Search

Based on monocular camera, an underwater detection and tracking system for amphibious spherical robot is proposed to realize autonomous cruise of underwater pipelines. Firstly, according to the imaging characteristics of underwater image, the image of pipeline is detected by image binarization, edge detection and Hough transform. And then, the Kalman filter was carried out according to the edge information and the underwater pipeline was tracked. The control scheme of the visual system to the amphibious spherical robot was improved, and the tracking pipe motion of the amphibious robot is controlled by PID algorithm. Finally, we carried out some experiments under different scenes to demonstrate the effectiveness of the proposed underwater pipeline tracking system, and the experimental results showed that the proposed underwater pipeline tracking algorithm has good robustness and real - time performance.

To execute vision-based tasks of the amphibious spherical robot, a visual tracking system was designed and constructed. A RGB-D camera was calibrated in the amphibious environments and was then used to perceive the surroundings of the robot. A RGB-D tracker, which was capable of handling occlusions and scale changes of the target, was built upon the KCF tracker to locate the target object. HoG and CN features in the color images were extracted to describe the target object. The scale and position models of the object was established using the Gaussian model and the depth histogram of the object. The occlusion event was recognized by segmenting the depth image and using an empirical formula. The online update process of the KCF tracker was temporarily stopped once an occlusion event was detected. Experimental results with various image sequences in amphibious environments demonstrated the effectiveness and robustness of the proposed tracking algorithm, which can meet the application requirements of the amphibious spherical robots.

Considering the complicated disturbance in underwater circumstance, usually it is difficult to solve the control problem when the robot changes its motion state or it is subject to ocean currents, its performance deteriorates since the fixed set of parameters is no longer valid for the new conditions. Thus, in this paper, an auto-tune PID (Proportional + Integral + Derivative)-like controller based on Neural Networks is applied to our amphibious spherical underwater robot, which has a great advantage on processing online for the robot due to their nonlinear dynamics. The Neural Networks (NN) plays the role of automatically estimating the suitable set of PID gains that achieves stability of the system. The NN adjusts online the controller gains that attain the smaller position tracking error. The performance of the NN-based controller is investigated in ADAMS and MATLAB cooperative simulation. The velocity of the spherical robot can be controlled to precisely track desired trajectory in body-fixed coordinate system. Additionally, real time experiments on our underwater spherical robot are conducted to show the effectiveness of the algorithm.

Location system is crucial to many intelligent robots, especially for underwater robots. To increase the autonomous ability of amphibious spherical robots in underwater environment, an underwater vision locating system was designed in this paper, and the ToF (time of fly) camera (RGB-D camera) was used and introduced in this system. Through the image capture from the camera in water, two kinds of image information could be acquired, which are include color image and depth image. The theoretical analysis show that the location of objective could be calculate easily from those image information. In underwater environment, the depth information attenuated, a calibration experiment for distance correction was designed. These results were used for the coordinate establishing. The construction of the experimental environment and final results were provided. Through the analysis of experimental results, the feasibility of the vision locating method based the RGB-D camera was verified and this system will be used for providing the location of amphibious spherical robots in the future work.

Robust and performing navigation systems for Autonomous Underwater Vehicles (AUVs) play a discriminant role towards the success of complex underwater missions. This paper presents a new design and development of a low-cost INS (Inertial Navigation System) using Miro-Electro-Mechanical-System (MEMS) inertial sensor and the pressure sensor (PS). The intensive pre-processing and modeling MEMES sensor's primitive, noisy motion data are outline, these techniques transform the erroneous motion data into practical motion indicators illustrated in 3D position, 3D velocity and 3D orientation. INS acts as a dead reckoning device. The pressure sensor is used to detect the depth data of underwater Vehicles. The quality of the filtering algorithm for the estimation of the AUV navigation state strongly affects the performance of the overall system. In this paper, the authors present adapt the Kalman Filter (KF) approach. Experiments were conducted to improve the navigation system performance of the INS and PS installed on the Amphibious Spherical Robot III (ASR III) for motion and attitude estimation. Lastly the experiment results are evaluated and verified using the sensor data from the navigation system.

The motion control of underwater spherical robot is a complicated process, which has the characteristics of high inertia and non-linearity. There are many influencing factors for the underwater spherical robot motion such as ambient temperature and water current, so it is difficult to obtain the real-time kinematic model. Therefore, it is hard for traditional PID to achieve stable motion control of the underwater spherical robot. In this paper, the actual motion control of underwater spherical robot was realized that used fuzzy PID control method. Compared with traditional PID for the underwater spherical robot, fuzzy PID has some advantages, such as good robustness and good dynamic performance. To demonstrate that the fuzzy PID was more suitable to our underwater spherical robot, we carried out some real time experiments. Comparison experimental results demonstrated that the fuzzy PID control method has better dynamic performance than the traditional PID.