Navigation Algorithm Research Articles

Unmanned Ground Vehicles for Continuous Crop Monitoring in Agriculture: Assessing the Readiness of Current ICT Technology

Continuous crop monitoring enables the early detection of field emergencies such as pests, diseases, and nutritional deficits, allowing for less invasive interventions and yielding economic, environmental, and health benefits. The work organization of modern agriculture, however, is not compatible with continuous human monitoring. ICT can facilitate this process using autonomous Unmanned Ground Vehicles (UGVs) to navigate crops, detect issues, georeference them, and report to human experts in real time. This review evaluates the current state of ICT technology to determine if it supports autonomous, continuous crop monitoring. The focus is on shifting from traditional cloud-based approaches, where data are sent to remote computers for deferred processing, to a hybrid design emphasizing edge computing for real-time analysis in the field. Key aspects considered include algorithms for in-field navigation, AIoT models for detecting agricultural emergencies, and advanced edge devices that are capable of managing sensors, collecting data, performing real-time deep learning inference, ensuring precise mapping and navigation, and sending alert reports with minimal human intervention. State-of-the-art research and development in this field suggest that general, not necessarily crop-specific, prototypes of fully autonomous UGVs for continuous monitoring are now at hand. Additionally, the demand for low-power consumption and affordable solutions can be practically addressed.

An adaptive EKF‐SLAM algorithm for cooperative navigation of multi‐aircrafts

AbstractAiming at cooperative navigation of multi‐aircrafts, an adaptive EKF‐SLAM algorithm for non‐fixed landmark is proposed. First, the aircraft motion model and angle measurement model are established. Second, the fixed landmark cooperative EKF‐SLAM algorithm is established. Furthermore, a distributed EKF‐SLAM algorithm is designed. Then, the adaptive EKF‐SLAM algorithm with non‐fixed landmark is proposed. Finally, simulation results verify the effectiveness of the proposed algorithm.

Hybrid Mobile Robot Path Planning Using Safe JBS-A*B Algorithm and Improved DWA Based on Monocular Camera

This paper addresses the formidable challenge of enabling autonomous navigation in Mobile Robots (MRs), focusing on the development of advanced path planning strategies. Despite their pivotal role in diverse applications, they face challenges in dynamic settings due to limitation in existing Global Path Planning (GPP) and Local Path Planning (LPP) techniques. In response to this, we propose an innovative hybrid path planning approach that enhances the A* algorithm with a risk-aware heuristic function and integrates the Jump Point Search (JPS) technique for route optimization. Additionally, B-spline smoothing is employed for perceptually global trajectory refinement. Our approach also includes an innovative improvement to the Dynamic Window Approach (DWA) to align with the proposed enhanced A* algorithm for effective local navigation. Acknowledging the importance of high-quality input in path planning, we present substantial improvements to the IRDC-Net, a monocular-image semantic-segmentation model that we studied previously. Novel improvements include the integration of quantization and the Adam optimizer, along with the implementation of the Balanced Cross-Entropy loss function. These enhancements not only elevate the output quality of IRDC-Net but also reduce the model’s training parameters. The experimental results demonstrate the performance and viability of the proposed algorithm. Ultimately, the hybrid MR’s path planning algorithm exhibits proficiency across various tasks, particularly in addressing the challenge of evading moving obstacles to ensure the robot’s safety while adhering to the global path.

Performance Evaluation of a Bioinspired Geomagnetic Sensor and Its Application for Geomagnetic Navigation in Simulated Environment.

For geomagnetic navigation technology, taking inspiration from nature and leveraging the principle of animals' utilization of the geomagnetic field for long-distance navigation, and employing biomimetic technology to develop higher-precision geomagnetic sensors and more advanced navigation strategies, has emerged as a new trend. Based on the two widely acknowledged biological magnetic induction mechanisms, we have designed a bioinspired weak magnetic vector (BWMV) sensor and integrated it with neural networks to achieve geomagnetic matching navigation. In this paper, we assess the performance of the BWMV sensor through finite element model simulation. The result validates its high measurement accuracy and outstanding adaptability to installation errors with the assistance of specially trained neural networks. Furthermore, we have enhanced the bioinspired geomagnetic navigation algorithm and proposed a more advanced search strategy to adapt to navigation under the condition of no prior geomagnetic map. A simulated geomagnetic navigation platform was constructed based on the finite element model to simulate the navigation of the BWMV sensor in geomagnetic environments. The simulated navigation experiment verified that the proposed search strategy applied to the BWMV sensor can achieve high-precision navigation. This study proposes a novel approach for the research of bioinspired geomagnetic navigation technology, which holds great development prospects.

A specialized inclusive road dataset with elevation profiles for realistic pedestrian navigation using open geospatial data and deep learning

Built environment characteristics can greatly influence pedestrians' route choices with factors beyond distance, such as accessibility, convenience, safety, and aesthetics, playing crucial roles. Although current navigation apps, such as Google Maps and Waze, have successfully provided driving directions, their navigation services are insufficient and sometimes unrealistic for addressing pedestrians' needs, largely due to the lack of dedicated pedestrian networks and the associated navigation algorithms. To address the research gaps, this paper proposes a novel approach that integrates freely available geospatial data and computer vision technology to create a specialized inclusive network dataset for outdoor pedestrian navigation. Moreover, a pedestrian navigation algorithm is developed to generate more practical “shortest” and “alternative” paths by incorporating various sidewalk attributes. We applied the method to create a pedestrian navigation network in Las Vegas. SpaceNet's open imagery dataset was used to extract Las Vegas's road networks. A virtual audit process assessed the visual and operational properties of the sidewalk networks using Google street-level images, evaluating factors including sidewalk presence, widths, surface types and conditions, missing curb ramps, greenery, protection from weather conditions, and lighting. Google Earth's open elevation data were used to analyze road elevation profiles as meaningful 3D indicators of sidewalk accessibility for wheelchair users. Further, additional geometric properties of the network, including road curviness, proximity to road intersections, and directional changes, were detected and analyzed. A navigation experiment conducted with individuals having varying mobility abilities, including regular pedestrians, older adults, and wheelchair users demonstrated the effectiveness of the newly developed network and algorithm in meeting the diverse needs of pedestrians.

Evaluation of Autonomous Navigation and Path Accuracy for Unmanned Surface Vehicles Using IMU Sensor and GPS Data

The development of autonomous systems for environmental monitoring is becoming increasingly important. This project focuses on creating a robotic marine vessel, Aqua Sense, for efficient water quality monitoring. Existing methods are often labour-intensive, time-consuming, and lack real-time data capability. The objective is to develop a robotic vessel with autonomous navigation for water quality applications. A comprehensive design approach, including a literature review and careful component selection, was employed. Key components include the Arduino Mega, Blue Robotics T200 thruster, GlobalSat BU-353N5 GPS sensor, BNO055 Inertial Measurement Unit (IMU), and a Li-po 11.1v battery. In this paper, several field trials data collection is presented to evaluate the navigation algorithm. These findings validate the feasibility of Aqua Sense for real-world applications. The varying distance errors at points B and C demonstrate an error range, with a maximum error of approximately 1.130m at point B (about 0.11% of the target location) and a significant variation at point C, reaching up to 1.660m (approximately 0.15%).

A Distributed Multi-Vehicle Coordination Algorithm for Navigation in Tight Environments

A Distributed Multi-Vehicle Coordination Algorithm for Navigation in Tight Environments

Manoeuvring in shallow and confined water with model predictive track controllers

Abstract Autonomous and computer-assisted navigation, for example through portable pilot units and data-driven decision supportive systems, is in full development. Remote-controlled vessels (manned but without a captain steering continuously on board) are used in Belgium (by Seafar in inland shipping) but also in other countries. A model predictive controller has been used to investigate environmental and operational parameters for the passage of the river Seine in Paris by different ship types. These fast-time simulations have been compared with simulations in real time executed by skippers on a ship manoeuvring simulator or measured real life tracks. A good predictability of the real situation requires accurate manoeuvring models. But what if this accuracy cannot be guaranteed? An illustration is made by comparing the tracks if, in the prescience prediction phase for the controller, wind or bank effects are neglected or doubled. The development of model predictive deep reinforcement learning control algorithms for navigation will be one of the challenges of the Data-driven Smart Shipping project that started May 2024.

Research on deep reinforcement learning-based complex crowd navigation algorithm using risk perception and path selection

Abstract Aiming at the Frozen Robot Problem and the poor effect of dynamic obstacle avoidance in traditional navigation methods when encountering dynamic obstacles, a deep reinforcement learning navigation method based on risk perception and path selection is proposed. The core of this method lies in CP (Collision Probability) module and IOU (Intersection over Union) module. The CP module calculates the CP between the robot and the nearby dynamic obstacles in real time, so that the robot can avoid the dangerous obstacles first. At the same time, the intersection-merging ratio module calculates the “pass ability” of the area near the robot in real time, and guides the robot to choose a safer area to pass through. Compared with the DRL method without these two modules, the proposed method achieves the highest navigation success rate in all simulation test environments, and the maximum improvement rate is 11%. At the same time, it still has advantages in navigation time and other indicators.

Lidar-Based Obstacle Detection and Path Prediction for Unmanned Surface Vehicles

Abstract Unmanned Surface Vehicles (USVs) represent an advanced technology with a wide range of applications in maritime contexts, and they offer a promising alternative to manned systems, particularly for the provision of services such as riverbed mapping. Furthermore, the use of USVs in combination with other robotic systems, such as flying drones, remotely operated underwater vehicles (ROVs) and autonomous underwater vehicles (AUVs), opens up innovative ways to inspect and monitor maritime infrastructure. However, the use of these systems in dynamic environments, such as ports or shipping lanes, requires a high degree of adaptability and precision in navigation to manoeuvre safely between other traffic participants and obstacles to prevent collisions. To address this problem, USVs require sophisticated perception systems for the precise detection and classification of nearby objects. Leveraging Light Detection and Ranging (LiDAR) technology, which is renowned for its efficacy in obstacle avoidance in robotics, this paper outlines the adaptation of a LiDAR sensor for USVs. The proposed pipeline enables the detection of other moving vessels and the accurate determination of their positions and trajectories up to 150 m from the USV. This paper introduces an obstacle detection system and validates it within a port setting. A methodical approach to LiDAR data preprocessing, clustering, and point cloud extraction will be outlined. Furthermore, it explores the application of an Unscented Kalman Filter (UKF) for the projection of motion paths of identified entities. This advanced form of data analysis provides the ability to predict the future position and path of potential obstacles, optimize decision-making for autonomous navigation algorithms and significantly improve the safety of USV operations. The pipeline is tested experimentally in sea trials by enacting five different scenarios that USV may encounter in a port setting. The results of the pipeline’s tracking capabilities are compared to the ground truth data collected by the tracked vessel and plotted to visualize the error.

A Robust SVD-UKF Algorithm and Its Application in Integrated Navigation Systems

To improve the positioning accuracy in Inertial Navigation System/Global Navigation Satellite System (INS/GNSS) integrated navigation and address the issue of measurement information anomalies, an integrated navigation algorithm based on an improved Huber-M estimation with Singular Value Decomposition Unscented Kalman Filter (SVD-UKF) is proposed. During the iterative update process of the prior information matrix in the UKF filtering, the Singular Value Decomposition (SVD) is introduced. This enhancement optimizes the prior information matrix, thereby enhancing numerical stability. The tail function of the Huber-M estimation is replaced with an exponential square loss function to improve the computational accuracy of the Huber-M estimation. The improved Huber-M estimation is then incorporated into the SVD-UKF framework. This approach reconstructs the UKF prior information and measurement information. The experimental results indicate that, compared to the traditional UKF and the Sage-Husa adaptive SVD-UKF algorithm, the improved algorithm enhances velocity accuracy by 68.7% and 31.2%, respectively, and improves position accuracy by 73.5% and 38.6%, respectively. The positioning accuracy and robustness of the INS/GNSS integrated navigation system were significantly improved, particularly under conditions with abnormal measurement information. The system demonstrated enhanced stability and resistance to interference in these scenarios.

Investigation of Enhanced Inertial Navigation Algorithms by Functional Iteration

Investigation of Enhanced Inertial Navigation Algorithms by Functional Iteration

A collaborative navigation algorithm for UAV Ad Hoc network based on improved sequence quadratic programming and unscented Kalman filtering in GNSS denied area

In global navigation satellite system (GNSS) denied area, collaborative positioning precision is important for unmanned aerial vehicle (UAV) to perform collaborative tasks in Ad Hoc network. Continuous optimization of algorithm complexity and parameter setting has long been a focal point in the field of collaborative positioning research. An algorithm of UAVs collaborative positioning based on improved sequential quadratic programming (SQP) and unscented kalman filter (UKF) is proposed. By optimizing the parameter constraints of SQP, parameters are controlled within certain conditions. The convergence speed of SQP is improved, and more accurate filtering parameters are obtained. The improved SQP and UKF are combined to optimize the location data of UAVs, which improves the precision of collaborative positioning. The simulation results show that the positioning precision can be greatly enhanced by approximately 25% when using the proposed algorithm, as compared to the traditional algorithm. The influence of the collaborative UAV number also is simulated. The positioning performance improve slowly when more than five UAVs are used for collaborative positioning. Therefore, the positioning performance cannot be improved only by increasing the number of UAVs, but also by improving the performance of collaborative positioning algorithm.

An Efficient Reinforcement Learning-Based Cooperative Navigation Algorithm for Multiple UAVs in Complex Environments

An Efficient Reinforcement Learning-Based Cooperative Navigation Algorithm for Multiple UAVs in Complex Environments

Global integrated navigation position correction algorithm and virtual polar region technology based on normal vector

To achieve the inherent uniformity of all-earth navigation for autonomous underwater vehicles (AUV), a global integrated navigation position correction algorithm based on the normal vector (n-vector) is proposed. First, a four-element vector comprising the non-singular n-vector and height represents the carrier’s position in the Earth-centered Earth-fixed (ECEF) frame. The integrated navigation systems are designed with the strapdown inertial navigation system (SINS), Doppler velocity log (DVL), and other equipment. Secondly, the reverse navigation algorithm in the ECEF mechanization is derived, and the results of forward and reverse navigation are fused to correct the AUV’s underwater position. Additionally, a virtual polar region technology based on the ECEF attitude, velocity, and height invariant method (E-AVHIM) is proposed to convert the actual test data obtained at low and middle latitudes into high latitudes for more convincing polar region algorithm verification. Simulations and lake trial demonstrated the excellence and efficiency of the proposed algorithm.

Development and research of an autonomous mobile platform with reduced computing power requirements

Today, the market is saturated with a variety of autonomous robotic devices that offer a variety of solutions to opti-mize workflows in various industries. One of the leading areas of their application is the automation of warehouse operations, where store robots move and optimize warehouse processes, reducing labor costs and speeding up task completion. These technologies reveal some limitations and shortcomings. For example, categories of robots such as transport carts, forklifts, and automated towing vehicles are limited in their functionality, often resulting in the need to use multiple types of devices for different tasks. This leads to equipment redundancy and complicates integration into existing warehouse systems. Another significant aspect is the need to improve the routing and nav-igation algorithms for these devices. Modern autonomous robot systems often face route optimization challenges, especially in dynamic and complex warehouse environments. This can lead to inefficiencies and increased time delays [1]. The goal of this work is to develop an autonomous mobile platform that would solve possible problems with navigation, have well-developed routing algorithms combined with low cost for affordable use in small busi-nesses. The research methods involve conducting various experiments on a real mobile platform to collect data and evaluate performance, including measuring the speed, accuracy, and power consumption of transportation tasks. Development and optimization of new algorithms for managing a mobile platform, planning routes, analyz-ing signals from sensors, processing images and video from a camera. The result of the work is that the possibility of compatibility of the on-board computer (single board computer) with the flight controller for movement on the ground surface has been investigated. On this basis, a mobile platform was created, which is presented in this arti-cle. This configuration is suitable for moving the platform either autonomously or using a control panel. The role of the technical vision system in providing navigation has been studied. The results of the work highlight innovation and the use of model functionality to create effective autonomous land navigation systems, including coordinates. The mobile platform can be used for transporting goods in warehouses, for working in extreme situations, for environmental monitoring or for educational purposes.

GNSS/INS integrated navigation algorithm framework based on cascade vector tracking algorithm for USV

The safety of Unmanned Surface Vehicle during the autonomous phase of navigation relies heavily on the onboard navigation equipment. However, in the face of changing and diverse navigation environments, global satellite navigation systems utilizing radio communication often face signal occlusions. This significantly reduces the positioning accuracy of navigation systems. To ensure the navigation accuracy of vehicles in various harsh environments, a Global Navigation Satellite Systems and Inertial Navigation System (GNSS/INS) integrated navigation system structure based on cascaded vector-tracking loop is proposed in this paper. The integrated navigation scheme not only improved the positioning accuracy of the navigation system but also effectively improved the robustness of the system. Compared with the traditional scalar-tracking loop and vector-tracking loop methods, it exhibits better performance. The experimental results show that the proposed method can reduce the horizontal position positioning error by 73.7% compared with the traditional vector-tracking loop method in the case of signal occlusion. Simultaneously, it can continuously output reliable and high-precision positioning information in the case of serious signal occlusion. The integrated navigation scheme proposed in this paper can be used as a research direction for the development of Unmanned Surface Vehicle navigation applications and provides solutions for the development of related navigation systems.

UAV Autonomous Navigation Based on Deep Reinforcement Learning in Highly Dynamic and High-Density Environments

Autonomous navigation of Unmanned Aerial Vehicles (UAVs) based on deep reinforcement learning (DRL) has made great progress. However, most studies assume relatively simple task scenarios and do not consider the impact of complex task scenarios on UAV flight performance. This paper proposes a DRL-based autonomous navigation algorithm for UAVs, which enables autonomous path planning for UAVs in high-density and highly dynamic environments. This algorithm proposes a state space representation method that contains position information and angle information by analyzing the impact of UAV position changes and angle changes on navigation performance in complex environments. In addition, a dynamic reward function is constructed based on a non-sparse reward function to balance the agent’s conservative behavior and exploratory behavior during the model training process. The results of multiple comparative experiments show that the proposed algorithm not only has the best autonomous navigation performance but also has the optimal flight efficiency in complex environments.

Energy-saving path planning navigation for solar-powered vehicles considering shadows

Globally, the adverse climate effects caused by greenhouse gas emissions are becoming increasingly apparent, and solutions to increase the use of eco-friendly transportation methods are urgently needed. Introducing solar-powered vehicles (SPVs), which are cars integrated with solar panels capable of generating power, presents a promising solution to reduce urban carbon footprints. However, the low adoption rate of SPVs implies that the benefits—such as environmental friendliness and ability to charge while driving—need to be more palpably experienced by consumers. To address this aspect, in this study, we aimed to develop a navigation system algorithm that guides users along routes that optimize energy consumption and solar energy production from the starting point to the destination. This was done with the objective of providing more tangible benefits from using SPVs. The study focused on the high-traffic urban center of Seoul, where determining solar power availability for a moving SPV is challenging, given the presence of shadows cast by roadside features such as buildings and trees. To achieve this, panoramic images from Google Street View were collected at 10 m intervals from all roads within the research area. From these images, sky and non-sky elements were separated. Subsequently, a hemispherical map was constructed and superimposed with the sun's path. The presence of shadows was determined by assessing whether the sun's path was obstructed by non-sky elements; if the path was unimpeded in the sky, no shadow was recorded. The shadow data obtained at each spot were efficiently stored in a database for quick retrieval and application based on specific locations and departure times. Using this shadow information, the navigation algorithm calculates power generation along a given route and considers the energy consumption of the SPV. Analysis led to the identification of an energy-saving route, which enabled the achievement of energy conservation and CO2 reduction benefits. Furthermore, a comprehensive sensitivity analysis was conducted to examine the impact of four critical parameters—module efficiency, solar panel area, vehicle speed, and departure time—on route selection and net energy consumption. The energy-saving path planning algorithm enhances the economic feasibility of solar charging for SPVs during travel; thus, this study can contribute significantly to the widespread adoption of SPVs, which play a definitive role in reducing transportation's carbon footprint.

Autonomous Vehicles Traversability Mapping Fusing Semantic–Geometric in Off-Road Navigation

This paper proposes an evaluating and mapping methodology of terrain traversability for off-road navigation of autonomous vehicles in unstructured environments. Terrain features are extracted from RGB images and 3D point clouds to create a traversal cost map. The cost map is then employed to plan safe trajectories. Bayesian generalized kernel inference is employed to assess unknown grid attributes due to the sparse raw point cloud data. A Kalman filter also creates density local elevation maps in real time by fusing multiframe information. Consequently, the terrain semantic mapping procedure considers the uncertainty of semantic segmentation and the impact of sensor noise. A Bayesian filter is used to update the surface semantic information in a probabilistic manner. Ultimately, the elevation map is utilized to extract geometric characteristics, which are then integrated with the probabilistic semantic map. This combined map is then used in conjunction with the extended motion primitive planner to plan the most effective trajectory. The experimental results demonstrate that the autonomous vehicles obtain a success rate enhancement ranging from 4.4% to 13.6% and a decrease in trajectory roughness ranging from 5.1% to 35.8% when compared with the most developed outdoor navigation algorithms. Additionally, the autonomous vehicles maintain a terrain surface selection accuracy of over 85% during the navigation process.