An Indoor Route Planning Method with Environment Awareness

Indoor navigation network is the basis of indoor navigation research. How to automatically generate indoor navigation network has become a research hotspot in recent years. At present, the indoor network generation is often obtained through indoor architectural Computer Aided Design (CAD) drawings or lidar Simultaneous Localization and Mapping (SLAM) methods, which are cumbersome and costly to obtain. In order to solve these problems, this paper proposes an automatic extraction method of indoor navigation network. The method first uses the built-in inertial device of the mobile phone to obtain pedestrian indoor motion data, and then uses the Kalman filter algorithm to generate pedestrian motion trajectories. After that, the Douglas-Peucker algorithm and DBSCAN algorithm are used to process the trajectories and construct the indoor navigation network. At the same time, the network will automatically update and optimize the subsequent track when the subsequent track is obtained. The experiment proves that this method can obtain indoor navigation network more quickly and efficiently, and the cost is lower when facing unsuspected environment.

Using WIFI fingerprint positioning is Vulnerable to indoor environment and various noise signals , positioning error in indoor environment to the wireless signal strength is in the controllable range, although the starting point can be obtained, but its accuracy is easily affected by complex indoor environment. Inertial positioning is not affected by the indoor environment, but there is a cumulative error. At present, the widespread application of intelligent mobile phone, the activities of various sensors embedded can indirectly describe pedestrians, with intelligent mobile phone to achieve indoor positioning can not only reduce the cost of positioning, which can meet the daily demand for indoor positioning. Indoor positioning method based on inertial navigation real-time location of pedestrian path and wireless signal fingerprint with the online positioning by using the neural network matching algorithm outperforms the KNN algorithm in the positioning accuracy, so it can avoid the cumulative error of inertial navigation and positioning, and also reduce the influence of environment interference factor on the positioning accuracy, finally verified by experiments two, positioning algorithm combined with neural network positioning result is obviously better than the traditional positioning accuracy.

Indoor localization finds wide-ranging applications in user navigation and intelligent building systems. Nevertheless, signal interference within complex indoor environments and challenges regarding localization generalization in multi-building and multi-floor scenarios have restricted the performance of traditional localization methods based on Wi-Fi fingerprinting. To tackle these issues, this paper presents the SE-MTCAELoc model, a multi-task convolutional autoencoder approach that integrates a squeeze-excitation (SE) attention mechanism for indoor positioning. Firstly, the method preprocesses Wi-Fi Received Signal Strength (RSSI) data. In the UJIIndoorLoc dataset, the 520-dimensional RSSI features are extended to 576 dimensions and reshaped into a 24 × 24 matrix. Meanwhile, Gaussian noise is introduced to enhance the robustness of the data. Subsequently, an integrated SE module combined with a convolutional autoencoder (CAE) is constructed. This module aggregates channel spatial information through squeezing operations and learns channel weights via excitation operations. It dynamically enhances key positioning features and suppresses noise. Finally, a multi-task learning architecture based on the SE-CAE encoder is established to jointly optimize building classification, floor classification, and coordinate regression tasks. Priority balancing is achieved using weighted losses (0.1 for building classification, 0.2 for floor classification, and 0.7 for coordinate regression). Experimental results on the UJIIndoorLoc dataset indicate that the accuracy of building classification reaches 99.57%, the accuracy of floor classification is 98.57%, and the mean absolute error (MAE) for coordinate regression is 5.23 m. Furthermore, the model demonstrates exceptional time efficiency. The cumulative training duration (including SE-CAE pre-training) is merely 9.83 min, with single-sample inference taking only 0.347 milliseconds, fully meeting the requirements of real-time indoor localization applications. On the TUT2018 dataset, the floor classification accuracy attains 98.13%, with an MAE of 6.16 m. These results suggest that the SE-MTCAELoc model can effectively enhance the localization accuracy and generalization ability in complex indoor scenarios and meet the localization requirements of multiple scenarios.

Abstract. The demand for indoor navigation is increasingly urgent in many applications such as safe management of underground spaces or location services in complex indoor environment, e.g. shopping centres, airports, museums, underground parking lot and hospitals. Indoor navigation is still a challenging research field, as currently applied indoor navigation algorithms commonly ignore important environmental and human factors and therefore do not provide precise navigation. Flexible and detailed networks representing the connectivity of spaces and considering indoor objects such as furniture are very important to a precise navigation. In this paper we concentrate on indoor navigation considering obstacles represented as polygons. We introduce a specific space subdivision based on a simplified floor plan to build the indoor navigation network. The experiments demonstrate that we are able to navigate around the obstacles using the proposed network. Considering to well-known path-finding approaches based on Medial Axis Transform (MAT) or Visibility Graph (VG), the approach in this paper provides a quick subdivision of space and routes, which are compatible with the results of VG.

The next step in location services will be repeating the success of location services in outdoor use for navigation and local search in the indoor environment. In order to make indoor positioning and navigation reality in large scale not only compelling business opportunities must be present, but also the technology must be low-cost, low-power, have low maintenance expenses and require minimal amount of new infrastructure. This paper reviews the challenges and solution models for indoor positioning starting from the service level aspects, reflecting them to the architectural considerations and finally discusses selected technical implementation issues.

<p>The interest in indoor positioning systems has been rising in the last couple of decades. This interest was further accelerated by the availability of signals of opportunity. The introduction of signals of opportunity into the indoor environments has meant that these widely available technologies can be utilised to achieve higher levels of accuracy and precision for positioning in parking garages, airports, underground locations, large office buildings, and shopping centres. Indoor positioning can also be utilised for emergency services or for Building Information Models (BIM) for purposes such as construction sites or hospital building management. In addition to the need for indoor and outdoor positioning, there is a need to ensure seamless transitions in and out of these different environments. For example, building information from BIM could be utilised for navigation of BIM users that considers the architectural barriers (e.g., for wheelchairs, baby strollers, and transport of large equipment within the facility). For this, a positioning system capable of seamlessly transitioning in and out of buildings is needed. This paper proposes a multi-sensor and cooperative positioning method of seamless environment transition and presents the first architecture concept. For this purpose, Global Navigation Satellite System (GNSS) data are planned to be fused with Ultra Wide-Band (UWB), Inertial Measurement Unit (IMU), Wireless-Fidelity (Wi-Fi), visual camera and LiDAR (Light Detection and Ranging) data. All sensors required for such a positioning system, are already available on modern smartphones commonly used as low-cost platforms for pedestrian navigation and localisation. Newer smartphones are also equipped with LiDAR and UWB chips, which are a future signal of opportunity, just like Wi-Fi currently is. The transition to different environments will be determined based on the UWB anchors called identical anchors that will be used to transition from the global coordinate system for the outdoor environment to the local building environment for positioning in indoor environments. The proposed multi-sensor and cooperative positioning system is expected to be able to achieve decimetre-level accuracy.</p>

Local positioning in buildings without access to the Internet is a crucial requirement in many scenarios, such as large corporate offices, hospitals, universities, and shopping malls. However, this need for local positioning also presents certain challenges and problems that must be addressed. One of the most significant challenges of local positioning in buildings without internet access is the lack of reliable and up-to-date indoor map data. Without accurate map data, it can be difficult to navigate through complex indoor environments or locate specific rooms or facilities within a building. Another challenge is the absence of GPS signals in indoor environments, which makes it challenging to obtain accurate location information. This is especially problematic when attempting to track the movement of people or objects within a building.Additionally, the lack of internet access can make it difficult to implement location-based services that rely on data transfer between devices. This includes applications like indoor navigation, asset tracking, and location-based marketing, which all require internet connectivity to function correctly. Despite these challenges, there is a growing need for local positioning in buildings without internet access. This is especially true for large organizations and institutions that rely on efficient and effective operations within their indoor environments. Some technologies can provide accurate location information and help to mitigate some of the challenges associated with local positioning in buildings without internet access. They allows to obtain the accurate location information without relying on GPS signals or internet connectivity.The need for local positioning in buildings without internet access is becoming increasingly important, especially for large organizations and institutions that require efficient and effective operations within their indoor environments.

Optimal sensor network deployment in built environments for tracking, surveillance, and monitoring of dynamic phenomena is one of the most challenging issues in sensor network design and applications (e.g., people movement). Most of the current methods for sensor network deployment and optimization are empirical and they often result in important coverage gaps in the monitored areas. To overcome these limitations, several optimization methods have been proposed in the recent years. However, most of these methods oversimplify the environment and do not consider the complexity of 3D architectural nature of the built environments specially for indoor applications (e.g., indoor navigation, evacuation, etc.). In this paper, we propose a novel local optimization algorithm based on a 3D Voronoi diagram, which allows a clear definition of the proximity relations between sensors in 3D indoor environments. This proposed structure is integrated with an IndoorGML model to efficiently manage indoor environment components and their relations as well as the sensors in the network. To evaluate the proposed method, we compared our results with the Genetic Algorithm (GA) and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithms. The results show that the proposed method achieved 98.86% coverage which is comparable to GA and CMA-ES algorithms, while also being about six times more efficient.

With the development of Internet of Thing (IoT), positioning is of a significant importance in indoor environments. Thus, recent years, localization technology has advanced greatly aimed at localizing the target by utilizing existing infrastructure such as WiFi. However, in a complex indoor environment, the performance of localization system tend to fluctuates when there is Non-Line-of-Sight (NLoS) propagation. Specially, for the high accuracy localization system using Angle of Arrival (AoA) or Time of Flight (ToF) of the direct signal path, the robustness is a challenge since the propagations of signal are not always in Line-of-Sight (LoS) due to the complicated indoor environment. Environment sensing is of significant importance for improving the accuracy and robustness of high accuracy localization system working in NLoS environment. In this paper, we propose a context-aware algorithm by using the spatial properties of multipath signal to aid indoor localization. Firstly, we investigate the influence of Signal-Noise-Ratio (SNR) on the distribution of signal spatial parameters, i.e., AoA and ToF, by deriving a mathematical model. Then, we creatively employ the method of clustering tendency analysis to construct a LoS/NLoS identification collaborating with non-parametric statistical method. Finally, we deploy a localization system with the proposed context-aware algorithm. The extensive experimental result shows that the proposed algorithm can sense environment well and further improve the accuracy and robustness of localization system.

High-precision, low-cost, and wide coverage indoor positioning technology is the key to indoor and outdoor integrated location-based services, and it has broad market prospects and social value. However, achieving sub-meter level positioning accuracy in indoor environments remains a real challenge due to the blockage of indoor Global Navigation Satellite System (GNSS) signals, the complexity of indoor environments, and the unpredictability of user behavior. In this paper, we introduce a multi-module BLE broadcaster (MMBB)-based indoor positioning solution in which a tightly coupled fusion architecture is implemented on a smartphone. The solution integrates ranging measurements from multiple MMBB and the measurements of the accelerometer built into a smartphone. It becomes an instant positioning solution without any training phase by adopting a calibrated linearly segmented path loss model for ranging. We apply the pedestrian walking speed derived by the smartphone accelerometer to constrain an unscented Kalman filter method that is used to estimate the location and speed. The accuracy of the proposed method is 50% at 0.79 m and 95% at 1.6 m at in terms of horizontal error distance. Position update frequency is 10 Hz and the time to first fix is 0.1 s. The system can easily adapt a global coordinator system so that it can seamlessly work together with the GNSS to form an indoor/outdoor positioning solution.

Indoor pedestrian navigation systems have become indispensable in modern times, facilitating efficient navigation through complex indoor environments such as malls and airports. Traditional GPS technology falls short in these settings due to signal blockage and reflections, leading to the emergence of indoor positioning systems (IPS). Leveraging technologies like Bluetooth beacons, Wi-Fi triangulation, and ultra-wideband signals, IPS provides precise real-time navigation within buildings. Augmented reality (AR) and virtual reality (VR) further enhance the indoor navigation experience, offering visual cues and pre-navigation simulations. Despite challenges such as precise mapping and signal interference, the adoption of indoor navigation technologies has increased, driven by the demand for better user experiences. This abstract explores the methods, technologies, and challenges associated with indoor pedestrian navigation, providing insights into current trends and future developments.

Introduction Today, the rapid acceleration of urbanization has made it necessary to reconsider the balance among energy consumption, environmental sustainability, and quality of life. Buildings, which account for a significant share of cities’ carbon footprint, play a critical role in efforts to improve energy efficiency and ensure user well-being. In this context, advances in digitalization and Internet of Things (IoT) technologies have enabled buildings to evolve beyond mere physical structures into dynamic, data-driven, and user-interactive systems. Within this framework, the present study constitutes a systematic literature review addressing the effects of indoor environment design in smart cities on energy efficiency (E), user comfort (C), and environmental sustainability (S). In recent years, IoT-based sensor and control technologies have reconfigured approaches to energy management in buildings by enabling the continuous monitoring of environmental parameters such as temperature, humidity, carbon dioxide levels, lighting, and movement, while also strengthening user experience through a holistic perspective. Methods In this regard, the study examined 76 different works in the literature, including field applications, experimental research, and conceptual models. These studies were evaluated through an inductive thematic analysis approach based on content and classified according to recurring conceptual clusters in the literature. Results An examination of these sources reveals that the contributions of IoT technologies to smart buildings and cities are multidimensional in nature. This extensive body of knowledge in the literature demonstrates that IoT is not merely a technical infrastructure but also an ecosystem that transforms energy, health, the environment, transportation, and social life. It is evident that the data derived from all reviewed studies were synthesized under the headings of energy efficiency, indoor environmental quality and comfort, smart city infrastructure, user interaction, security/facility management, and industrial applications. Accordingly, the present study evaluates the contributions of IoT-based solutions to reducing energy consumption, improving environmental conditions, and supporting user-centered indoor design. The reviewed studies show that these technologies not only enhance energy efficiency (maximum savings: smart parking [92.6%] and smart lighting [73.2%]; average building savings: 20–30% through BEMS and IoT systems; HVAC optimization: 30–70% through artificial intelligence), but also support user health and comfort (the use of smart systems is generally expected to produce an improvement of more than 20% in comfort levels, while this rate can reach the 70–90% range with advanced personalized models). Furthermore, they demonstrate that IoT-based systems play a strategic role in achieving environmental sustainability goals, reducing carbon emissions, and implementing smart city policies. Discussion The original contribution of this study lies in its systematic synthesis of energy, comfort, and sustainability within an integrated thematic classification framework, thereby revealing trends in the field, research gaps, and potential future directions.

Indoor localization systems (ILS) evolved over the last years, mainly due to the fact that Global Positioning Systems (GPS) lack precision or fail entirely to localize smartphone users in indoor environments. Many studies attempted to alleviate this issue by utilizing techniques developed on top of technologies, such as Bluetooth beacons and RFID that require costly installation of specialized equipment, or techniques such as Google Wi-Fi/Cell DB and fingerprinting that utilize the received signal strength intensity (RSSI) of the already existing Wi-Fi access points (APs) of a building or cellular towers of the surrounding telecommunication infrastructure. The latter approaches, however, face privacy and/or performance issues since they gain knowledge regarding the requested user location during the indoor localization process and/or require high energy, storage and computational power resources in order to localize the user in situ the smartphone device. In this chapter, we introduce a bio-inspired modeling approach for addressing all the aforementioned concerns. In particular, an artificial neural network is used to model an area’s RSSI data at the server side, which is then forwarded to the client side to predict the user’s current location on the smartphone device. The proposed approach improves the smartphone performance during user navigation while maintaining a fine-grain localization accuracy, but also preserving the user’s privacy with respect to conventional fingerprinting approaches. Our experimental studies demonstrate the superiority of the proposed approach on real datasets of Wi-Fi traces.

Indoor mobile positioning is widely used in shopping malls, energy saving in buildings, medical care and emergency rescue. Range-free algorithms typically use the connectivity of a wireless sensor network system to estimate the location of target nodes, typically through Dv-hop, the prime method, ap-proximate point-in-triangulation test, or APIT for short. -free algorithms can be obtained by changing the distribution density of reference nodes or by changing the blind node communication radius to obtain higher accuracy. Due to constraints such as complex indoor environments, current indoor positioning methods are often less accurate and more expensive. To address these issues, this paper improves on the traditional center-of-mass algorithm by using a six-point center-of-mass algorithm for indoor positioning to further improve the accuracy of the indoor positioning algorithm. To this end, the following work is accomplished in this paper: 1. introduced the algorithms currently used for indoor positioning and their shortcomings, laying the theoretical foundation for the improved approach proposed in the following paper. 2. introduced the basic working principle of the center-of-mass algorithm and proposed an improved system using the six-point center-of-mass algorithm. 3. established the best possible model through experiments, then input test data and evaluated it based on expert judgement. The experimental results show that the model proposed in this study has excellent accuracy in indoor wireless positioning.

With the widespread adoption of smart mobile devices, smartphone-based indoor positioning technology has become a significant area of research. This study proposes a collaborative adaptive multisource data fusion method for indoor positioning, utilizing the inherent multisensor capabilities of smartphones. In the offline phase, a multilayer perceptron (MLP) is trained using collected Wi-Fi fingerprint data. Specifically, we recorded 114 fingerprint locations in Scenario 1 and 99 in Scenario 2, each containing 20000 fingerprint datasets. During the online phase, the system collects real-time Wi-Fi fingerprint data and matches it against the trained dataset. Subsequently, the user’s step length and direction data are integrated into a pedestrian dead reckoning (PDR) algorithm to estimate positions within complex indoor environments. Finally, we apply an adaptive extended Kalman filter (AEKF), which adjusts weights to further improve positioning accuracy. Experimental results demonstrate that the AEKF method reduces root-mean-square errors (RMSEs) to 0.763 and 0.884 m in scenarios with different complexities, enhancing accuracy by 10.13% and 30.17% compared with the traditional EKF methods. Comparative analysis with mainstream algorithms further highlights the advantages of AEKF, achieving maximum accuracy improvements of up to 36.54%. These findings underscore the effectiveness of our approach in advancing indoor positioning technology for mobile applications, offering practicality and cost-effectiveness without requiring additional hardware.