Search

Ensuring safe and continuous autonomous navigation in long-term mobile robot applications is still challenging. To ensure a reliable representation of the current environment without the need for periodic remapping, updating the map is recommended. However, in the case of incorrect robot pose estimation, updating the map can lead to errors that prevent the robot’s localisation and jeopardise map accuracy. In this paper, we propose a safe Lidar-based occupancy grid map-updating algorithm for dynamic environments, taking into account uncertainties in the estimation of the robot’s pose. The proposed approach allows for robust long-term operations, as it can recover the robot’s pose, even when it gets lost, to continue the map update process, providing a coherent map. Moreover, the approach is also robust to temporary changes in the map due to the presence of dynamic obstacles such as humans and other robots. Results highlighting map quality, localisation performance, and pose recovery, both in simulation and experiments, are reported.

Offshore support structures and mooring systems are predominantly subject to corrosion and fatigue. These structures are typically covered with marine growth of various types. Conventional inspection methods for assessment of the structural integrity require access to the cleaned surface of these structures; however, the cleaning process is highly undesirable from the technical, economical, and environmental points of view. This paper highlights research on feasibility assessment of detection and localization of corrosion damage under marine growth using acoustic emission (AE). Experiments were conducted on two carbon steel plates, one baseline sample and one covered with artificially fabricated marine growth. The results of accelerated corrosion experiments suggest that corrosion-induced ultrasound signals can be detected with satisfactory signal-to-noise ratio using non-contact AE sensors. Ultrasound waves passing through marine growth showed around 12 dB drop in amplitude when compared to the base plate. A localization algorithm for corrosion induced-ultrasound signals was successfully implemented.

The recent advancements in Information and Communication Technology (ICT) as well as increasing demand for vehicular safety has led to significant progressions in Autonomous Vehicle (AV) technology. Perception and Localisation are major operations that determine the success of AV development and usage. Therefore, significant research has been carried out to provide AVs with the capabilities to not only sense and understand their surroundings efficiently, but also provide detailed information of the environment in the form of 3D maps. Visual Simultaneous Localisation and Mapping (V-SLAM) has been utilised to enable a vehicle understand its surroundings, map the environment, and identify its position within the area. This paper presents a detailed review of V-SLAM techniques implemented for AV perception and localisation. An overview of SLAM techniques is presented. In addition, an in-depth review is conducted to highlight various V-SLAM schemes, their strengths, and limitations. Challenges associated with V-SLAM deployment and future research directions are also provided in this paper.

Recent deep learning frameworks draw strong research interest in application of ego-motion estimation as they demonstrate a superior result compared to geometric approaches. However, due to the lack of multimodal datasets, most of these studies primarily focused on single-sensor-based estimation. To overcome this challenge, we collect a unique multimodal dataset named LboroAV2 using multiple sensors, including camera, light detecting and ranging (LiDAR), ultrasound, e-compass and rotary encoder. We also propose an end-to-end deep learning architecture for fusion of RGB images and LiDAR laser scan data for odometry application. The proposed method contains a convolutional encoder, a compressed representation and a recurrent neural network. Besides feature extraction and outlier rejection, the convolutional encoder produces a compressed representation, which is used to visualise the network’s learning process and to pass useful sequential information. The recurrent neural network uses this compressed sequential data to learn the relationship between consecutive time steps. We use the Loughborough autonomous vehicle (LboroAV2) and the Karlsruhe Institute of Technology and Toyota Institute (KITTI) Visual Odometry (VO) datasets to experiment and evaluate our results. In addition to visualising the network’s learning process, our approach provides superior results compared to other similar methods. The code for the proposed architecture is released in GitHub and accessible publicly.

Smart maintenance is essential to achieving a safe and reliable railway, but traditional maintenance deployment is costly and heavily human-involved. Ineffective job execution or failure in preventive maintenance can lead to railway service disruption and unsafe operations. The deployment of robotic and autonomous systems was proposed to conduct these maintenance tasks with higher accuracy and reliability. In order for these systems to be capable of detecting rail flaws along millions of mileages they must register their location with higher accuracy. A prerequisite of an autonomous vehicle is its possessing a high degree of accuracy in terms of its positional awareness. This paper first reviews the importance and demands of preventive maintenance in railway networks and the related techniques. Furthermore, this paper investigates the strategies, techniques, architecture, and references used by different systems to resolve the location along the railway network. Additionally, this paper discusses the advantages and applicability of on-board-based and infrastructure-based sensing, respectively. Finally, this paper analyses the uncertainties which contribute to a vehicle’s position error and influence on positioning accuracy and reliability with corresponding technique solutions. This study therefore provides an overall direction for the development of further autonomous track-based system designs and methods to deal with the challenges faced in the railway network.

Cloud Computing and Cloud Platforms have become an essential resource for businesses, due to their advanced capabilities, performance, and functionalities. Data redundancy, scalability, and security, are among the key features offered by cloud platforms. Location-Based Services (LBS) often exploit cloud platforms to host positioning and localisation systems. This paper introduces a systematic review of current positioning platforms for GNSS-denied scenarios. We have undertaken a comprehensive analysis of each component of the positioning and localisation systems, including techniques, protocols, standards, and cloud services used in the state-of-the-art deployments. Furthermore, this paper identifies the limitations of existing solutions, outlining shortcomings in areas that are rarely subjected to scrutiny in existing reviews of indoor positioning, such as computing paradigms, privacy, and fault tolerance. We then examine contributions in the areas of efficient computation, interoperability, positioning, and localisation. Finally, we provide a brief discussion concerning the challenges for cloud platforms based on GNSS-denied scenarios.

The capability to estimate the pose of known geometry from point cloud data is a frequently arising requirement in robotics and automation applications. This problem is directly addressed by Iterative Closest Point (ICP), however, this method has several limitations and lacks robustness. This paper makes the case for an alternative method that seeks to find the most likely solution based on available evidence. Specifically, an evidence-based metric is described that seeks to find the pose of the object that would maximise the conditional likelihood of reproducing the observed range measurements. A seedless search heuristic is also provided to find the most likely pose estimate in light of these measurements. The method is demonstrated to provide for pose estimation (2D and 3D shape poses as well as joint-space searches), object identification/classification, and platform localisation. Furthermore, the method is shown to be robust in cluttered or non-segmented point cloud data as well as being robust to measurement uncertainty and extrinsic sensor calibration.

Solid-State LiDAR (SSL) takes an increasing share of the LiDAR market. Compared with traditional spinning LiDAR, SSLs are more compact, energy-efficient and cost-effective. Generally, the current study of SSL mapping is limited to adapting existing SLAM algorithms to an SSL sensor. However, compared with spinning LiDARs, SSLs are different in terms of their irregular scan patterns and limited FOV. Directly applying existing SLAM approaches on them often increase the instability of a mapping process. This study proposes a systematic design, which consists of a dual-LiDAR mapping system and a three DOF interpolated six DOF odometry. For dual-LiDAR mapping, this work uses a 2D LiDAR to enhance a 3D SSL performance on a ground vehicle platform. The proposed system takes a 2D LiDAR to preprocess the scanning field into a number of feature sections according to the curvatures on the 2D fraction. Subsequently, this section information is passed to 3D SSL for direction feature selection. Additionally, this work proposes an odometry interpolation method which uses both LiDARs to generate two separated odometries. The proposed odometry interpolation method selectively determines the appropriate odometry information to update the system state under challenging conditions. Experiments are conducted in different scenarios. The results proves that the proposed approach is able to utilise 12 times more corner features from the environment than the comparied method, thus results in a demonstrable improvement in its absolute position error.

Creating an accurate awareness of the environment using laser scanners is a major challenge in robotics and auto industries. LiDAR (light detection and ranging) is a powerful laser scanner that provides a detailed map of the environment. However, efficient and accurate mapping of the environment is yet to be obtained, as most modern environments contain glass, which is invisible to LiDAR. In this paper, a method to effectively detect and localise glass using LiDAR sensors is proposed. This new approach is based on the variation of range measurements between neighbouring point clouds, using a two-step filter. The first filter examines the change in the standard deviation of neighbouring clouds. The second filter uses a change in distance and intensity between neighbouring pules to refine the results from the first filter and estimate the glass profile width before updating the cartesian coordinate and range measurement by the instrument. Test results demonstrate the detection and localisation of glass and the elimination of errors caused by glass in occupancy grid maps. This novel method detects frameless glass from a long range and does not depend on intensity peak with an accuracy of 96.2%.

Radiation mapping, through the detection of ionising gamma-ray emissions, is an important technique used across the nuclear industry to characterise environments over a range of length scales. In complex scenarios, the precise localisation and activity of radiological sources becomes difficult to determine due to the inability to directly image gamma photon emissions. This is a result of the potentially unknown number of sources combined with uncertainties associated with the source-detector separation—causing an apparent ‘blurring’ of the as-detected radiation field relative to the true distribution. Accurate delimitation of distinct sources is important for decommissioning, waste processing, and homeland security. Therefore, methods for estimating the precise, ‘true’ solution from radiation mapping measurements are required. Herein is presented a computational method of enhanced radiological source localisation from scanning survey measurements conducted with a robotic arm. The procedure uses an experimentally derived Detector Response Function (DRF) to perform a randomised-Kaczmarz deconvolution from robotically acquired radiation field measurements. The performance of the process is assessed on radiation maps obtained from a series of emulated waste processing scenarios. The results demonstrate a Projective Linear Reconstruction (PLR) algorithm can successfully locate a series of point sources to within 2 cm of the true locations, corresponding to resolution enhancements of between 5× and 10×.

This paper presents a novel two-stage system which integrates topological localisation candidates from a radar-only place recognition system with precise pose estimation using spectral landmark-based techniques. We prove that the—recently available—seminal radar place recognition (RPR) and scan matching sub-systems are complementary in a style reminiscent of the mapping and localisation systems underpinning visual teach-and-repeat (VTR) systems which have been exhibited robustly in the last decade. Offline experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community with performance comparing favourably with and even rivalling alternative state-of-the-art radar localisation systems. Specifically, we show the long-term durability of the approach and of the sensing technology itself to autonomous navigation. We suggest a range of sensible methods of tuning the system, all of which are suitable for online operation. For both tuning regimes, we achieve, over the course of a month of localisation trials against a single static map, high recalls at high precision, and much reduced variance in erroneous metric pose estimation. As such, this work is a necessary first step towards a radar teach-and-repeat (RTR) system and the enablement of autonomy across extreme changes in appearance or inclement conditions.

The inspection of aquatic environments is a challenging activity, which is made more difficult if the environment is complex or confined, such as those that are found in nuclear storage facilities and accident sites, marinas and boatyards, liquid storage tanks, or flooded tunnels and sewers. Human inspections of these environments are often dangerous or infeasible, so remote inspection using unmanned underwater vehicles (UUVs) is used. Due to access restrictions and environmental limitations, such as low illumination levels, turbidity, and a lack of salient features, traditional localisation systems that have been developed for use in large bodies of water cannot be used. This means that UUV capabilities are severely restricted to manually controlled low-quality visual inspections, generating non-geospatially located data. The localisation of UUVs in these environments would enable the autonomous behaviour and the development of accurate maps. This article presents a review of the state-of-the-art in localisation technologies for these environments and identifies areas of future research to overcome the challenges posed.

In core computer vision tasks, we have witnessed significant advances in object detection, localisation and tracking. However, there are currently no methods to detect, localize and track objects in road environments, and taking into account real-time constraints. In this paper, our objective is to develop a deep learning multi object detection and tracking technique applied to road smart mobility. Firstly, we propose an effective detector-based on YOLOv3 which we adapt to our context. Subsequently, to localize successfully the detected objects, we put forward an adaptive method aiming to extract 3D information, i.e., depth maps. To do so, a comparative study is carried out taking into account two approaches: Monodepth2 for monocular vision and MADNEt for stereoscopic vision. These approaches are then evaluated over datasets containing depth information in order to discern the best solution that performs better in real-time conditions. Object tracking is necessary in order to mitigate the risks of collisions. Unlike traditional tracking approaches which require target initialization beforehand, our approach consists of using information from object detection and distance estimation to initialize targets and to track them later. Expressly, we propose here to improve SORT approach for 3D object tracking. We introduce an extended Kalman filter to better estimate the position of objects. Extensive experiments carried out on KITTI dataset prove that our proposal outperforms state-of-the-art approches.

This paper presents an algorithm for the localisation of partial discharge (PD) sources in power transformers based on the electromagnetic waves radiated by a PD pulse. The proposed algorithm is more accurate than existing methods, since it considers the effects of the reflection, refractions and diffractions undergone by the ultra-high frequency (UHF) signal within the equipment tank. The proposed method uses computational simulations of the electromagnetic waves generated by PD, and obtains the time delay of the signal between each point in the 3D space and the UHF sensors. The calculated signals can be compared with the signals measured in the field, so that the position of the PD source can be located based on the best correlation between the simulated propagation delay and the measured data. The equations used in the proposed method are defined as a 3D optimisation problem, so that the binary particle swarm optimisation algorithm can be used. To test and demonstrate the proposed algorithm, computational simulations were performed. The solutions were sufficient to identify not only the occurrence of defects, but also the winding and the region (top, centre or base) in which the defect occurred. In all cases, an accuracy of greater than 15 cm was obtained for the location, in a 180 MVA three-phase transformer.

This article evaluates the use of least-squares support vector machines, with ray-traced data, to solve the problem of localisation in multipath environments. The schemes discussed concern 2-D localisation, but could easily be extended to 3-D. It does not require NLOS identification and mitigation, hence, it can be applied in any environment. Some background details and a detailed experimental setup is provided. Comparisons with schemes that require NLOS identification and mitigation, from earlier work, are also presented. The results demonstrate that the direct localisation scheme using least-squares support vector machine (the Direct method) achieves superior outage to TDOA and TOA/AOA for NLOS environments. TDOA has better outage in LOS environments. TOA/AOA performs better for an accepted outage probability of 20 percent or greater but as the outage probability lowers, the Direct method becomes better.

Recent developments in localisation systems for autonomous robotic technology have been a driving factor in the deployment of robots in a wide variety of environments. Estimating sensor measurement noise is an essential factor when producing uncertainty models for state-of-the-art robotic positioning systems. In this paper, a surveying grade optical instrument in the form of a Trimble S7 Robotic Total Station is utilised to dynamically characterise the error of positioning sensors of a ground based unmanned robot. The error characteristics are used as inputs into the construction of a Localisation Extended Kalman Filter which fuses Pozyx Ultra-wideband range measurements with odometry to obtain an optimal position estimation, all whilst using the path generated from the remote tracking feature of the Robotic Total Station as a ground truth metric. Experiments show that the proposed method yields an improved positional estimation compared to the Pozyx systems’ native firmware algorithm as well as producing a smoother trajectory.