Indoor Obstacles Research Articles

Effects of exit obstacles on the evacuation dynamics of blind people

The modeling of blind people’s behavior is an important topic in pedestrian evacuation dynamics. In order to study movement characteristics of blind people in evacuation process and the effect of indoor obstacles on the evacuation efficiency of blind people, an extended cellular automata model is proposed to simulate blind people evacuation by considering the influence of obstacles. The control variable method is adopted to study the effect of indoor obstacles on the blind evacuation efficiency rule. The numerical simulation is applied to analyze the evacuation process of blind people under different setting (e.g. the location, size and other factors) of obstacles and different evacuation scenarios. The shunt effect of obstacles is discussed and the layout strategy of obstacles is optimized. The results show that the longitudinal obstacles in front of the exit can effectively play the diversion role of obstacles when the obstacle is at a certain distance from the exit, which will improve the evacuation efficiency of the blind. Furthermore, a horizontal obstacle of appropriate length can constrain the trajectory of the blind people and improve the efficiency of evacuation, but when the horizontal obstacle is too long, it will induce extra jam on both sides of the obstacle and hinder the evacuation of the blind. The finding can provide the theoretical basis for the blind people’s organization, management and the optimization of evacuation strategies during an emergency.

High-Performance and Lightweight AI Model for Robot Vacuum Cleaners with Low Bitwidth Strong Non-Uniform Quantization

Artificial intelligence (AI) plays a critical role in the operation of robot vacuum cleaners, enabling them to intelligently navigate to clean and avoid indoor obstacles. Due to limited computational resources, manufacturers must balance performance and cost. This necessitates the development of lightweight AI models that can achieve high performance. Traditional uniform weight quantization assigns the same number of levels to all weights, regardless of their distribution or importance. Consequently, this lack of adaptability may lead to sub-optimal quantization results, as the quantization levels do not align with the statistical properties of the weights. To address this challenge, in this work, we propose a new technique called low bitwidth strong non-uniform quantization, which largely reduces the memory footprint of AI models while maintaining high accuracy. Our proposed non-uniform quantization method, as opposed to traditional uniform quantization, aims to align with the actual weight distribution of well-trained neural network models. The proposed quantization scheme builds upon the observation of weight distribution characteristics in AI models and aims to leverage this knowledge to enhance the efficiency of neural network implementations. Additionally, we adjust the input image size to reduce the computational and memory demands of AI models. The goal is to identify an appropriate image size and its corresponding AI models that can be used in resource-constrained robot vacuum cleaners while still achieving acceptable accuracy on the object classification task. Experimental results indicate that when compared to the state-of-the-art AI models in the literature, the proposed AI model achieves a 2-fold decrease in memory usage from 15.51 MB down to 7.68 MB while maintaining the same accuracy of around 93%. In addition, the proposed non-uniform quantization model reduces memory usage by 20 times (from 15.51 MB down to 0.78 MB) with a slight accuracy drop of 3.11% (the classification accuracy is still above 90%). Thus, our proposed high-performance and lightweight AI model strikes an excellent balance between model complexity, classification accuracy, and computational resources for robot vacuum cleaners.

Construction of indoor obstacle element map based on scene-aware priori obstacle rules

An obstacle element map is the basis of indoor navigation space subdivision. Effective and reasonable indoor space subdivision can improve the fineness of indoor navigation path planning. To divide an indoor navigation space more finely, an indoor obstacle element map construction method based on scene-aware a priori rules for obstacles is proposed. This method divides indoor space into navigable space (N-space), semi-navigable space (SN-space), and non-navigable space (NN-space) based on the flexible space subdivision framework (FSS) and classifies indoor obstacles into four categories, walls, doors, movable obstacles (MOs), and immovable obstacles (IMOs). First, by analyzing the layout and mobility of common indoor elements, the obstacle prior rules for seven types of indoor scenes (including hospitals, residences, classrooms, office buildings, transportation hubs, restaurants, and shopping malls) are formulated, and a method for obtaining obstacle prior rules based on scene recognition is proposed. Then, obstacles and their mobility are extracted from the semantic segmentation results of point clouds based on the acquired rules and mobility indicators. Finally, the extracted obstacles are processed to construct the obstacle element map, wall and door elements are fitted by the random sample consensus (RANSAC) algorithm, and IMOs and MOs are processed by Euclidean clustering. The experimental results show that the proposed method can effectively determine four types of indoor obstacles, and the overall accuracy in simple scenes is 85.22 %, while in complex scenes it is 97.96 %. Under the experimental environment (CPU: Intel Core i7-7700K; Memory: 16 GB and 2400 MHz; OS: Win10) in this paper, the construction of a simple scene obstacle element map can be completed in 5 s. In addition to the spatial information of the indoor elements, the obstacle element map also contains information about whether the elements can be moved, which provides the basis for the subdivision of the indoor space.

A Novel Carrier Loop Based on Coarse-to-Fine Weighted Adaptive Kalman Filter for Weak Communication-Positioning Integrated Signal.

We propose a communication-navigation integrated signal (CPIS), which is superimposed on the communication signal with power that does not affect the communication service, and realizes high-precision indoor positioning in a mobile communication network. Due to the occlusion of indoor obstacles and the power limitation of the positioning signal, existing carrier loop algorithms have large tracking errors in weak signal environments, which limits the positioning performance of the receiver in a complex environment. The carrier loop based on Kalman filtering (KF) has a good performance in respect of weak signals. However, the carrier frequency error of acquisition under weak signals is large, and the KF loop cannot converge quickly. Moreover, the KF algorithm based on fixed noise covariance increases or diverges in filtering error in complex environments. In this paper, a coarse-to-fine weighted adaptive Kalman filter (WAKF)-based carrier loop algorithm is proposed to solve the above problems of the receiver. In the coarse tracking stage, acquisition error reduction and bit synchronization are realized, and then a carrier loop based on Sage–Husa adaptive filtering is entered. Considering the shortcomings of the filter divergence caused by the negative covariance matrix of Sage–Husa in the filter update process, the weighted factor is given and UD decomposition is introduced to suppress the filtering divergence and improve the filtering accuracy. The simulation and actual environment test results show that the tracking sensitivity of the proposed algorithm is better than that based on the Sage–Husa adaptive filtering algorithm. In addition, compared with the weighted Sage–Husa AKF algorithm, the coarse-to-fine WAKF-based carrier loop algorithm converges faster.

Design of a Small Sweeping Robot Based on STM32

With the continuous improvement of people’s living standards and the emergence of various intelligent appliances, a household floor sweeping robot is designed in this subject, which can automatically clean the ground in the room. The robot takes STM32F103ZET6 single chip microcomputer as the controller, uses two DC motors and L298N driving chips to drive the robot to walk, and uses ultrasonic sensors to detect indoor obstacles, The infrared sensor is used to detect the indoor edge position, the straight travel control of the robot is realized through the coding disk combined with PID algorithm, and the turning control is realized through differential control and PWM speed regulation. The robot can realize the garbage cleaning in the regular room, and has a certain application prospect.

Research on SLAM based on RBPF algorithm in indoor environment

In order to realize the simultaneous localization and mapping (SLAM) of robots in indoor environments, a SLAM method for four-wheel mobile robots based on RBPF algorithm and lidar is proposed. The mobile robot realizes its own positioning during the movement. The lidar scans the location of indoor obstacles, updates the map in real time, and gradually realizes the construction of a local map to a global map through data association. Aiming at the particle barrenness that may occur when the RBPF algorithm realizes SLAM during resampling, an adaptive resampling method is adopted to ensure that there are enough particles to realize SLAM every time. The experimental results show that when the linear velocity and angular velocity of the four-wheel mobile robot are small, indoor SLAM can be better realized.

A new deep learning-based distance and position estimation model for range-based indoor localization systems

Many fine-grained indoor localization systems rely on accurate distance estimation between anchors and a target node to determine its exact position. The Received Signal Strength Indicator (RSSI) is commonly used for distance estimation because it is available in most low cost standard wireless devices. Despite the cost efficiency, the distance estimation accuracy in the RSSI-based ranging model needs to be enhanced, especially indoors. The RSSI is sensitive to multiple indoor factors that fluctuate in time and space and lead therefore to its variation. These factors are the origin of the distance estimation error increase in RSSI-based ranging models which in turn raise the position estimation error. Previous works have presented different in-site self-calibration processes to improve the accuracy of distance estimation using RSSI-to-distance samples. It permits to settle the parameters of the RSSI-based ranging model such as the Path Loss Model (PLM) and to mitigate the changing behavior of the RSSI. However, the RSSI measurement depends not only on the distance between the transmitter and the receiver but also on the indoor ambient temperature and humidity variations. Besides, indoor obstacles such as furniture, metallic surfaces or walls have also an impact on the RSSI measurements. We present in this paper a new RSSI-based indoor ranging model using deep learning on collected in-site samples to ensure efficient and autonomic calibration process. This permits to mitigate disturbing factors such as temperature, humidity and noise in order to increase the accuracy of both distance and position estimations. The experimental results have shown that our ranging model has improved not only the precision of distance estimation but also the position estimation in the range-based indoor localization systems.

Generating Comfortable Navigable Space for 3D Indoor Navigation Considering Users' Dimensions.

Most existing indoor navigation methods implicitly treat indoor users as ideal points. However, the ignorance of individual 3D indoor space needs may result in that navigation users do not have enough space or comfortable space to move in a real situation. Therefore, this paper proposes a novel human-oriented navigation approach that considers users’ dimensions and interactions with indoor objects to establish comfortable navigable space. First, object space (O-Space) for users is derived according to their types (i.e., non-disabled people or disabled people) and functional space (F-Space) for indoor objects is determined according to their functions, locations, sizes, and interactions. Then, narrow gaps where users cannot pass through easily are calculated based on indoor obstacles defined by O-Space, the use of F-Space, and stationary objects. Finally, comfortable navigable space is established by excluding inappropriate sealed spaces that wrap indoor obstacles and narrow gaps of the entire indoor space. Two indoor navigation cases were conducted and the results demonstrate that our method could provide comfortable space and user-friendly paths that navigation users can navigate easily without stress. Furthermore, our method also shows great potential for improving user experience during navigation, especially in unfamiliar indoor environments and even emergencies.

Wireless Indoor Positioning With Vertically Uniform Alternating Magnetic Fields

With the growing demands for localizing humans and mobile service robots, wireless indoor positioning has become a hot topic. Due to inevitable multipath scatterings in indoor spaces, technical challenges still exist. In this paper, we propose a new solution based on vertically uniform alternating magnetic fields. Such fields can be established by long coils driven by watt-level alternating currents with hertz-scale frequencies. Detected by commercial magnetic sensors, the coexisting dual-frequency magnetic fields are able to distribute in indoor spaces with tens of square meters. With 104-km-scale wavelengths, indoor obstacles can be considered as negligible Rayleigh scatters, and thus, this method is robust in complex indoor environments. Insensitive to height, the vertically polarized magnetic fields can be conveniently detected by existing smartphones, implying a human-oriented WIP based on smartphones.

Integrated IMU with Faster R-CNN Aided Visual Measurements from IP Cameras for Indoor Positioning

Considering the radio-based indoor positioning system pertaining to signal degradation due to the environmental factors, and rising popularity of IP (Internet Protocol) cameras in cities, a novel fusion of inertial measurement units (IMUs) with external IP cameras to determine the positions of moving users in indoor environments is presented. This approach uses a fine-tuned Faster R-CNN (Region Convolutional Neural Network) to detect users in images captured by cameras, and acquires visual measurements including ranges and angles of users with respect to the cameras based on the proposed monocular vision relatively measuring (MVRM) method. The results are determined by integrating the positions predicted by each user’s inertial measurement unit (IMU) and visual measurements using an EKF (Extended Kalman Filter). The results experimentally show that the ranging accuracy is affected by both the detected bounding box’s by Faster R-CNN height errors and diverse measuring distances, however, the heading accuracy is solely interfered with bounding box’s horizontal biases. The indoor obstacles including stationary obstacles and a pedestrian in our tests more significantly decrease the accuracy of ranging than that of heading, and the effect of a pedestrian on the heading errors is greater than stationary obstacles on that. We implemented a positioning test for a single user and an external camera in five indoor scenarios to evaluate the performance. The robust fused IMU/MVRM solution significantly decreases the positioning errors and shows better performance in dense multipath scenarios compared with the pure MVRM solution and ultra-wideband (UWB) solution.

Wifi-friendly building, enabling wifi signal indoor: an initial study

The 802.11 network (wireless fidelity/WiFi) is the most common wireless infrastructure applied for internet access indoor. Widespread devices and installation simplicity make it better than similar technologies such as 802.16 and other 802.xx series. The access points are the most influential devices for indoor access. However, building indoor architectures contribute to the signal quality. Since WiFi installation in buildings becomes prevalent, the architecture should consider WiFi-friendliness into consideration. The more friendly the building to WiFi signal, the more efficient the 802.11 based wireless infrastructure. This paper present preliminary study how the building, specially the obstacle material, effects the WiFi signal propagation indoor. The study was performed by using ESP8266-based WiFi signal reader, to determine the impact indoor obstacles to WiFi signal propagation. The initial study shows that simple reflecting materials increase signal level about 1.14 dBm. WiFi-friendly building can be achieved by transforming building properties into signal interconnector. A simple photo frame with aluminium sheet insertion increase signal level on the second floor up to 6.56dBm.

Indoor Semantic Modelling for Routing: The Two-Level Routing Approach for Indoor Navigation

Indoor Semantic Modelling for Routing: The Two-Level Routing Approach for Indoor Navigation

Obstacle mapping in wireless sensor networks via minimum number of measurements

In this study, a group of wireless sensors are tasked to trace indoor obstacles without the need to sense them, directly. The authors introduce a novel framework based on compressed sensing theory that allows sensors to map two-dimensional spatial details, non-invasively. By exploiting an alternative projection method which reduces the randomness nature of previous works, the resulting measurement matrix can provide linear samples from an unknown environment more efficiently. It is shown that how sparse representation of the spatial parameters in some domains can be utilised in order to realise obstacle mapping with minimum number of wireless transmissions and receptions. In addition, theoretical analyses along with simulation results illustrate premier performance of their framework. Furthermore, they test their method in different circumstances and show how drawbacks such as walls, bulkheads, and environmental constraints can affect the reconstruction performance. Therefore, they proposed two algorithms (i.e. reducing wall effect and reducing bulkhead effect) in order to decrease the impression of walls and bulkheads which is supported theoretically. Finally, a well-applicable scenario based on their framework is defined and proposing the next best transmitter algorithm remarkable results are achieved.

Interval type 2 fuzzy localization for wireless sensor networks

Indoor localization in wireless sensor networks (WSN) is a challenging process. This paper proposes a new approach to solve the localization problematic. A fuzzy linguistic localization scheme is proposed. Based on interval type 2 fuzzy logic (IT2FL), a signal processing of the radio signal strength indicator (RSSI) minimizes the uncertainty in RSSI measurements from anchors caused by the indoor obstacles. The fuzzy system subdivides the map on fuzzy sets described by a new fuzzy location indicator (FLI). Fluctuations on RSS fingerprints are then reduced thanks to the IT2FL in the input side and the FLI in the output side. Experimentations were done in the Cynapsys indoor environment on a WSN test bed. The experimental results prove higher success rate in position estimations thanks to the FLI concept and the superiority of interval type 2 fuzzy logic to handle signal fluctuations.

밀폐공간에서 Wi-Fi기반 통신 연결 방안에 대한 기초 연구

Recently, thanks to advances in ICT(Information and Communication Technology), a large number of robot systems and specialized equipments are deployed in order to substitute for fire fighters in fire and disaster sites. However, when these unmaned devices are controlled by wireless remote controllers at the remote site, they may suffer from significant performance degradations such as interference, signal collision and fading due to unexpected indoor obstacles. In this paper, the extended measurements and analyses of wireless communication failures are conducted by using commercial wireless devices. All experiments are performed in confined and enclosed spaces such as office and dormitory which is consisted of a number of densely populated small rooms. Finally, the appropriate solutions for such enclosed spaces are proposed especially when wireless devices are deployed. We expect that the proposed communication scenarios can improve the search and rescue performance in real disaster sites.

Efficient Sensor Localization for Indoor Environments Using Classification of Link Quality Patterns

In ubiquitous sensor networks (USN), sensor node localization is normally performed with global positioning system (GPS) or radio signal strength (RSS) between a target node and reference nodes. Because GPS is not available in indoor environments, RSS-based approach is commonly used for indoor localization. However, RSS-based approach is hard to be applied to real indoor environments (e.g., home) because of signal interferences with various indoor obstacles such as walls, doors, furniture, and electric appliances. In this paper, we propose an efficient indoor localization method for Zigbee sensor nodes by classifying link quality indicator (LQI) patterns between a target node and multiple reference nodes rather than using calculation with RSS values. And we also present the results of indoor localization experiments in our ubiquitous home network test bed using the proposed localization method.

A WSN-Based Localization Scheme Considering the Reliability of RSSI Measurements

In this paper, we propose a localization scheme considering the reliability of RSSI (Received Signal Strength Indication) measurements in the WSN (Wireless Sensor Network) environment. This scheme attempts to reduce location errors due to indoor obstacles or environmental factors, when location calculations are based on RSSI. The standard deviation is used to evaluate the reliability of RSSI measurements from the reference node. Also, the directional path loss exponent is calculated through learning with respect to the reference node. The experimental results show that the proposed localization scheme improves the performance significantly in terms of location accuracy, compared to the existing RSSI-based approaches.

Efficient Sensor Localization Method with Classifying Environmental Sensor Data

Sensor location estimation is important for many location-based systems in ubiquitous environments. Sensor location is usually determined using a global positioning system. For indoor localization, methods that use the received signal strength (RSS) of wireless sensors are used instead of a global positioning system because of the lack of availability of a global positioning system for indoor environments. However, there is a problem in determining sensor locations from the RSS: radio signal interference occurs because of the presence of indoor obstacles. To avoid this problem, we propose a novel localization method that uses environmental data recorded at each sensor location and a data classification technique to identify the location of sensor nodes. In this study, we used a wireless sensor node to collect data on various environmental parameters—temperature, humidity, sound, and light. We then extracted some features from the collected data and trained the location data classifier to identify the location of the wireless sensor node.

Analysis and Modeling of Near-Ground Wave Propagation in the Presence of Building Walls

An efficient semi-analytic model for near-ground wave propagation in indoor scenarios is presented. For transceivers deployed in indoor environments on or near the ground, since RF wave propagation is dominated by Norton surface waves, these higher order waves and their interactions with building walls and other indoor obstacles have to be captured for accurate field calculations. Existing ray tracing routines which are commonly used for indoor field prediction, are inadequate for evaluating signal coverage of transceiver nodes very close to the ground (less than a wavelength above ground) since such routines neglect higher order surface waves. In addition, geometrical optics alone is inadequate to treat finite-size and possible irregular-shaped obstacles at low radio frequencies (VHF and lower UHF). Our approach for calculation of near-ground wave propagation and scattering is based on a hybrid physical optics and asymptotic expansion of dyadic Green's function for a half-space dielectric medium. Equivalence principle in conjunction with physical optics approximation is utilized to handle scattered field from building walls which are the dominant scatterers in indoor settings. Simulation results for various indoor propagation scenarios based on the new approach is validated by using both measurement results and full-wave numerical solvers.

The Influence of Indoor Obstacles on General Ventilation Designs

The Influence of Indoor Obstacles on General Ventilation Designs