There is growing international interest in a global exploration of the surface of Mars, more distant planets, and planetary moons. Mobile robots are of high interest for unmanned planetary exploration. During the last decade, there has been significant progress toward a supervised autonomous robotic capability for remotely controlled scientific exploration of planetary surfaces. Planetary Micro-Rovers such as Micro-RoSA-2 Mars Rover were designed for autonomous exploration mission in space. The European Space Agency (ESA) also started to develop concepts for micro-rovers for Mars missions. The mission is characterized by limited tele-operation, limited knowledge of the planetary terrain, challenges in obstacle detection and avoidance and hazard detection. Therefore, it requires an accurate obstacle detection and avoidance system which is one of the most critical factors in the design of autonomous vehicles used in such planetary missions. Numerous methods for obstacle avoidance and detection behaviors have been suggested and research in this area of robotics is conducted extensively. Fixed mounting of sonar sensors, rotating sonar sensor, laser scanner and vision based systems are the primary sensors that can be used for the obstacle detection and avoidance behaviors of the mobile robots. With the rapidly improvement of computer technology, Visual-based sensors gain an intense popularity and consequently have been begun to be utilized in so many robotic researches. Among the various applications in robotics, one of the most popular concepts is gathering information from the navigation environments for mobile robots by working on optical flow of vision which is derived from a stereo camera located on the robots. We can determine the optical flow the movement of the objects within the area of robotic vision. If a relative motion in the environment, whether from objects or mobile robot, is present, then the information that can be gathered from this environment is enough for the mobile robot to execute its obstacle detection and avoidance behaviors. Optical flow can be roughly defined as the apparent motion of features in a sequence of images. During navigation, the robot movement is perceived as a relative motion of the field of view, and, in consequence, it gives the impression that static objects and features move respect to the robot. To extract optical flow from a video stream, the direction and magnitude of translational or rotational scene feature movement must be computed at every pair of consecutive camera frames. Optical flow between two consecutive frames is usually represented by a vector for every pixel, where its norm depends on the motion speed and its direction represents the movement of the corresponding pixel in consecutive images. But as the latest researches and techniques have come to view, new practical methods were put forward. In this study, by making use of optical flow calculation and multi layer perceptron Artificial Neural Network, A methodology has been tried to be put forward for mobile robot obstacle detection and avoidance behavior. The study of methodology has been supported by experimental results that were obtained from Matlab simulation environments. The images of the views were taken from the real navigation environment and then optical flow calculations for all images were obtained via matlab simulink blocks that were created in advance, as an algorithm which can calculate optical flows from stereo visions. As optical flows of each pair of stereo views were derived, a data base was constituted in order to train the multi layer perceptron. By the help of data set and Levenberg-Marquardt learning algorithm, a neural network which was well trained in Matlab environment in order to detect the presence of obstacles was created. Experimental results, obtained during the study have strengthened the ideas which have supported the usage of the Optical Flow via Artificial Neural Network in mobile robotics for obstacle detection and avoidance behaviors.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optical flow-based obstacle detection and avoidance behaviors for mobile robots used in unmanned planetary exploration


    Contributors:
    Dur, E. (author)


    Publication date :

    2009


    Size :

    10 Seiten, 14 Quellen




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English





    Mobile Robots with Dynamic Obstacle Avoidance

    Ali, Maram / Das, Saptarshi | IEEE | 2023


    Mobile robots for planetary exploration

    Schilling, K. / Jungius, C. | Tema Archive | 1996


    Unmanned aircraft obstacle avoidance

    SCHULTZ STEPHEN L / MONACO JOHN | European Patent Office | 2019

    Free access

    UNMANNED AIRCRAFT OBSTACLE AVOIDANCE

    SCHULTZ STEPHEN L / MONACO JOHN | European Patent Office | 2018

    Free access