This paper mainly studies an autonomous path-planning and real-time path-tracking optimization method for snake robot. Snake robots can perform search and rescue, exploration, and other tasks in a variety of complex environments. Robots with visual sensors such as LiDAR can avoid obstacles in the environment through autonomous navigation to reach the target point. However, in an unstructured environment, the navigation of snake robot is easily affected by the external environment, causing the robot to deviate from the planned path. In order to solve the problem that snake robots are easily affected by environmental factors in unstructured environments, resulting in poor path-following ability, this paper uses the Los algorithm combined with steering control to plan the robot in real time and control the robot’s steering parameters in real time, ensuring that the robot can stably follow the planned path.

Autonomous navigation has been a long-standing research topic, and researchers have worked on many challenging problems in indoor and outdoor environments. One application area of navigation solutions is material handling in industrial environments. With Industry 4.0, the simple problem in traditional factories has evolved into the use of autonomous mobile robots within flexible production islands in a self-decision-making structure. Two main stages of such a navigation system are safe transportation of the vehicle from one point to another and reaching destinations at industrial standards. The main concern in the former is roughly determining the vehicle’s pose to follow the route, while the latter aims to reach the target with high accuracy and precision. Often, it may not be possible or require extra effort to satisfy requirements with a single localization method. Therefore, a multi-stage localization approach is proposed in this study. Particle filter-based large-scale localization approaches are utilized during the vehicle’s movement from one point to another, while scan-matching-based methods are used in the docking stage. The localization system enables the appropriate approach based on the vehicle’s status and task through a decision-making mechanism. The decision-making mechanism uses a similarity metric obtained through the correntropy criterion to decide when and how to switch from large-scale localization to precise localization. The feasibility and performance of the developed method are corroborated through field tests. These evaluations demonstrate that the proposed method accomplishes tasks with sub-centimeter and sub-degree accuracy and precision without affecting the operation of the navigation algorithms in real time.

The Autonomous Navigation System (ANS) constitutes a critical key enabling technology required for operating Maritime Autonomous Surface Ships (MASS). To assure the safety of MASS operations, the effective identification of potential objects and target ships interacting with the own MASS is quintessential. This study proposes a systematic method to identify the items interacting with the own MASS. This method is based on a similar approach previously employed for the encountering items’ identification in robotics, which is customised herein for the MASS needs. The developed method is applied to a short-sea shipping MASS. The environmental features, agents and objects related to her navigation are identified and ranked based on the frequency of encounter and the potential collision consequences. The results demonstrate the ability of the method to identify additional items in comparison to Automatic Identification System based data. The interactions with the small ships are considered as the most critical, due to their potential accidental consequences and their exhibited high frequency of encounter. This study results are employed to support the ANS design and testing of the investigated ship.

This paper proposes a novel autonomous navigation method for Mars-orbiting probes. Satellite-to-satellite tracking (SST) between two probes is generally deemed to involve autonomous measurements with no dependence on any external observation sites on the Earth. For the conventional two-body dynamic model, it is well known that the orbit states cannot be estimated by merely using such SST measurements. Considering the effects of third-body gravitation perturbation and the weak Mars tesseral harmonics perturbation, autonomous navigation with SST measurements alone becomes weakly observable and may be achieved by some nonlinear filtering techniques. Two significant improvements are made to mitigate the nonlinearity brought by the dynamic models. First, singularity-avoiding orbit elements are selected to represent the dynamic models in order to reduce the intensity of the nonlinearity which cannot be overcome by the traditional position–velocity state expression. Second, the unscented Kalman filter method is effectively utilised to avoid the linearised errors calculated by its extended Kalman filter counterpart which may exceed the tesseral harmonics perturbation. A constellation, consisting of one low-orbit probe and one high-orbit probe, is designed to realise the autonomous orbit determination of both participating Mars probes. A reliable navigation solution is successfully obtained by Monte Carlo simulation runs. It shows that the errors of the semimajor axes of the two Mars probes are less than 10 m and the position errors are less than 1 km.

A behavioral-based strategy for cooperative hunting using drones is proposed in this paper. In this decentralized scheme, each drone acts as an individual agent computing its guidance strategy toward the target based on the relative position of its neighbors without the use of direct communication. The algorithm is based on the deviated pure pursuit methodology, and the emerged behavior mimics a natural hunting formation. Simulations and real-time experiments with varying conditions were carried out to validate the effectiveness of the proposed hunting scheme. Videos of the system in action can be seen on: https://youtu.be/g2dODbd6ZLA.

Recognition of obstacle type based on visual sensors is important for navigation by unmanned surface vehicles (USV), including path planning, obstacle avoidance, and reactive control. Conventional detection techniques may fail to distinguish obstacles that are similar in visual appearance in a cluttered environment. This work proposes a novel obstacle type recognition approach that combines a dilated operator with the deep-level features map of ResNet50 for autonomous navigation. First, visual images are collected and annotated from various different scenarios for USV test navigation. Second, the deep learning model, based on a dilated convolutional neural network, is set and trained. Dilated convolution allows the whole network to learn deep features with increased receptive field and further improves the performance of obstacle type recognition. Third, a series of evaluation parameters are utilised to evaluate the obtained model, such as the mean average precision (mAP), missing rate and detection speed. Finally, some experiments are designed to verify the accuracy of the proposed approach using visual images in a cluttered environment. Experimental results demonstrate that the dilated convolutional neural network obtains better recognition performance than the other methods, with an mAP of 88%.

This article proposes the design and development of a novel custom-built, autonomous scaled multiwheeled vehicle that features an eight-wheel drive and eight-wheel steer system. In addition to the mechanical and electrical design, high-level path planning and low-level vehicle control algorithms are developed and implemented including a two-stage autonomous parking algorithm is developed. A modified position-based visual servoing algorithm is proposed and developed to achieve precise pose correction. The results show significant gains in accuracy and efficiency comparing with an open-source path planner. It is the aim of this work to expand the research of autonomous platforms taking the form of commercial and off-road vehicles using actuated steering and other mechanisms attributed to passenger vehicles. The outcome of this work is a unique autonomous research platform that features independently driven wheels, steering, autonomous navigation, and parking.

Economic and technological development has increased the amount, density and complexity of maritime traffic, which has resulted in new challenges. One challenge is conforming to the distinct evasion manoeuvres required by vessels entering into near-collision situations (NCSs). Existing rules are vague and do not precisely dictate which, when and how collision avoidance manoeuvres (CAMs) should be executed. The automatic identification system (AIS) is widely used for vessel monitoring and traffic control. This paper presents an efficient, scalable method for processing large-scale raw AIS data using the closest point of approach (CPA) framework. NCSs are identified to create a database of historical traffic data. Important features describing CAMs are defined, estimated and analysed. Applications on a high-quality real-world data set show promising results for a subset of the identified situations. Future applications may play a significant role in the maritime regulatory framework, navigation protocol compliance evaluation, risk assessment, automatic collision avoidance, and algorithm design and testing for autonomous vessels.

We present a robot navigation system based on Behavioral Finite State Social Machine. The paper makes a robot operate as a social tour guide that adapts its navigation based on the behavior of the visitors. The problem of a robot leading a human group with a limited field-of-view vision is relatively untouched in the literature. Uncertainties arise when the visitors are not visible, wherein the behavior of the robot is adapted as a social response. Artificial potential field is used for local planning, and a velocity manager sets the speed disproportional to time duration of missing visitors.

In this paper, a novel method for autonomous navigation for an extra-terrestrial body landing mission is proposed. Based on state-of-the-art crater detection and matching algorithms, a crater edge-based navigation method is formulated, in which solar illumination direction is adopted as a complementary optical cue to aid crater edge-based navigation when only one crater is available. To improve the pose estimation accuracy, a distributed Extended Kalman Filter (EKF) is developed to encapsulate the crater edge-based estimation approach. Finally, the effectiveness of proposed approach is validated by Monte Carlo simulations using a specifically designed planetary landing simulation toolbox.

A Laser Scanning aided Inertial Navigation System (LSINS) is able to provide highly accurate position and attitude information by aggregating laser scanning and inertial measurements under the assumption that the rigid transformation between sensors is known. However, a LSINS is inevitably subject to biased estimation and filtering divergence errors due to inconsistent state estimations between the inertial measurement unit and the laser scanner. To bridge this gap, this paper presents a novel integration algorithm for LSINS to reduce the inconsistences between different sensors. In this new integration algorithm, the Radial Basis Function Neural Networks (RBFNN) and Singular Value Decomposition Unscented Kalman Filter (SVDUKF) are used together to avoid inconsistent state estimations. Optimal error estimation in the LSINS integration process is achieved to reduce the biased estimation and filtering divergence errors through the error state and measurement error model built by the proposed method. Experimental tests were conducted to evaluate the navigation performance of the proposed method in Global Navigation Satellite System (GNSS)-denied environments. The navigation results demonstrate that the relationship between the laser scanner coordinates and the inertial sensor coordinates can be established to reduce sensor measurement inconsistencies, and LSINS position accuracy can be improved by 23·6% using the proposed integration method compared with the popular Extended Kalman Filter (EKF) algorithm.

A Q-learning approach is often used for navigation in static environments where state space is easy to define. In this paper, a new Q-learning approach is proposed for navigation in dynamic environments by imitating human reasoning. As a model-free method, a Q-learning method does not require the environmental model in advance. The state space and the reward function in the proposed approach are defined according to human perception and evaluation, respectively. Specifically, approximate regions instead of accurate measurements are used to define states. Moreover, due to the limitation of robot dynamics, actions for each state are calculated by introducing a dynamic window that takes robot dynamics into account. The conducted tests show that the obstacle avoidance rate of the proposed approach can reach 90.5% after training, and the robot can always operate below the dynamics limitation.

Safe and accurate navigation for autonomous trajectory tracking of quadrotors using monocular vision is addressed in this paper. A second order Sliding Mode (2-SM) control algorithm is used to track desired trajectories, providing robustness against model uncertainties and external perturbations. The time-scale separation of the translational and rotational dynamics allows to design position controllers by giving a desired reference in roll and pitch angles, which is suitable for practical validation in quad-rotors equipped with an internal attitude controller. A Lyapunov based analysis proved the closed-loop stability of the system despite the presence of unknown external perturbations. Monocular vision fused with inertial measurements are used to estimate the vehicle's pose with respect to unstructured scenes. In addition, the distance to potential collisions is detected and computed using the sparse depth map coming also from the vision algorithm. The proposed strategy is successfully tested in real-time experiments, using a low-cost commercial quadrotor.

An interplanetary autonomous navigation network, named the Internet of Spacecraft (IoS), is proposed in this paper to enable a Solar System-wide autonomous navigation capability for spacecraft. This network consists of two types of spacecraft, namely host and client spacecraft. The former provide the absolute reference for the whole network, and the latter determine their positions by communicating with the host spacecraft or other client spacecraft. To investigate the performance of IoS, a detailed application scheme that supports a flight from Earth to Mars is developed and analysed. IoS is not a simple extension of the navigation constellation. It is independent of the ground tracking system and the configuration of the network is flexible in that any spacecraft-installed identical device can be added to it. Moreover, client spacecraft whose positions have been determined can also be regarded as host spacecraft and provide further navigation information to others. This paper aims to provide technical support for future deep space exploration.

This paper presents an overview of the most recent vision-based multi-rotor micro unmanned aerial vehicles (MUAVs) intended for autonomous navigation using a stereoscopic camera. Drone operation is difficult because pilots need the expertise to fly the drones. Pilots have a limited field of view, and unfortunate situations, such as loss of line of sight or collision with objects such as wires and branches, can happen. Autonomous navigation is an even more difficult challenge than remote control navigation because the drones must make decisions on their own in real time and simultaneously build maps of their surroundings if none is available. Moreover, MUAVs are limited in terms of useful payload capability and energy consumption. Therefore, a drone must be equipped with small sensors, and it must carry low weight. In addition, a drone requires a sufficiently powerful onboard computer so that it can understand its surroundings and navigate accordingly to achieve its goal safely. A stereoscopic camera is considered a suitable sensor because of its three-dimensional (3D) capabilities. Hence, a drone can perform vision-based navigation through object recognition and self-localise inside a map if one is available; otherwise, its autonomous navigation creates a simultaneous localisation and mapping problem.

This paper concentrates on designing an autonomous navigation scheme for Mars exploration. In this scheme, formation flying spacecraft are used to realise absolute orbit determination when orbiting around Mars. Inertial Line-Of-Sight (LOS) vectors from “deputy” spacecraft to the “chief” are measured using radio cross-link, optical devices and attitude sensors. Since the system's observability is closely related to the navigation performance, an analytical approach is proposed to optimise the observability. In this method, the gravity gradient tensor difference is chosen as the performance index to optimise two navigation scenarios. When there is one deputy flying around the chief, optimal parameters are obtained by solving the constrained optimisation problem. When a second deputy is added into the formation, the optimal configuration is also obtained. These results reveal that the observability is mainly determined by the magnitude of the in-track and cross-track distances in the configuration. An Extended Kalman Filter (EKF) is used to estimate the position and velocity of the chief. The results of a navigation simulation confirms that adding more deputies can significantly improve the navigational performance.

The precise autonomous navigation for deep space exploration by combination of multi-source observation data is a key issue for probe control and scientific applications. In this paper, the performance of an integrated Optical Celestial Navigation (OCN) and X-ray Pulsars Autonomous Navigation (XNAV) system is investigated for the orbit of Mars Pathfinder. Firstly, OCN and XNAV single systems are realised by an Unscented Kalman Filter (UKF). Secondly, the integrated system is simulated with a Federated Kalman Filter (FKF), which can do the information fusion of the two subsystems of UKF and inherits the advantages of each subsystem. Thirdly, the performance of our system is evaluated by analysing the relationship between observation errors and navigation accuracy. The results of the simulation experiments show that the biases between the nominal and our calculated orbit are within 5 km in all three axes under complex error conditions. This accuracy is also better than current ground-based techniques.

In this paper, we consider the joint estimation of the position of a spacecraft and debris in Earth orbit to achieve spacecraft localisation based on angular measurements and precise measurements of the debris relative to the spacecraft. The dynamic model of the spacecraft caters for several perturbing effects, such as Earth and Moon gravitational field asymmetry and the Earth's oblateness effect. The Moon's position is assumed to be accurately known for the purposes of simulation from published Jet Propulsion Laboratory (JPL) ephemerides. The measurement process is based on the elevation and azimuth of the Moon and the Sun with respect to the spacecraft reference system. Range measurements are not assumed to be available. Position and velocity of the spacecraft are estimated by using the Unscented Kalman Filter (UKF). The performance of the filters are evaluated on an example of an Earth-orbiting satellite at an altitude over 1200 km with measurements of the directions of the Moon and the Sun only. It is shown that the estimates of position and velocity components track the corresponding simulated position and velocity components.

Volunteer potato is a perennial weed that is difficult to control in crop rotations. It was our objective to build a small, low-cost robot capable of detecting volunteer potato plants in a cornfield and thus demonstrate the potential for automatic control of this weed. We used an electric toy truck as the basis for our robot. We developed a fast row-recognition algorithm based on the Hough transform and implemented it using a webcam. We developed an algorithm that detects the presence of a potato plant based on a combination of size, shape, and color of the green elements in an image and implemented it using a second webcam. The robot was able to detect potatoes while navigating autonomously through experimental and commercial cornfields. In a first experiment, 319 out of 324 images were correctly classified (98.5%) as showing, or not showing, a potato plant. In a second experiment, 126 out of 141 images were correctly classified (89.4%). Detection of a potato plant resulted in an acoustic signal, but future robots may be fitted with weed control equipment, or they may use a global positioning system to map the presence of weed plants so that regular equipment can be used for control.

Nowadays, the most widely used method for estimating location of autonomous vehicles in real time is the use of Global Navigation Satellite Systems (GNSS). However, positioning in urban environments using GNSS is hampered by poor satellite geometry due to signal obstruction created by both man-made and natural features of the urban environment. The presence of obstacles is the reason for the decreased number of observed satellites as well as uncertainty of GNSS positioning. It is possible that in some sections of the vehicle route there might not be enough satellites necessary to fix position. It is common to use software for static GNSS measurement campaign planning, but it is often only able to predict satellite visibility at one point. This article presents a proposal for dynamic GNSS mission planning using a Digital Terrain Model (DTM) and dead reckoning. The methodology and sample results of numerical experiments are also described. They clearly show that proper dynamic GNSS mission planning is necessary in order to complete a task by an autonomous vehicle in an obstructed environment.