Navigation Performance Research Articles

HOGN-TVGN: Human-inspired Embodied Object Goal Navigation based on Time-varying Knowledge Graph Inference Networks for Robots

Object goal navigation tasks are critical for robots operating in unfamiliar environments, where they must locate specific objects using visual cues. The ability to leverage prior knowledge significantly enhances a robot’s associative capabilities, leading to improved navigation performance. However, existing methods struggle with the generalization challenge when transferring navigation models to new environments, a key issue addressed in this paper. To overcome this challenge, on the one hand, a time-varying knowledge graph is proposed to update the prior knowledge graph with context vectors derived from co-occurrence objects in the current observation. This approach prioritizes local graphs centered around the target and co-occurring objects, allowing for efficient and accurate target localization. Furthermore, the dynamic updating mechanism facilitates efficient exploration in new scenarios. On the other hand, to embed prior knowledge more rationally in the reinforcement learning-based navigation strategy, a time-varying knowledge graph inference network (TVGN) is presented. The TVGN utilizes context vectors and global spatial semantic information to perceive and understand the environment in real-time. It formulates navigation strategies based on the precise goal information encoded within the graph, thereby enhancing the robot’s efficiency in reaching the target. Based on the widely applied dataset AI2-THOR, extensive comparative experiments are conducted to illustrate the effectiveness of the proposed method. Experimental results indicate that our model outperforms state-of-the-art competitors, demonstrating notable advantages in navigation effectiveness and efficiency in previously unseen environments.

Precision Mars Entry Navigation with Atmospheric Density Adaptation via Neural Networks

Spacecraft entering Mars require precise navigation algorithms capable of accurately estimating the vehicle’s position and velocity in dynamic and uncertain atmospheric environments. Discrepancies between the true Martian atmospheric density and the onboard density model can significantly impair the navigation performance. This work introduces a new approach to online filtering for Martian entry using a neural network to estimate atmospheric density and employing a “consider” analysis to account for the uncertainty in the estimate. The network is trained on an exponential atmospheric density model, and its parameters are dynamically adapted in real time to account for any mismatch between the true and estimated densities. The adaptation of the network is formulated as a maximum likelihood problem by leveraging the measurement innovations of the filter to identify optimal network parameters. Within the context of the maximum likelihood approach, incorporating a neural network enables the use of stochastic optimizers known for their efficiency in the machine learning domain. Performance comparisons are conducted against two online adaptive approaches, covariance matching and state augmentation and correction, in various realistic Martian entry navigation scenarios. The results show superior estimation accuracy compared to other approaches and precise alignment of the estimated density with a broad selection of realistic Martian atmospheres sampled from perturbed Mars Global Reference Atmospheric Model data.

Augmented reality navigation method based on image segmentation and sensor tracking registration technology

With the rapid development of modern science and technology, navigation technology provides great convenience for people's life, but the problem of inaccurate localization in complex environments has always been a challenge that navigation technology needs to be solved urgently. To address this challenge, this paper proposes an augmented reality navigation method that combines image segmentation and multi-sensor fusion tracking registration. The method optimizes the image processing process through the GA-OTSU-Canny algorithm and combines high-precision multi-sensor information in order to achieve accurate tracking of positioning and guidance in complex environments. Experimental results show that the GA-OTSU-Canny algorithm has a faster image edge segmentation rate, and the fastest start speed is only 1.8 s, and the fastest intersection selection time is 1.2 s. The navigation system combining the image segmentation and sensor tracking and registration techniques has a highly efficient performance in real-world navigation, and its building recognition rates are all above 99%. The augmented reality navigation system not only improves the navigation accuracy in high-rise and urban canyon environments, but also significantly outperforms traditional navigation solutions in terms of navigation startup time and target building recognition accuracy. In summary, this research not only provides a new framework for the theoretical integration of image processing and multi-sensor data, but also brings innovative technical solutions for the development and application of practical navigation systems.

Model inductive bias enhanced deep reinforcement learning for robot navigation in crowded environments

Navigating mobile robots in crowded environments poses a significant challenge and is essential for the coexistence of robots and humans in future intelligent societies. As a pragmatic data-driven approach, deep reinforcement learning (DRL) holds promise for addressing this challenge. However, current DRL-based navigation methods have possible improvements in understanding agent interactions, feedback mechanism design, and decision foresight in dynamic environments. This paper introduces the model inductive bias enhanced deep reinforcement learning (MIBE-DRL) method, drawing inspiration from a fusion of data-driven and model-driven techniques. MIBE-DRL extensively incorporates model inductive bias into the deep reinforcement learning framework, enhancing the efficiency and safety of robot navigation. The proposed approach entails a multi-interaction network featuring three modules designed to comprehensively understand potential agent interactions in dynamic environments. The pedestrian interaction module can model interactions among humans, while the temporal and spatial interaction modules consider agent interactions in both temporal and spatial dimensions. Additionally, the paper constructs a reward system that fully accounts for the robot’s direction and position factors. This system's directional and positional reward functions are built based on artificial potential fields (APF) and navigation rules, respectively, which can provide reasoned evaluations for the robot's motion direction and position during training, enabling it to receive comprehensive feedback. Furthermore, the incorporation of Monte-Carlo tree search (MCTS) facilitates the development of a foresighted action strategy, enabling robots to execute actions with long-term planning considerations. Experimental results demonstrate that integrating model inductive bias significantly enhances the navigation performance of MIBE-DRL. Compared to state-of-the-art methods, MIBE-DRL achieves the highest success rate in crowded environments and demonstrates advantages in navigation time and maintaining a safe social distance from humans.

Navigation performance analysis of Earth–Moon spacecraft using GNSS, INS, and star tracker

Global Navigation Satellite System (GNSS) can provide an approach for spacecraft autonomous navigation in earth–moon space to make up for the insufficiency of earth-based tracking, telemetry, and control systems. However, its weak power and poor observation geometry near the moon causes new problems. After the GNSS signal characteristics and satellite visibility were evaluated in Phasing Orbit and Lunar Transfer Orbit, we proposed an adaptive Kalman filter based on the Carrier-to-Noise ratio (C/N0) and innovation vector to weaken the influence of GNSS accuracy attenuation as much as possible. The experimental results show that the spacecraft position and velocity accuracy are better than 10 m and 0.1 m/s near the Earth, and better than 50 m and approximately 0.2 m/s near the moon use GNSS with the proposed adaptive algorithms. Additionally, because of the deterioration of navigation performance based on the orbit filter during orbital maneuvering, we used accelerometer data to compensate for the dynamic model to maintain navigation performance. The results of the experiment provide a reference for subsequent studies.

Application of an offline grey box method for predicting the manoeuvring performance

The prediction of manoeuvring performance for safe navigation and effective design of ships increasingly depends on artificial intelligence (AI), mainly digital twin technology. This technology requires a digital model of the physical ship. The hydrodynamic coefficients and parameters of these models are commonly obtained through two experimental methods: the planar motion mechanism (PMM) and the circular motion test (CMT). These methods are time-consuming and expensive, which may not be feasible during the early stages of the design process. This study investigates a cost-effective alternative approach to these methods by implementing a grey box method on ships. For the first of these implementations, a full-scale tanker ship was applied with artificial training data of zigzag manoeuvres. A validation study was carried out by comparing the simulation and free-running model test results of the tanker. For the second of these implementations, a scale model of a car carrier was selected, and several numerical search methods were combined to obtain a more accurate digital model. The 3-degree-of-freedom (DOF) Manoeuvring Modelling Group (MMG) models identified through this combination were validated with simulations and compared with the free-running model test results for various manoeuvres. The contribution of this study lies in the accurate capture of the manoeuvring characteristics of the physical model, which is achieved through the use of the adjustment interval and the combination of various numerical search method of the grey box method. Consequently, the developed model can be used in future studies as a faster decision-making tool for determining the straight-line stability or instability of a ship in the ship design and in predicting the manoeuvring performance of the ship.

Environment adaptive navigation (EAN): A data-driven approach for improved navigation accuracy

The quality of GNSS-based navigation services is highly influenced by the type of operating environment. The urban environments with buildings and structures pose substantial challenges for GNSS navigation accuracy. To address this challenge, we propose a data-driven approach Environment Adaptive Navigation (EAN) because complex mathematical models for GNSS environments are impractical for real-time use due to their processing load. This data-driven approach analyzes real-time GNSS data to understand how the environment affects performance and optimize receiver settings for each scenario. Keeping this in view, raw GNSS data was collected through field trials including the three environments: clear sky, partially degraded, and highly degraded. We then analyzed this data to pinpoint factors affecting accuracy, such as the number of available satellites and standard error measurements. The proposed solution, the EAN algorithm, tackles these limitations of the GNSS due to the urban environments and improves the navigation performance. This data-driven approach analyzes real-time GNSS data to identify the specific environment (clear, partially degraded, or highly degraded). Based on this assessment, EAN dynamically adjusts receiver settings, like tracking loop bandwidth, to achieve optimal performance under those conditions. Integrating the EAN model into GNSS receivers allows for real-time environment detection and adaptive configuration. This EAN-based GNSS receiver holds significant promise for safety-critical applications like Intelligent Transportation Systems (ITS). Precise navigation is crucial for functionalities within ITS, such as route optimization and autonomous vehicle operation. The effectiveness of the EAN-based receiver was validated through a field experiment demonstrating a notable increase in tracked satellites and a substantial reduction in outages within a highly degraded environment.

A study on dual quaternion based cooperative relative navigation of multiple UAVs with monocular vision-inertial integration

This paper addresses a cooperative relative navigation problem for multiple aerial agents, relying on visual tracking information between vehicles. The research aims to investigate a sensor fusion architecture and algorithm that leverages partially available absolute navigation knowledge while exploiting collaborative visual interaction between vehicles in mission flight areas, where satellite navigation-denied regions are irregularly located. To achieve this, the paper introduces a new approach to defining the relative poses of cameras and develops a corresponding process to secure the relative pose information. This contrasts with previous research, which simply linearized the relative pose information of aircraft cameras into navigation states defined in an absolute coordinate system. Specifically, the target pose in relative navigation is defined, and the pose of the camera and feature points are directly derived using dual quaternion representation, which compactly represents both translation and rotation. Furthermore, a mathematical model for the relative pose of the camera is derived through the dual quaternion framework, enabling an explicit pose formulation of relative navigation. The study investigates navigation performance in typical mission flight scenarios using an in-house high-fidelity simulator and quantitatively highlights the contributions of the proposed scheme by comparing the navigation error performance. Consequently, the proposed method demonstrates to have navigation accuracy in decimeter level even in GNSS-denied environments and an improved 3D Root Mean Square (RMS) error by 30% smaller than the conventional absolute navigation framework.

Enhancing Vehicle Navigation and Safety through Integration of Pre-Recorded Maps with Vehicle Control Unit

Powerful navigation and safety systems are vital to ensuring autonomous (DV) or semi-autonomous vehicles continue well in varied environmental conditions. However, in such a world those who depend on that internet connectivity to navigate their car would have problems in areas where network reliability is less than perfect. The purpose of this work is to investigate the feasibility and advantages of combining offline mapping with locally sensed positioning systems for better vehicle navigation and safety. While connected to the internet, vehicles cache offline maps and use local sensor information (such as GPS) from their inertial navigation system or computer vision without needing continuous access. The research outlines a hardware-software architecture with embedded offline map data storage, edge-based road following algorithms and an integration mechanism to advanced driving assistance systems (ADAS). In the evaluation of performance, accuracy assessments with online mapping systems are considered for offline maps and how these can have implications on end driver usability as well impacts on real-world autonomous driving technologies. The results suggest that offline mapping and on-board sensor-based localization would be able to improve vehicle contextual navigation performance in diverse driving scenarios.

A Review of Research on Marine Main Propulsion Systems

Ship power, as an essential component of ship engineering, directly affects the navigation performance, economy, and environmental friendliness of ships. This article reviews the development history of ship power, introduces the main propulsion devices including internal combustion engines, steam engines, and electric motors, and discusses the structure and optimization design of ship power systems. Modern ship power technology includes traditional diesel and gasoline engines, as well as new power devices such as liquefied natural gas (LNG) engines, hybrid power systems, and fuel cells. Electric ships are gaining attention due to their efficiency and environmental benefits. In the future, ship power technology will develop towards green environmental protection, intelligence, integration, diversification, and digitization, providing more reliable and efficient power support for the shipping industry and the advancement of ship engineering.

Heart rate variability modulates memory function in a virtual task

Heart rate variability (HRV) is considered one of the most relevant indicators of physical well-being and relevant biomarker for preventing cardiovascular risks. More recently, a growing amount of research has tracked an association between HRV and cognitive functions (i.e., attention). Research is still scarce on spatial orientation, a basic capability in our daily lives. It is also an important indicator of memory performance, and its malfunctioning working as an early sign of dementia. In this study, a total of 43 female students (M Age = 18.76; SD = 2.02) were measured in their lnRMSSD using the photoplethysmography technique with the Welltory smartphone app. They were also tested in their spatial memory with The Boxes Room, a virtual navigation test. Measures of physical activity were obtained with the International Physical Activity Questionnaire (IPAQ). Correlation analyses and repeated measures ANOVA were performed, comparing participants with high / low lnRMSSD in their spatial performance. Results showed that, at an equal level of physical activity, participants with a higher lnRMSSD were more effective in the early trials of The Boxes Room, being more precise in estimating the correct position of the stimuli. Moreover, a subsequent simple linear regression showed that a higher lnRMSSD was related to a smaller number of errors at the beginning of the spatial task. Overly, these results outline the relationship between HRV and navigation performance in early stages of processing, where the environment is still unknown and the situation is more demanding.

A hybrid optimization method based on extreme learning machine aided factor graph for INS/GPS information fusion during GPS outages

To enhance the navigation capability of the microelectromechanical system (MEMS)-based inertial navigation system (INS)/global positioning system (GPS) integrated system under satellite denied, a hybrid optimization navigation method using minimal learning parameter (MLP) to improve extreme learning machine (ELM) aided adaptive factor graph (AFG) is proposed. The proposed method mainly contains two innovative optimizations: (1) Fully considering the key parameters of each sensor in the INS/GPS integrated navigation system, the factor graph technology is introduced to develop an information fusion model for the system. Based on the maximum correlation entropy criterion and adaptive technology, the existing factor graph method for information fusion is optimized to solve the problem that the abnormal output of each sensor in the INS/GPS integrated system caused by complex environments affects the accuracy of information fusion, thus enhancing the robustness and navigation performance of the INS/GPS integrated system; (2) Moreover, ELM is optimized by MLP to predict the velocity and position observation information of the INS/GPS integrated system and tackle the performance deterioration of the system during GPS outages. The structural parameters of ELM are optimized with the MLP method, aiming to abate the computational burden of the traditional neural network (NN) to avoid “dimension explosion”, as well as enhance the generalization ability and robustness of the network to make it learn from the uncertainty of the system smoothly and quickly. Relevant ground vehicle experiments are designed to evaluate the proposed method. The experimental results demonstrate that the proposed strategy has superior performance and is more feasible for real-time implementation than other comparison approaches.

Wayfinding in pairs: comparing the planning and navigation performance of dyads and individuals in a real-world environment

Navigation is essential to life, and it is cognitively complex, drawing on abilities such as prospective and situated planning, spatial memory, location recognition, and real-time decision-making. In many cases, day-to-day navigation is embedded in a social context where cognition and behavior are shaped by others, but the great majority of existing research in spatial cognition has focused on individuals. The two studies we report here contribute to our understanding of social wayfinding, assessing the performance of paired and individual navigators on a real-world wayfinding task in which they were instructed to minimize time and distance traveled. In the first study, we recruited 30 pairs of friends (familiar dyads); in the second, we recruited 30 solo participants (individuals). We compare the two studies to the results of an earlier study of 30 pairs of strangers (unfamiliar dyads). We draw out differences in performance with respect to spatial, social, and cognitive considerations. Of the three conditions, solo participants were least successful in reaching the destination accurately on their initial attempt. Friends traveled more efficiently than either strangers or individuals. Working with a partner also appeared to lend confidence to wayfinders: dyads of either familiarity type were more persistent than individuals in the navigation task, even after encountering challenges or making incorrect attempts. Route selection was additionally impacted by route complexity and unfamiliarity with the study area. Navigators explicitly used ease of remembering as a planning criterion, and the resulting differences in route complexity likely influenced success during enacted navigation.

Mobile Robot Navigation Based on Noisy N-Step Dueling Double Deep Q-Network and Prioritized Experience Replay

Effective real-time autonomous navigation for mobile robots in static and dynamic environments has become a challenging and active research topic. Although the simultaneous localization and mapping (SLAM) algorithm offers a solution, it often heavily relies on complex global and local maps, resulting in significant computational demands, slower convergence rates, and prolonged training times. In response to these challenges, this paper presents a novel algorithm called PER-n2D3QN, which integrates prioritized experience replay, a noisy network with factorized Gaussian noise, n-step learning, and a dueling structure into a double deep Q-network. This combination enhances the efficiency of experience replay, facilitates exploration, and provides more accurate Q-value estimates, thereby significantly improving the performance of autonomous navigation for mobile robots. To further bolster the stability and robustness, meaningful improvements, such as target “soft” updates and the gradient clipping mechanism, are employed. Additionally, a novel and powerful target-oriented reshaping reward function is designed to expedite learning. The proposed model is validated through extensive experiments using the robot operating system (ROS) and Gazebo simulation environment. Furthermore, to more specifically reflect the complexity of the simulation environment, this paper presents a quantitative analysis of the simulation environment. The experimental results demonstrate that PER-n2D3QN exhibits heightened accuracy, accelerated convergence rates, and enhanced robustness in both static and dynamic scenarios.

An improved crater-based navigation approach using projective invariants

This research presents an innovative approach designed to enhance the performance of crater-based navigation systems. The core of this approach revolves around proposing a novel method for calculating and incorporating the degree of perturbation observed in matched craters. The foundation of our algorithm lies in the concept of comparing the similarity of projective invariants between image and database craters during the crater matching process. The degree of perturbation in each extracted crater is quantified and normalized using a multivariate Gaussian model. These values are subsequently employed as observation weights within the navigation system. Simulation results confirm the effectiveness of our approach in accurately computing weights that reflect the varying levels of error between craters. Moreover, when integrated into the navigation system, proposed method substantially elevates navigation performance.

What Prevents Us From Learning Virtual Reality Space: A Study of Indoor Corridor Angle and Obstacle Transparency

People sometimes become disorientated and feel unnatural in virtual reality (VR) spaces created via devices such as head-mounted displays. The main problem is that multiple structures make it difficult to learn the VR space, particularly indoors. These structures segment the space and form boundaries for sightlines and activity areas. How obstacles in segmented space affect human behavior have been less discussed in studies related to navigation. This study sought to clarify the mechanism for the effect of spatial segmentation effect on human spatial cognition, in the context of indoor navigation. This study was conducted in a VR scenario with an omni-directional treadmill; a total of 76 college students participated, and 52 of them were included in the analysis. The study found that the cognitive distortion from spatial segmentation primarily operates by activity area rather than visual obstruction, and it can be inferred that the basis of human abstraction of spatial information may perhaps be the activity area. Regardless of obstacle transparency, non-rectangular spatial segmentation deteriorates navigational performance. The results suggest that, future metaverse communities should consider designing rectangular segmented activity areas to improve navigation performance and reduce disorientation.

A Fusion Approach for UAV Onboard Flight Trajectory Management and Decision Making Based on the Combination of Enhanced A* Algorithm and Quadratic Programming

The rapid advancement of unmanned aerial vehicle (UAV) technologies has led to an increasing demand for UAV operations in low-altitude, high-density, and complex airspace such as mountains or urban areas. In order to handle complex scenarios and ensure flight safety for UAVs with different flight missions beyond visual line of sight in such environments, a fusion framework of onboard autonomous flight trajectory management and decision-making system using global strategical path planning and local tactical trajectory optimization combination is proposed in this paper. The global strategical path planning is implemented by an enhanced A* algorithm under the multi-constraint of UAV positioning uncertainty and obstacle density to improve the safety and cost-effectiveness. The local tactical trajectory optimization is realized using quadratic programming to ensure smoothness, kinematic feasibility, and obstacle avoidance of the planned trajectory in dynamic environments. Receding-horizon control is used to ensure the flight path and trajectory planning efficiently and seamlessly. To assess the performance of the system, a terrain database and a navigation system are employed for environment and navigation performance simulation. The experimental results confirm that the fusion approach can realize better safety and cost-effectiveness through path planning with kino-dynamic feasible trajectory optimization.

Application Research of 5G Communication Technology in Satellite Navigation and Positioning

With the rapid development of 5G communication technology and the increasing perfection of global satellite navigation and positioning, the application of 5G communication technology in satellite navigation and positioning is particularly important. Based on the overview of 5G communication technology and satellite navigation and positioning, this paper analyzes the important value of 5G communication technology in satellite navigation and positioning, and then discusses the application of 5G communication technology and satellite navigation and positioning, aiming to integrate 5G communication technology, further improve the performance of satellite navigation and positioning system, and expand its application scenarios. It will bring greater convenience and benefits to social development.

Positioning of a lunar surface rover on the south pole using LCNS and DEMs

With the renewed interest in the lunar surface exploration, the European Space Agency is supporting, as part of the Moonlight program, the development of a dedicated Lunar Communications and Navigation Service (LCNS) infrastructure. This should enable to achieve real time positioning and autonomous navigation in the cislunar space, including, among others, lunar landing and surface operations. One of the services proposed, as part of the LunaNet framework (NASA, 2022), is called the Lunar Augmented Navigation Service (LANS) and it is based on a GNSS-like concept. However, compared to Earth-based GNSS, the expected number of available satellites in lunar orbit will initially be limited, which triggers the interest of coupling these technologies at the receiver level with other navigation data sources. In the case of surface rovers, use of digital elevation model (DEM) data has shown to be a potential other source of information to support positioning. The purpose of this contribution is to look at the actual navigation performances achievable when using a simple (four satellites constellation) lunar radio navigation constellation combined with a DEM, through a state estimation filter, for different rover dynamic and different DEM accuracy levels. It is shown that a 5 meter real-time horizontal position accuracy can be achieved, for 99.7% of the time, using a precise enough DEM (5 m/pixel) and a 4 satellite-constellation under different rover’s dynamic conditions (i.e. velocities).

Spreading code optimization for low-earth orbit satellites via mixed-integer convex programming

Optimizing the correlation properties of spreading codes is critical for minimizing inter-channel interference in satellite navigation systems. By improving the codes’ correlation sidelobes, we can enhance navigation performance while minimizing the required spreading code lengths. In the case of low-earth orbit (LEO) satellite navigation, shorter code lengths (on the order of a hundred) are preferred due to their ability to achieve fast signal acquisition. Additionally, the relatively high signal-to-noise ratio in LEO systems reduces the need for longer spreading codes to mitigate inter-channel interference. In this work, we propose a two-stage block coordinate descent (BCD) method which optimizes the codes’ correlation properties while enforcing the autocorrelation sidelobe zero property. In each iteration of the BCD method, we solve a mixed-integer convex program over a block of 25 binary variables. Our method is applicable to spreading code families of arbitrary sizes and lengths, and we demonstrate its effectiveness for a problem with 66 length-127 codes and a problem with 130 length-257 codes.