization result and effectively reduce the position drift due to the long-term loss of markers in pure marker localization. The proposed algorithm can be easily implemented in a hardware of one Raspberry Pi Zero and two STM32 micro controllers produced by STMicroelectronics (Geneva, Switzerland). Thus, a small-size and low-cost marker-based localization system is presented. The experimental results show that the speed estimation result of the proposed system is better than Px4flow, and it has the centimeter accuracy of mapping and positioning. The presented system not only gives satisfying localization precision, but also has the potential to expand other sensors (such as visual odometry, ultra wideband (UWB) beacon and lidar) to further improve the localization performance. The proposed system can be reliably employed in Micro Aerial Vehicle (MAV) visual localization and robotics control.
Cited by 39Open access