Search results

This paper aims to facilitate the research and development of resilient navigation approaches, explore the robustness of adversarial training to different interferences and promote their practical applications in real complex environments.

In this paper, the authors first summarize the real accidents of self-driving cars and develop a set of methods to simulate challenging scenarios by introducing simulated disturbances and attacks into the input sensor data. Then a robust and transferable adversarial training approach is proposed to improve the performance and resilience of current navigation models, followed by a multi-modality fusion-based end-to-end navigation network to demonstrate real-world performance of the methods. In addition, an augmented self-driving simulator with designed evaluation metrics is built to evaluate navigation models.

Synthetical experiments in simulator demonstrate the robustness and transferability of the proposed adversarial training strategy. The simulation function flow can also be used for promoting any robust perception or navigation researches. Then a multi-modality fusion-based navigation framework is proposed as a light-weight model to evaluate the adversarial training method in real-world.

The adversarial training approach provides a transferable and robust enhancement for navigation models both in simulation and real-world.

The purpose of this paper is to provide a comprehensive and unified presentation of recent developments in skid-steer wheeled mobile robots (SSWMR) with regard to its control, guidance and navigation for the researchers who wish to study in this field.

Most of the contemporary unmanned ground robot’s locomotion is based upon the wheels. For wheeled mobile robots (WMRs), one of the prominent and widely used driving schemes is skid steering. Because of mechanical simplicity and high maneuverability particularly in outdoor applications, SSWMR has an advantage over its counterparts. Different prospects of SSWMR have been discussed including its design, application, locomotion, control, navigation and guidance. The challenges pertaining to SSWMR have been pointed out in detail, which will seek the attention of the readers, who are interested to explore this area.

Relying on the recent literature on SSWMR, research gaps are identified that should be analyzed for the development of autonomous skid-steer wheeled robots.

An attempt to present a comprehensive review of recent advancements in the field of WMRs and providing references to the most intriguing studies.

The main purpose of this paper is to investigate two key elements of localization and mapping of Autonomous Underwater Vehicle (AUV), i.e. to overview various sensors and algorithms used for underwater localization and mapping, and to make suggestions for future research.

The authors first review various sensors and algorithms used for AUVs in the terms of basic working principle, characters, their advantages and disadvantages. The statistical analysis is carried out by studying 35 AUV platforms according to the application circumstances of sensors and algorithms.

As real‐world applications have different requirements and specifications, it is necessary to select the most appropriate one by balancing various factors such as accuracy, cost, size, etc. Although highly accurate localization and mapping in an underwater environment is very difficult, more and more accurate and robust navigation solutions will be achieved with the development of both sensors and algorithms.

This paper provides an overview of the state of art underwater localisation and mapping algorithms and systems. No experiments are conducted for verification.

The paper will give readers a clear guideline to find suitable underwater localisation and mapping algorithms and systems for their practical applications in hand.

There is a wide range of audiences who will benefit from reading this comprehensive survey of autonomous localisation and mapping of UAVs.

The paper will provide useful information and suggestions to research students, engineers and scientists who work in the field of autonomous underwater vehicles.

Accurate perception of the environment using range sensors such as laser scanner, SONAR, infrared, vision, etc., for the application, such as path planning, localization, autonomous navigation, simultaneously localization and mapping, is a highly challenging area. The reliability of the perception by range sensors relies on the sensor accuracy, precision, sensor model, sensor registration, resolution, etc. Laser scanner is even though accurate and precise but still the efficient and consistent mapping of the environment is yet to be attained because laser scanner gives error as the extrinsic and intrinsic parameters varied which cause specular reflection, refraction, absorption, etc., of the laser beam. The paper aims to discuss this issue.

This paper presents an error analysis in sensory information of laser scanner due to the effect of varying the scanning angle with respect to the optical axis and surface reflectivity or refractive index of the targets. Uncertainties caused by these parameters are reduced by proposing a new technique, tilt mounting system (TMS) with designed filters of tilting the angular position of a laser scanner with the best possible selection of range and scanning angle for the robust occupancy grid mapping. Various experiments are performed in different indoor environments, and the results are validated after the implementation of the TMS approach with designed filters.

After the implementation of the proposed TMS approach with filters, the errors in the laser grid map are reduced by 15.6 percent, which results in 62.5 percent reduction in the collision of a mobile robot during autonomous navigation in the laser grid map.

The TMS approach with designed filter reduces the effect of variation in intrinsic and extrinsic parameters to generate efficient laser occupancy grid map to achieve collision-free autonomous navigation.

This paper aims to present a multi-source information fusion algorithm based on factor graph for autonomous underwater vehicles (AUVs) navigation and positioning to address the asynchronous and heterogeneous problem of multiple sensors.

The factor graph is formulated by joint probability distribution function (pdf) random variables. All available measurements are processed into an optimal navigation solution by the message passing algorithm in the factor graph model. To further aid high-rate navigation solutions, the equivalent inertial measurement unit (IMU) factor is introduced to replace several consecutive IMU measurements in the factor graph model.

The proposed factor graph was demonstrated both in a simulated and vehicle environment using IMU, Doppler Velocity Log, terrain-aided navigation, magnetic compass pilot and depth meter sensors. Simulation results showed that the proposed factor graph processes all available measurements into the considerably improved navigation performance, computational efficiency and complexity compared with the un-simplified factor graph and the federal Kalman filtering methods. Semi-physical experiment results also verified the robustness and effectiveness.

The proposed factor graph scheme supported a plug and play capability to easily fuse asynchronous heterogeneous measurements information in AUV navigation systems.

Briefly reviews co‐ordinate‐based navigation, behaviour‐based navigation, navigation with a conic mirror and navigation with a spherical mirror. Proposes to include fuzzy languages and fuzzy instructions to perform robot navigation. Gives illustrative examples. One main characteristic of this approach is to trade precision with speed. This approach may also be applied to object motion tracking and fault‐tolerant task scheduling.

This paper aims to review the use of imaging technologies in robotics, with an emphasis on inspection applications and the control of autonomous robots.

Following a brief introduction, this paper first considers vision‐based robotic inspection systems and highlights a selection of recent applications. Second, it considers the use of vision in autonomous robot navigation and discusses some of the challenges and recent developments.

This shows that developments in machine vision have led to vision systems being used in a diversity of component‐level and in‐service robotic inspection tasks. It also illustrates that vision systems have a key role to play in the emerging generation of autonomous, mobile robots.

This paper provides a review of recent developments in vision‐based robotic inspection and autonomous, mobile robot navigation.

This paper explores the technologies necessary for the development of autonomous ground vehicles to be used in the construction process. Consideration is given to the technological challenges to be resolved for the machines to evolve in an almost unstructured environment. The paper includes sample cases of current applications and examines future perspectives on the use of these devices. Emphasis is placed on the collaborative aspects that need to be developed between man and machine in order to make effective use of these resources on site.

The purpose of this paper is to provide a more capable and holistic adjustable autonomy system, involving situation reasoning among all involved information sources, to make an adjustable autonomy system which knows what the situation is currently, what needs to be done in the present situation, and how risky the task is in the present situation. This will enhance efficiency for calculating the level of autonomy.

Situation reasoning methodologies are present in many autonomous systems which are called situation awareness. Situation awareness in autonomous systems is divided into three levels, situation perception, situation comprehension and situation projection. Situation awareness in these systems aims to make the tactical plans cognitive, but situation reasoning in adjustable autonomous systems aim to communicate mission assessments to unmanned vehicle or humans. Thus, in solving this problem, it is important to design a new situation reasoning module for the adjustable autonomous system.

The contribution of this paper is presenting the Situation Reasoning Module (SRM) for an adjustable autonomous system, which encapsulates event detection, cognitive situations, cognitive tasks, performance capacity assessment and integrated situation reason. The paper concludes by demonstrating the benefits of the SRM in a real‐world scenario, a situation reasoning simulation in unmanned surface vehicles (USV) while performing a navigation mission.

The method presented in this paper represents a new SRM to reason the situation for adjustable autonomous system. While the results presented in the paper are based on fuzzy logic and Bayesian network methodology. The results of this paper can be applicable to land, sea and air robotics in an adjustable autonomous system.

This paper aims to address three major issues in the development of a vision‐based navigation system for small unmanned aerial vehicles (UAVs) which can be characterized as follows: technical constraints, robust image feature matching and an efficient and precise method for visual navigation.

The authors present and evaluate methods for their solution such as wireless networked control, highly distinctive feature descriptors (HDF) and a visual odometry system.

Proposed feature descriptors achieve significant improvements in computation time by detaching the explicit scale invariance of the widely used scale invariant feature transform. The feasibility of wireless networked real‐time control for vision‐based navigation is evaluated in terms of latency and data throughput. The visual odometry system uses a single camera to reconstruct the camera path and the structure of the environment, and achieved and error of 1.65 percent w.r.t total path length on a circular trajectory of 9.43 m.

The originality/value lies in the contribution of the presented work to the solution of visual odometry for small unmanned aerial vehicles.