Development Of Autonomous Navigation System Research Articles

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.

Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data

The development of autonomous navigation systems requires digital building models at the LoD3 level. Buildings with atypically shaped features, such as turrets, domes, and chimneys, should be selected as landmark objects in these systems. The aim of this study was to develop a method that automatically transforms segmented LiDAR (Light Detection And Ranging) point cloud to create such landmark building models. A detailed solution was developed for selected buildings that are solids of revolution. The algorithm relies on new methods for determining building axes and cross-sections. To handle the gaps in vertical cross-sections due to the absence of continuous measurement data, a new strategy for filling these gaps was proposed based on their automatic interpretation. In addition, potential points associated with building ornaments were used to improve the model. The results were presented in different stages of the modeling process in graphic models and in a matrix recording. Our work demonstrates that complicated buildings can be represented with a light and regular data structure. Further investigations are needed to estimate the constructed building model with vectorial models.

ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation

Annotation is a crucial first step in the semantic segmentation of urban images that facilitates the development of autonomous navigation systems. However, annotating complex urban images is time-consuming and challenging. It requires significant human effort making it expensive and error-prone. To reduce human effort during annotation, multiple images need to be annotated in a short time-span. In this paper, we introduce ScribbleNet, an interactive image segmentation algorithm to address this issue. Our approach provides users with a pre-segmented image that iteratively improves the segmentation using scribble as an annotation input. This method is based on conditional inference and exploits the learnt correlations in a deep neural network (DNN). ScribbleNet can: (1) work with urban city scenes captured in unseen environments, (2) annotate new classes not present in the training set, and (3) correct several labels at once. We compare this method with other interactive segmentation approaches on multiple datasets such as CityScapes, BDD, Mapillary Vistas, KITTI, and IDD. ScribbleNet reduces the annotation time of an image by up to 14.7 × over manual annotation and up to 5.4× over the current approaches. The algorithm is integrated into the publicly available LabelMe image annotation tool and will be released as an open-source software.

Real-Time Free Space Semantic Segmentation for Detection of Traversable Space for an Intelligent Wheelchair.

The last decades saw a great innovation in computer vision. Recently, the field has been fundamental in the development of autonomous navigation systems. Modern assistive technologies, like smart wheelchairs, could employ autonomous navigation to assist users during operation. A prerequisite for such systems is to recognise the navigable space in real-time. The current research features an off-the-shelf powered wheelchair customised into an intelligent robot, which perceives the environment using Point Cloud Semantic Segmentation (PCSS). The implemented algorithm is used to distinguish between two conditions, traversable and non-traversable space, in real-time, using the aforementioned conditions as the two labelled classes. The accuracy of traversable space detection resulted as 99.64% while the accuracy of non-traversable space detection was 91.79%. The performance of the suggested method was invariant to changes in wheelchair velocity indicating that the latency of the suggested algorithm is within the tolerable limits for real-time operation.

FAITH: Fast Iterative Half-Plane Focus of Expansion Estimation Using Optic Flow

Course estimation is a key component for the development of autonomous navigation systems for robots. While state-of-the-art methods widely use visual-based algorithms, it is worth noting that they all fail to deal with the complexity of the real world by being computationally greedy and sometimes too slow. They often require obstacles to be highly textured to improve the overall performance, particularly when the obstacle is located within the focus of expansion (FOE) where the optic flow (OF) is almost null. This study proposes the FAst ITerative Half-plane (FAITH) method to determine the course of a micro air vehicle (MAV). This is achieved by means of an event-based camera, along with a fast RANSAC-based algorithm that uses event-based OF to determine the FOE. The performance is validated by means of a benchmark on a simulated environment and then tested on a dataset collected for indoor obstacle avoidance. Our results show that the computational efficiency of our solution outperforms state-of-the-art methods while keeping a high level of accuracy. This has been further demonstrated onboard an MAV equipped with an event-based camera, showing that our event-based FOE estimation can be achieved online onboard tiny drones, thus opening the path towards fully neuromorphic solutions for autonomous obstacle avoidance and navigation onboard MAVs.

Collision avoidance path planning in multi-ship encounter situations

Collision avoidance path planning is still one of the essential problems in the design and application of an intelligent maritime navigation system. Its main obstacle is how to determine effective and cooperative collision avoidance maneuvers within a multi-ship encounter situation. By deconstructing a multi-ship encounter, this study adopted ship domain around target ships to assess the collision danger that own ship should avoid. Subsequently, the fitness function that has multiple dynamic obstacle constraints was designed in a two-dimensional map. Based on DE algorithm, a path-planning method was developed to compute collision-free and optimal navigation paths for ships. Simulation results show that the algorithm can generate a safe and suitable path from each perspective in a multi-ship encounter. The results also validate the practicality of the generated paths, consistency of the algorithm outputs and performance of the algorithm. It would be expected to provide a reference for collision avoidance decision making as well as contribute to the development of autonomous navigation systems.

The 2^k Neighborhoods for Grid Path Planning

Grid path planning is an important problem in AI. Its understanding has been key for the development of autonomous navigation systems. An interesting and rather surprising fact about the vast literature on this problem is that only a few neighborhoods have been used when evaluating these algorithms. Indeed, only the 4- and 8-neighborhoods are usually considered, and rarely the 16-neighborhood. This paper describes three contributions that enable the construction of effective grid path planners for extended 2k-neighborhoods; that is, neighborhoods that admit 2k neighbors per state, where k is a parameter. First, we provide a simple recursive definition of the 2k-neighborhood in terms of the 2k-1-neighborhood. Second, we derive distance functions, for any k ≥ 2, which allow us to propose admissible heuristics that are perfect for obstacle-free grids, which generalize the well-known Manhattan and Octile distances. Third, we define the notion of canonical path for the 2k-neighborhood; this allows us to incorporate our neighborhoods into two versions of A*, namely Canonical A* and Jump Point Search (JPS), whose performance, we show, scales well when increasing k. Our empirical evaluation shows that, when increasing k, the cost of the solution found improves substantially. Used with the 2k-neighborhood, Canonical A* and JPS, in many configurations, are also superior to the any-angle path planner Theta* both in terms of solution quality and runtime. Our planner is competitive with one implementation of the any-angle path planner, ANYA in some configurations. Our main practical conclusion is that standard, well-understood grid path planning technology may provide an effective approach to any-angle grid path planning.

Development of autonomous navigation system for rice transplanter

Rice transplanting requires the operator to manipulate the rice transplanter in straight trajectories. Various markers are proposed to help experienced drivers in keeping straightforward and parallel to the previous path, which are extremely boring in terms of large-scale fields. The objective of this research was to develop an autonomous navigation system that automatically guided a rice transplanter working along predetermined paths in the field. The rice transplanter used in this research was commercially available and originally manually-operated. An automatic manipulating system was developed instead of manual functions including steering, stop, going forward and reverse. A sensor fusion algorithm was adopted to integrate measurements of the Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS) and Inertial Measurement Unit (IMU), and calculate the absolute moving direction under the UTM coordinate system. A headland turning control method was proposed to ensure a robust turning process considering that the rice transplanter featured a small turning radius and a relatively large slip rate at extreme steering angles. Experiments were designed and conducted to verify the performance of the newly developed autonomous navigation system. Results showed that both lateral and heading errors were less than 8 cm and 3 degrees, respectively, in terms of following straight paths. And headland turns were robustly executed according to the required pattern. Keywords: autonomous navigation, rice transplanter, sensor fusion, headland turning DOI: 10.25165/j.ijabe.20181106.3023 Citation: Yin X, Du J, Noguchi N, Yang T X, Jin C Q. Development of autonomous navigation system for rice transplanter. Int J Agric & Biol Eng, 2018; 11(6): 89–94.

Development of Autonomous Navigation System Using 3D Map with Geometric and Semantic Information

This paper presents an autonomous navigation system. Our system is based on an accurate 3D map, which includes “geometric information” (e.g., curb, wall, street tree) and “semantic information” (e.g., sidewalk, roadway, crosswalk) extracted by environmental recognition. By using the semantic map, we can obtain the suitable area to keep away from undesired places. Furthermore, by comparing the map with real-time 3D geometric information from LIDAR, we obtain the robot position. To show the effectiveness of our system, we conduct a 3D semantic map construction experiment and driving test. The experiment results show that the proposed system enables accurate and highly reproducible localization and stable autonomous mobility.

해양사고의 원인분석과 저감대책

Marine accidents of fishing vessels occupied about 70.5% of the whole marine accidents in Korea from 1996 to 2015, this ratio was not much changed for a long time. A lot of efforts have been taken recently but marine accidents do not reduce. Therefore a fundamental counterplan to decrease accidents in fishing vessel is indispensable for reduction of whole marine accidents in Korea.BR Since the most frequent occurring accidents in fishing vessels were engine trouble and collision in statistics by KMST (1996∼2015), the study focused on them. The cause of engine trouble were poor inspection and maintenance of the mechanical system. The greatest portion of marine accidents was collision, and the biggest cause of the collision was poor watch-keeping. The better watch-keeping will be the best way to reduce the accident. For this reason, it may be necessary for the navigator to make strict precaution on the other vessels under way systematically and keep the regulation for preventing collisions, and for an engineer on watch to make a check the mechanical system periodically for reduction the engine trouble. Instead of penalty, incentive about safe navigation will be helpful for reduce accident as if automobile insurance would do. In order to prevent engine trouble, the fisheries federation establish the repair center. Futhermore the development of autonomous navigation system is necessary to reduce the marine accident.

Position Estimation Method Using Artificial Landmarks and Omnidirectional Vision

The development of autonomous navigation systems for agricultural vehicles is an important endeavor. We propose a position estimation method based on artificial landmarks and omnidirectional vision for agricultural vehicle navigation to augment GPS-based solutions. The method sets four red artificial landmarks as a rectangle in the corners of an operating area and estimates an absolute position relative to the landmark-based coordinate system on the ground. This article introduces an algorithm to extract the landmarks and estimate the directional angles of the landmarks using only one omnidirectional image. Camera location was estimated based on the directional angles of the landmarks. Experiments were conducted under natural sunlight in a 50 m 50 m square area to verify the method. Experimental results showed that the maximum and mean position errors were about 46.96 cm and 31.99 cm, respectively. Camera tilt experiments showed that the tilt angle had some effect on errors, but not significantly, and it was not necessary to compensate for the errors caused by camera tilt on uneven ground. In conclusion, this method is feasible to augment GPS-based solutions for agricultural vehicle navigation.