Autonomous Navigation Research Articles

The innovative vector of technology–based development of shipping companies is autonomous navigation

The article is devoted to the current state of water transport, problems and prospects of its development. Special attention is paid to the innovative vector of development of shipping companies on the basis of technologies - autonomous navigation. The development of the shipping industry on the basis of autonomous navigation opens significant opportunities in the sphere of safety improvement, increase of profit by reducing the costs of maintenance of ship crews. Examples of implementation and use of remote control of a vessel using autonomous navigation means along a socially and economically significant route are given. The article studies the legal acts that came into force in 2024, fixing the legal basis for the creation of autonomous navigation, which gives the opportunity to actively develop this promising direction. It will allow water transport to be competitive, and thus one of the key sectors of the Russian economy to become a pillar for achieving its growth. Based on the study of the materials of the Russian Federation SP in the field of inland water transport development, the factors that will contribute to the efficiency of the implementation of the initiatives of socio-economic development of the Russian Federation until 2030 are proposed.

Development of autonomous navigation system based on neural network and visual servoing for row-crop tracking in vegetable greenhouses

Accurate navigation line localization strategy and robust path tracking control scheme are two key techniques for advancing precision agriculture and enhancing the sustainability of smart farms. In this paper, a superior and cost-effective autonomous navigation system for a visual servoing-based agricultural vehicle in the greenhouse scenario with a distinct layout of two crop rows in each ridge is presented. First, based on image segmentation techniques, a neural network model named DGLNet integrating recognition of crop rows and prediction of the effective area of the navigation line is designed. The linear equation of the navigation line we required is obtained through post-processing operations of linear fitting completed in the effective area. According to experimental results, directly teaching the neural network to learn navigation line localization features utilizes the semantic and spatial information in the feature map to establish a stronger relationship between crop rows and the navigation line, which greatly improves the generalization of the navigation line localization in the case of large-angle yaw scenarios without additional training datasets. In addition, the performance of the network is significantly enhanced by adding an attention mechanism in the backbone based on U-Net. Subsequently, a dataset of cabbage vegetable images covering a wide range of complexities in the greenhouse scenario is created, and is available to support future academic research now. Further, a path tracking control scheme based on point-feature and line-feature is proposed, which can control the agricultural vehicle using the information from camera images without the need to perform explicit localization or maintain a global map. Finally, extensive field experiments have been carried out to show that this autonomous navigation system can preserve the stability of the vehicle and ensure timely convergence of deviations in different complex scenarios, which indicates that this control scheme is reliable and robust. Meanwhile, benefit from the efficiency of this recognition algorithm and the unnecessity of the complete representation of the path in the control scheme, the system has high real-time performance in every scenario.

Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation

AbstractLow‐light object detection is needed for ensuring security, enabling surveillance, and enhancing safety in diverse applications, including autonomous vehicles, surveillance systems, and search and rescue operations. A comprehensive study on low‐light object detection is presented using state‐of‐the‐art you only look once (YOLO) models, including YOLOv3, YOLOv5, YOLOv6, and YOLOv8, aiming to enhance detection performance under challenging low‐light conditions. The ExDark dataset is a dataset that consists of adequate low‐light images, modified to simulate realistic low‐light scenarios, and employed for evaluation. The deep learning algorithm optimises YOLO's architecture for low‐light detection by adapting the network structure and training strategies while preserving the algorithm's integrity. The experimental results show that YOLOv8 consistently outperforms baseline models, achieving significant improvements in accuracy and robustness in low‐light scenarios. The deep learning algorithm that acquired the best score, YOLOv8s, had a mean average precision score of 0.5513. This work contributes to the field of low‐light object detection, offering promising solutions for real‐world applications like nighttime surveillance and autonomous navigation in low‐light conditions, addressing the growing demand for advanced low‐light object detection.

Advancements in UAV Path Planning: A Deep Reinforcement Learning Approach with Soft Actor-Critic for Enhanced Navigation

This paper tackles the intricate challenge of autonomous navigation for Unmanned Aerial Vehicles (UAVs) through dynamically changing environments. We focus on a sophisticated Deep Reinforcement Learning (DRL) approach using the Soft Actor-Critic (SAC) algorithm, optimized for UAV path planning within a continuous action space. This methodology leverages environmental image data to enhance the precision of flight maneuvers and effective obstacle avoidance. Our approach, validated through extensive simulations in Gazebo and field tests, demonstrates the algorithm’s efficacy in enabling UAVs to adeptly navigate obstacles using depth maps. The study further explores the robustness of the SAC algorithm by comparing it with traditional DRL methods, emphasizing its superior performance in real-world applications. This research contributes significantly to advancing UAV technology, particularly in autonomous motion planning, by integrating cutting-edge machine learning techniques. The video link is: https://www.youtube.com/watch?v=Nd_aMzejNXY .

Development of a Robotic Platform with Autonomous Navigation System for Agriculture

The development of autonomous agricultural robots using a global navigation satellite system aided by real-time kinematics and an inertial measurement unit for position and orientation determination must address the accuracy, reliability, and cost of these components. This study aims to develop and evaluate a robotic platform with autonomous navigation using low-cost components. A navigation algorithm was developed based on the kinematics of a differential vehicle, combined with a proportional and integral steering controller that followed a point-to-point route until the desired route was completed. Two route mapping methods were tested. The performance of the platform control algorithm was evaluated by following a predefined route and calculating metrics such as the maximum cross-track error, mean absolute error, standard deviation of the error, and root mean squared error. The strategy of planning routes with closer waypoints reduces cross-track errors. The results showed that when adopting waypoints every 3 m, better performance was obtained compared to waypoints only at the vertices, with maximum cross-track error being 44.4% lower, MAE 64.1% lower, SD 39.4% lower, and RMSE 52.5% lower. This study demonstrates the feasibility of developing autonomous agricultural robots with low-cost components and highlights the importance of careful route planning to optimize navigation accuracy.

Femtosecond pulse amplification on a chip

Femtosecond laser pulses enable the synthesis of light across the electromagnetic spectrum and provide access to ultrafast phenomena in physics, biology, and chemistry. Chip-integration of femtosecond technology could revolutionize applications such as point-of-care diagnostics, bio-medical imaging, portable chemical sensing, or autonomous navigation. However, current chip-integrated pulse sources lack the required peak power, and on-chip amplification of femtosecond pulses has been an unresolved challenge. Here, addressing this challenge, we report >50-fold amplification of 1 GHz-repetition-rate chirped femtosecond pulses in a CMOS-compatible photonic chip to 800 W peak power with 116 fs pulse duration. This power level is 2–3 orders of magnitude higher compared to those in previously demonstrated on-chip pulse sources and can provide the power needed to address key applications. To achieve this, detrimental nonlinear effects are mitigated through all-normal dispersion, large mode-area and rare-earth-doped gain waveguides. These results offer a pathway to chip-integrated femtosecond technology with peak power levels characteristic of table-top sources.

New color channel driven physical lighting model for low-light image enhancement

Outdoor imaging systems, affected by low-light conditions, generally produce low-quality images with poor visibility. Low-quality images can directly influence high-level tasks such as surveillance and autonomous navigation systems. Enhancing the images captured under inadequate lighting conditions aims to generate higher visual quality in these images. However, current low-light enhancement methods may result in color unnaturalness, information loss, and strange artifacts. We propose a new color channel-driven physical lighting model (NCC-PLM) to respond to these issues to improve image quality. More concretely, we first apply a gamma correction to the input image according to its darkness degree, which is determined by its average intensity value. Then, we introduce a new color channel prior to estimate the environmental light (EL) and light scattering attenuation rate (LSAR). Finally, the enhanced image is obtained through the estimations and physical lighting model. Experimental results on various datasets demonstrate the proposed method's effectiveness and superiority over the compared methods both visually and qualitatively. Specifically, we enhance the visual quality of low-light images by revealing intricate details and maintaining color consistency, leading to a natural appearance.

Self Balancing Robot with Autonomous Navigation and Obstacle Detection

Self Balancing Robot with Autonomous Navigation and Obstacle Detection

Global Localization using OpenStreetMap and Elevation Offsets

Localization is a critical component in autonomous vehicle navigation stacks. While GNSS-only localization cannot be fully reliable and available all the time, localization based on 3D high-definition (HD) maps have to be robust to world changes, which is still a challenging issue. Added to that, in general, HD maps are expensive and difficult to construct and maintain.In this paper, we propose a particle filter-based 2D global pose estimation method that can use the crowdsourced OpenStreetMap (OSM) API, a digital surface map, or both. The main contributions of the proposed approach are: that it is lightweight, does not require the vehicle to map the environment, does not require a GPU (can be used with low-power computing resources), is agnostic to the odometry source, and achieved relatively low position and orientation errors for this localization modality using the KITTI dataset sequences. The proposed method's implementation is open source and is available with the experimental results on our GitHub page.

A Survey of Image Enhancement and Dehazing Algorithms to Improving Autonomous Navigation in Fog and Dust.

Video captured during sand-dust weather conditions indicates significant degradation, diminished contrast, and pronounced color distortion. The reason behind this phenomenon is the impact of sand-dust particles, which result in the dispersion and assimilating of light. Consequently, resultant image seems blurred and lacks contrast. Additionally, the alteration in color is attributed to the swift reduction of blue light. Adverse weather circumstances, such as fog, sand, and dust storms, cause problems with vision for deploying self-driving automobiles. To guarantee secure and seamless operations during frequent adverse weather conditions, video enhancement plays a vital role in facilitating vehicular mobility and navigational in both road and air transportation. To improve the safety and efficiency of operation, it is imperative to employ video dehazing techniques, particularly in adverse weather conditions. The purpose of our overview is to offer interested researchers a thorough and methodical examination of image enhancement approaches, serving as an important point of reference for their work. The text explored different image enhancement methods, along with the challenges, constraints, advantages, and drawbacks associated with using these techniques throughout the past five years. Specifically, it focused on three aspects: supervised algorithms, unsupervised algorithms, and quality evaluation.

Learning Autonomous Navigation in Unmapped and Unknown Environments.

Autonomous decision-making is a hallmark of intelligent mobile robots and an essential element of autonomous navigation. The challenge is to enable mobile robots to complete autonomous navigation tasks in environments with mapless or low-precision maps, relying solely on low-precision sensors. To address this, we have proposed an innovative autonomous navigation algorithm called PEEMEF-DARC. This algorithm consists of three parts: Double Actors Regularized Critics (DARC), a priority-based excellence experience data collection mechanism, and a multi-source experience fusion strategy mechanism. The algorithm is capable of performing autonomous navigation tasks in unmapped and unknown environments without maps or prior knowledge. This algorithm enables autonomous navigation in unmapped and unknown environments without the need for maps or prior knowledge. Our enhanced algorithm improves the agent's exploration capabilities and utilizes regularization to mitigate the overestimation of state-action values. Additionally, the priority-based excellence experience data collection module and the multi-source experience fusion strategy module significantly reduce training time. Experimental results demonstrate that the proposed method excels in navigating the unmapped and unknown, achieving effective navigation without relying on maps or precise localization.

Multi-Strategy Improved Harris Hawk Optimization Algorithm and Its Application in Path Planning.

Path planning is a key problem in the autonomous navigation of mobile robots and a research hotspot in the field of robotics. Harris Hawk Optimization (HHO) faces challenges such as low solution accuracy and a slow convergence speed, and it easy falls into local optimization in path planning applications. For this reason, this paper proposes a Multi-strategy Improved Harris Hawk Optimization (MIHHO) algorithm. First, the double adaptive weight strategy is used to enhance the search capability of the algorithm to significantly improve the convergence accuracy and speed of path planning; second, the Dimension Learning-based Hunting (DLH) search strategy is introduced to effectively balance exploration and exploitation while maintaining the diversity of the population; and then, Position update strategy based on Dung Beetle Optimizer algorithm is proposed to reduce the algorithm's possibility of falling into local optimal solutions during path planning. The experimental results of the comparison of the test functions show that the MIHHO algorithm is ranked first in terms of performance, with significant improvements in optimization seeking ability, convergence speed, and stability. Finally, MIHHO is applied to robot path planning, and the test results show that in four environments with different complexities and scales, the average path lengths of MIHHO are improved by 1.99%, 14.45%, 4.52%, and 9.19% compared to HHO, respectively. These results indicate that MIHHO has significant performance advantages in path planning tasks and helps to improve the path planning efficiency and accuracy of mobile robots.

A hybrid RVO-MPPI approach for efficient collision avoidance for multiple autonomous underwater vehicles

Collision-avoidance path planning for Autonomous Underwater Vehicles (AUVs) in complex underwater environments presents a significant challenge, particularly considering the maneuverability limitations of fin-rudder-controlled AUVs. This study proposes a novel navigation approach that combines the strengths of Reciprocal Velocity Obstacle (RVO) principles and Model Predictive Path Integral (MPPI) control to enhance autonomous obstacle avoidance for multiple AUVs. The key innovation lies in leveraging RVO-based obstacle avoidance velocities to enhance both action sampling and cost function optimization in MPPI framework. Specifically, a neural network trained through supervised learning is utilized to convert the RVO-provided avoidance velocities into desired actions for MPPI. Additionally, these velocities are incorporated into the MPPI cost function, thereby enhancing the optimization process and facilitating convergence towards optimal, collision-free navigation solutions. Simulation experiments validated the method's capability to provide effective obstacle avoidance behavior across various complex scenarios. Results indicate that this approach successfully integrates MPPI's predictive capabilities with RVO's velocity avoidance logic, enabling AUVs to navigate efficiently through complex underwater environments while ensuring mission safety and effectiveness. This approach offers a promising new solution for autonomous navigation of AUVs, with potential applications in ocean exploration, underwater search and rescue, and other maritime operations. Future research will explore the performance of this approach in real-world underwater environments and consider the impact of additional dynamic factors.

Stable solution to the problem of autonomous navigation of moving objects on analytical trajectory intervals using inertial measurement results

Stable solution to the problem of autonomous navigation of moving objects on analytical trajectory intervals using inertial measurement results

Effective Map Merging for Long-Term Autonomous Navigation

Effective Map Merging for Long-Term Autonomous Navigation

Method of Motion Planning for Digital Twin Navigation and Cutting of Shearer.

To further enhance the intelligence level of coal mining faces and achieve the autonomous derivation, learning, and optimization of shearer navigation cutting, this paper proposes the methods of shearer digital twin navigation cutting motion planning based on the concept of shearer autonomous navigation cutting technology and intelligent coal mining face digital twins. This study includes the digital twin theory and the construction method of the shearer digital twin navigation cutting motion planning system based on this theory. Based on the digital twin theory, a shearer digital twin navigation cutting motion planning system was constructed. This system supports the service functions of the shearer cutting digital twin, dynamic navigation map digital twin, reinforcement learning environment construction, and motion planning through the physical perception layer, comprehensive data layer, and digital-model fusion analysis layer. Finally, by comparing the effects of the DQN-NAF and DDPG deep reinforcement learning algorithms in the shearer motion planning task within the constructed digital twin environment, the results show that the DQN-NAF algorithm demonstrates better performance and stability in solving the shearer digital twin motion planning task.

Optimized TD3 algorithm for robust autonomous navigation in crowded and dynamic human-interaction environments

Mobile robots have been incorporated into human society to help perform tasks that can affect or endanger health and life. One of the challenges is in the mobile robot-human interaction, as unexpected movements made by people can cause collisions with the robots when accomplishing a task. In this paper an optimized algorithm based on TD3 (Twin Deep Deterministic Policy gradient) used in Deep Reinforcement Learning is proposed, which allows the robot to take its own actions based on the observations it makes, without defining any trajectory beforehand. Using this algorithm that uses the actor-critical policy that helps to determine the linear and angular velocity of the robot, which allows the robot to move in unknown dynamic environments avoiding collisions. It is proposed to use a buffer that stores the values sent by the neural network and analyses them together with the odometry parameters of the robot to send the best decision to the robot to achieve a collision-free path and meet the objectives. The purpose of this algorithm is to meet as many consecutive targets as possible, i.e. the robot never returns to its initial position, it is assigned new targets regardless of the position it has reached. Finally, the results obtained by training the algorithm correspond nearly 0 for the actor and critic training, with a training of 12,000 episodes, and with an evaluation results 92 % of effectivity of our algorithm, based on 772 steps performed by the rob ten in a time of 11 s.

Multi-robot collision avoidance method in sweet potato fields.

Currently, precise spraying of sweet potatoes is mainly accomplished through semi-mechanized or single spraying robots, which results in low operating efficiency. Moreover, it is time-consuming and labor-intensive, and the pests and diseases cannot be eliminated in time. Based on multi robot navigation technology, multiple robots can work simultaneously, improving work efficiency. One of the main challenges faced by multi robot navigation technology is to develop a safe and robust collision avoidance strategy, so that each robot can safely and efficiently navigate from its starting position to the expected target. In this article, we propose a low-cost multi-robot collision avoidance method to solve the problem that multiple robots are prone to collision when working in field at the same time. This method has achieved good results in simulation. In particular, our collision avoidance method predicts the possibility of collision based on the robot's position and environmental information, and changes the robot's path in advance, instead of waiting for the robot to make a collision avoidance decision when it is closer. Finally, we demonstrate that a multi-robot collision avoidance approach provides an excellent solution for safe and effective autonomous navigation of a single robot working in complex sweet potato fields. Our collision avoidance method allows the robot to move forward effectively in the field without getting stuck. More importantly, this method does not require expensive hardware and computing power, nor does it require tedious parameter tuning.

Optimizing Autonomous UAV Navigation with D* Algorithm for Sustainable Development

Autonomous navigation for Unmanned Aerial Vehicles (UAVs) has emerged as a critical enabler in various industries, from agriculture, delivery services, and surveillance to search and rescue operations. However, navigating UAVs in dynamic and unknown environments remains a formidable challenge. This paper explores the application of the D* algorithm, a prominent path-planning method rooted in artificial intelligence and widely used in robotics, alongside comparisons with other algorithms, such as A* and RRT*, to augment autonomous navigation capabilities in UAVs’ implication for sustainability development. The core problem addressed herein revolves around enhancing UAV navigation efficiency, safety, and adaptability in dynamic environments. The research methodology involves the integration of the D* algorithm into the UAV navigation system, enabling real-time adjustments and path planning that account for dynamic obstacles and evolving terrain conditions. The experimentation phase unfolds in simulated environments designed to mimic real-world scenarios and challenges. Comprehensive data collection, rigorous analysis, and performance evaluations paint a vivid picture of the D* algorithm’s efficacy in comparison to other navigation methods, such as A* and RRT*. Key findings indicate that the D* algorithm offers a compelling solution, providing UAVs with efficient, safe, and adaptable navigation capabilities. The results demonstrate a path planning efficiency improvement of 92%, a 5% reduction in collision rates, and an increase in safety margins by 2.3 m. This article addresses certain challenges and contributes by demonstrating the practical effectiveness of the D* algorithm, alongside comparisons with A* and RRT*, in enhancing autonomous UAV navigation and advancing aerial systems. Specifically, this study provides insights into the strengths and limitations of each algorithm, offering valuable guidance for researchers and practitioners in selecting the most suitable path-planning approach for their UAV applications. The implications of this research extend far and wide, with potential applications in industries such as agriculture, surveillance, disaster response, and more for sustainability.

Global path planning for inland vessels based on fast marching algorithm

Ship path planning is essential for enhancing navigation safety, shipping efficiency, cost savings and autonomy. This paper presents a path planning algorithm specifically designed for inland vessels, exemplified on the Western Scheldt waterway area from Hansweert to Bath in the Netherlands (known as the area of Schaar van Valkenisse). The algorithm utilizes the fast marching (FM) method to generate safe and cost-efficient paths for both autonomous and conventional navigation, considering factors such as water depth, distance to waterway borders, preferential navigation zones (e.g. starboard side and parallel routes), ship dimensions, and manoeuvring characteristics.The fast marching algorithm uses starting points and a velocity grid, generated based on the aforementioned factors, to produce an arrival time map. The velocity here represents preferences for deeper water, and wider and starboard navigation zones. Subsequently, a gradient descent algorithm is applied to determine the fastest route from the destination to the starting point on the arrival time map. To ensure the route is navigable, the optimal path is updated to a Dubins path that satisfies the ships’ dynamic constraints by using a so-called Dubins model filter.Case studies with various navigation scenarios demonstrate that the path planning tool can provide expected results with tunable parameters allowing for customized preferences. This work can further assist in predicting paths for a traffic study, designing fairways, aids to navigation and can possibly serve as an operational tool to assess the accessibility of a (alternative) fairway.