A computationally-efficient 2D imaging sonar model for underwater robotics simulations in Gazebo

Object detection and classification in the water enhances not only the application of the autonomous underwater vehicle(AUV) but also localization of the AUV. Object detection and classification using sonar images are challenging problems due to low resolution and low signal-to-noise ratio. In this paper, we propose shape classification method using multi-view sonar images for AUV. To train multi-view of sonar images, we used network which is connected in parallel with convolutional neural network(CNN). We used Alex-net for the basic CNN model. The extracted features by the CNN are collected through the pooling layer and connected to the fully connected layer to classify the shape. To overcome the lack of training data, sonar simulator was used to generate data set. As a result, 6 shape are well classified and also shows possibility for the recognition of the real sonar images acquired in water tank.

This research develops an underwater construction robot to level rubbles on the seabed for port construction. The rubble leveling is carried out by an underwater robot equipped with imaging sonars and underwater cameras, LBL and gyroscope sensors. A virtual reality system is developed to visualize the robots figure and the topography over the working environment; hence, the robot is virtually tele-operated by an operator. This paper presents the robot’s system and control, and it describes the working process of the rubble leveling carried out by the robot. In addition, the performance of the robot is demonstrated through the experimental results in subsea. The working speed of the robot is faster than that of a human diver, and the robot can work longer than the diver who can work for a limited time to prevent submarine sickness. The robot is expected to have much higher efficiency in deep water where a human diver is unable to work.

During the 1990s, numerous worldwide research and development activities have occurred in underwater robotics, especially in the area of autonomous underwater vehicles (AUVs). As the ocean attracts great attention on environmental issues and resources as well as scientific and military tasks, the need for and use of underwater robotic systems has become more apparent. Great efforts have been made in developing AUVs to overcome challenging scientific and engineering problems caused by the unstructured and hazardous ocean environment. In the 1990s, about 30 new AUVs have been built worldwide. With the development of new materials, advanced computing and sensory technology, as well as theoretical advancements, R&D activities in the AUV community have increased. However, this is just the beginning for more advanced, yet practical and reliable AUVs. This paper surveys some key areas in current state-of-the-art underwater robotic technologies. It is by no means a complete survey but provides key references for future development. The new millennium will bring advancements in technology that will enable the development of more practical, reliable AUVs.

The purpose of the study was to present a sequence of development of an algorithm for improving the quality of images obtained using side-scan sonar. Mathematical image processing techniques such as contrast enhancement, edge processing, and colorimetric techniques were used to achieve this goal. Steps to improve image contrast included normalising signal intensity, adaptive contrast enhancement using limited contrast alignment of histograms, and correction of uneven lighting. The sonar radiation pattern and image intensity normalisation scheme were demonstrated. The contrast limited adaptive histogram equalisation filter showed higher values of the peak signal-to-noise ratio and structural similarity index compared to conventional histogram alignment, indicating better preservation of detail, image structure, and noise reduction. Analysis of edge processing, in particular by Canny and Sobel, has shown their potential effectiveness in improving the detail of underwater structures. In addition, the use of Gaussian smoothing allowed reducing the level of high-frequency noise and make textures smoother. As a result, there was a decrease in graininess, softness of object contours, and overall smoothing of the scene. In addition, cubic spline regression showed normalised image data. In turn, colorimetric analysis focused on converting images between greyscale and colour spaces, which made it easier to identify underwater objects and structures. An example of Hue-Saturation-Value components was given, which demonstrated different effects on the quality of sonar image visualisation. The Value component provided the most expressive distinction between the object and the background, while the Hue component was ineffective for structure analysis. The combination of Value and Saturation allowed for improved contour detail. Optimisation of the pseudo-colour gamut allowed adapting the image to different tasks, contributing to more accurate object recognition. The results obtained confirm the feasibility of using the presented methods in a wide range of applied tasks related to visualisation and analysis of underwater environments

In certain precision work scenarios, underwater robots require the ability to adhere to surfaces in order to perform tasks effectively. An efficient and stable suction device plays a pivotal role in the functionality of such underwater robots. The vortex suction cup, distinguished by its uncomplicated design, high suction efficiency, and capability for non-contact adhesion, holds significant promise for integration into underwater robotic systems. This paper presents a novel design for a vortex suction cup and investigates its suction force and torque when encountering surfaces with varying curvature radii using Computational Fluid Dynamics (CFD) simulations and experimental testing. These findings offer valuable insights for the development of robots capable of adapting to underwater structures of different dimensions. Results from both experiments and simulations indicate that reducing the curvature radius of the adhered surface results in a decrease in suction force and an increase in torque exerted on the suction cup. As the adhered surface transitions from flat to a curvature radius of 150 mm, the adhesion force of our proposed vortex suction cup decreases by approximately 10%, while the torque increases by approximately 20% to 30%. Consequently, the adhesion efficiency of the suction cup decreases by about 25% to 30%.

This paper presents a process of vision based controller implementation in order to control a spherical rolling robot. A Linear Quadratic Gaussian (LQG) controller is applied as a complementary controller for the proposed spherical rolling robot. The LQG controller is used to synchronize the robot's motors. The simulation results, which are obtained from a Co-simulation between MSC ADAMS and MATLAB software validated the prosperity of the proposed LQG controller in term of synchronizing the aforesaid robot's motors, which lead the robot to have a better performance in path tracking and decreasing the deviation rate from the desired path. In order to find a short path between the obstacles, which are set in the robot's workspace, a potential field algorithm is designed and implemented on the robot workspace in Gazebo simulator. As stated by the simulation results, the performance of the spherical rolling robot under study in terms of autonomous path tracking is considerably improved. The mentioned performance is considered according to the vision control which is done in Gazebo simulator. Furthermore, the simulation results corroborate that using the LQG and vision based controllers simultaneously, improved the performance of the aforesaid robot significantly in terms of steering and obstacle avoidance.

A pulsed-laser ablation method for non-contact experimental vibration analysis of completely submerged underwater structures is proposed. Although impact testing with an impulse hammer is commonly used for vibration analysis due to its simplicity, impact testing has limited use in underwater conditions. An input-detection-free frequency response function measurement in water will greatly contribute to the development of high-precision and high-speed positioning autonomous underwater vehicles, underwater vehicle-manipulators, underwater robots, submarines, etc., which are used in dangerous conditions (e.g., deep oceans, under ice, and nuclear reactor plants). To achieve these high-performance underwater systems, vibrations due to hydrodynamic parameters (such as added mass, buoyant force, drag force, and damping coefficient) should be suppressed, and vibration tests should be conducted on the actual equipment submerged in water. The proposed method yields the frequency response function by applying a pulsed-laser-ablation excitation force to an underwater structure and measuring the output using a laser Doppler vibrometer. Because the direction, strength, and effective duration of the pulsed-laser-ablation force are essentially constant, this force can be estimated by measuring these properties in advance. Hence, the proposed method realizes input-detection-free frequency response function measurements in underwater conditions.

The integrate of underwater structure of dams and bridges are very important for the safety of the projects. However, due to the complex flow field near the underwater structure, it is a challenge for the underwater robot to maintain stable near the underwater structures when performing inspection tasks. Moreover, it is difficult for underwater robots to absorb on the surface of underwater structures due to rough surface. This paper proposes a design of an adsorption track wheel for underwater wall-climbing robot, which combines the swirl suction cup and track wheel. The relationship between the water flow velocity, the wall gap and the suction cup adsorption force are analyzed. The influence of the surface curvature diameter of the structure and the diameter of the suction cup on the suction force is explored, and the structure of the suction cup is optimized to resist the influence of the water flow on the suction cup as much as possible while considering the flow velocity. After the suction cup improved, a prototype is designed and built. The final experiment demonstrates that the track wheel can provide sufficient adsorption force and friction force, which helps the structure to resist the water flow velocity up to 2.5m/s. Finally, it proposes the track wheel prototype can provide stable adsorption on the surface of underwater buildings for complex flow field.

With the expansion of human activities into mountainous regions, jungles, deserts, rural roads, and off-road terrains, there is an increasing demand for reliable navigation and location services in wild unstructured environments. Unlike urban environments, where established methodologies exist for constructing navigation maps, roadless unstructured environments lack comprehensive frameworks for navigation map construction. The conventional waypoint-based structures, which are well-suited to urban environments, are often ill-suited to the expansive and unstructured nature of field regions. Moreover, the absence of predefined user paths necessitates a fundamentally different approach to map construction. To address this challenge, we propose a novel method for generating navigation maps in unstructured roadless environment. New methodology leverages remote sensing as input for environmental perception, translating user traversability into geographical parameters and constructing a navigation mesh as a computational map. Compared with existing methods, the new method can adapt to large-scale unstructured environments. To validate the proposed method, reliability sampling tests and operational experiments were conducted on traversable area delineation and the navigation map generation. The experimental results indicate an 84% accuracy in traversable area analysis, with the constructed navigation map effectively supporting positioning and path planning while significantly reducing computational complexity in large-scale path planning tasks. The navigation mesh generated through this method effectively enhances the implementation of navigation and positioning services in off-road and roadless environments. The proposed method facilitates the construction of navigation maps capable of delivering navigation and localization services without requiring human presence in the target area.

Nowadays, small autonomous underwater robots are strongly preferred for remote exploration of unknown and unstructured environments. Such robots allow the exploration and monitoring of underwater environments where a long term underwater presence is required to cover a large area. Furthermore, reducing the robot size, embedding electrical board inside and reducing cost are some of the challenges designers of autonomous underwater robots are facing. As a key device for reliable operation-decision process of autonomous underwater robots, a relatively fast and cost effective controller based on Fuzzy logic and proportional-integral-derivative method is proposed in this thesis. It efficiently models nonlinear system behaviors largely present in robot operation and for which mathematical models are difficult to obtain. To evaluate its response, the fault finding test approach was applied and the response of each task of the robot depicted under different operating conditions. The robot performance while combining all control programs and including sensors was also investigated while the number of program codes and inputs were increased.

This paper presents the implementation of an electrical power system in MATLAB/Simulink and its execution in a real-time environment, called laboratory set-up for real-time power system simulation. This test-bed can help engineer and operator to learn the reaction of real power system in a virtual environment. Consistent to this issue, related software and hardware (National Instrument) are utilized to monitor electrical system variables, as well as analyze and evaluate power system stability in different real scenarios. The system implemented in MATLAB/Simulink, includes synchronous generator, power system stabilizer (PSS), excitation system and external grid. PXIe-8133 hardware allows user to execute different scenarios in the real-time mode. Also, LabVIEW DSC Module, a special monitoring system for industrial application, is used to access and flow data between several Vis. A program is developed in LabVIEW environment to initialize interaction between MATLAB generated *.dll file and LabVIEW via simulation interface toolkit (SIT) and in a parallel operation, data is simultaneously transferred between these two environments. EZDSP 320f2812 board is considered as hardware-in-the-loop (HIL). This feature helps engineer to implement control logic of power system equipment (here, real excitation system logic) in the DSP board. Based on the proposed idea, this board can serve as an emulator of real system and the functionality of control logic as well as its behavior is simulated and verified. This board and related potentiometer play the role of real excitation system and receive three-phase voltages and currents from NI PXI 7833R card. In return, the board generates excitation voltage and sends it back to PXIe-8133 and consequently, the loop will be closed. Finally, different scenarios in a power system are provided to show the application of real-time HIL system in the power industry as well as verification of proposed approach for training centers.

Model predictive control is a promising method in robot control tasks. How to design an effective model structure and efficient prediction framework for model predictive control is still an open challenge. To reduce the time consumption and avoid compounding-error of the multi-step prediction process in model predictive control, we propose a single-model simultaneous framework, which uses single dynamics model to predict the entire prediction horizon simultaneously by taking all control actions with the current state as inputs. Based on this framework, we further propose an adversarial dynamics model that contains two parts. The generator provides a dynamics model for the prediction process, while the discriminator provides constraints that are hard to describe by manually defined loss. This adversarial dynamics model can accelerate training and improve model accuracy in unstructured environments. Experiments conducted in Gazebo simulator and on a real mobile robot demonstrate the efficiency and accuracy of the single-model simultaneous framework with an adversarial dynamics model.

This paper proposes a method to detect underwater objects using sonar image simulator and convolutional neural network (CNN). Instead of simulating very realistic sonar images which is computationally complex, we implemented a simple sonar simulator that calculates only semantic information. Then, we generated training images of target objects by adding randomized degradation effects to the simulated images. The CNN trained with these generated images is robust to the degradation effects inherent in sonar images and thus can detect target objects in real sonar images. We verified the proposed method using the sonar images captured at sea through field experiments. The proposed method can implement object detection more easily because it only uses simulated images instead of real sonar images which are challenging to acquire. The proposed method can also be applied to other sonar-image-based algorithms.

The evolution of bionic machines into intelligent robots to adapt to real scenarios is inseparable from positioning sensors. However, traditional positioning methods such as camera arrays, ultrasound, or GPS are limited in narrow concealed spaces, harsh temperatures, or dynamic light fields, which hinder the practical application of special robots. Here, we report a flexible sensor inspired by Gnathonemus petersii that enables robots to achieve contactless and high-precision spatial localization independent of the unstructured features of the environment. Sensors are obtained from low-cost materials (carbon nanotubes and polyimides) and simple structures (fibers) and preparation processes (spin-coating). Experiments and simulations confirmed the high resolution (<1 mm) of the sensor over a large distance detection range (>150 mm) and high bandwidth (0-520 MPa) of contact force. Moreover, the sensing capability is still feasible when the sensor is bent to various curvatures and not affected under harsh conditions such as ultralow temperatures (below -78 °C), ultrahigh temperatures (over 250 °C), darkness, or brightness. We demonstrate the practical potential of the proposed sensors for a biomimetic hyper-redundant continuum robot to locate and avoid collisions in unstructured environments.

The Army Research Laboratory (ARL) Robotics Collaborative Technology Alliance (CTA) conducted an assessment and evaluation of multiple algorithms for real-time detection of pedestrians in Laser Detection and Ranging (LADAR) and video sensor data taken from a moving platform. The algorithms were developed by Robotics CTA members and then assessed in field experiments jointly conducted by the National Institute of Standards and Technology (NIST) and ARL. A robust, accurate and independent pedestrian tracking system was developed to provide ground truth. The ground truth was used to evaluate the CTA member algorithms for uncertainty and error in their results. A real-time display system was used to provide early detection of errors in data collection.