Mehmet Serdar Guzel

Optical flow based system design for mobile robots

This paper presents a new optical flow based navigation strategy, based on a multi-scale variational approach, for mobile robot navigation using a single Internet based camera as a primary sensor. Real experiments to guide a Pioneer 3-DX mobile robot in a cluttered environment are presented, and the analysis of the results allow us to validate the proposed behavior based navigation strategy Main contributions of this approach is that it proposes an alternative high performance navigation algorithm for the systems, consuming high computation time for image acquisition

A Behaviour-Based Architecture for Mapless Navigation Using Vision

Autonomous robots operating in an unknown and uncertain environment must be able to cope with dynamic changes to that environment. For a mobile robot in a cluttered environment to navigate successfully to a goal while avoiding obstacles is a challenging problem. This paper presents a new behaviour-based architecture design for mapless navigation. The architecture is composed of several modules and each module generates behaviours. A novel method, inspired from a visual homing strategy, is adapted to a monocular vision-based system to overcome goal-based navigation problems. A neural network-based obstacle avoidance strategy is designed using a 2-D scanning laser. To evaluate the performance of the proposed architecture, the system has been tested using Microsoft Robotics Studio (MRS), which is a very powerful 3D simulation environment. In addition, real experiments to guide a Pioneer 3-DX mobile robot, equipped with a pan-tilt-zoom camera in a cluttered environment are presented. The analysis of the resul...

Vision Based Obstacle Avoidance Techniques

Vision is one of the most powerful and popular sensing method used for autonomous navigation. Compared with other on-board sensing techniques, vision based approaches to navigation continue to demand a lot of attention from the mobile robot research community. This is largely due to its ability to provide detailed information about the environment, which may not be available using combinations of other types of sensors. One of the key research problems in mobile robot navigation is the focus on obstacle avoidance methods. In order to cope this problem, most autonomous navigation systems rely on range data for obstacle detection. Ultrasonic sensors, laser rangefinders and stereo vision techniques are widely used for estimating the range data. However all of these have drawbacks. Ultrasonic sensors suffer from poor angular resolution. Laser range finders and stereo vision systems are quite expensive, and computational complexity of the stereo vision systems is another key challenge (Saitoh et al., 2009). In addition to their individual shortcomings, Range sensors are also unable to distinguish between different types of ground surfaces, such as they are not capable of differentiating between the sidewalk pavement and adjacent flat grassy areas. The computational complexity of the avoidance algorithms and the cost of the sensors are the most critical aspects for real time applications. Monocular vision based systems avoid these problems and are able to provide appropriate solution to the obstacle avoidance problem. There are two fundamental groups of vision based obstacle avoidance techniques; those that compute the apparent motion, and those that rely on the appearance of individual pixels for monocular vision based obstacle avoidance systems. First group is called as Optical flow based techniques, and the main idea behind this technique is to control the robot using optical flow, from which heading of the observer and time-to-contact values are obtained (Guzel & Bicker, 2010). One way of the control using these values is by acting to achieve a certain type of flow. For instance, to maintain ambient orientation, the type of Optic flow required is no flow at all. If some flow is detected, then the robot should change the forces produced by its effectors so as to minimize this flow, based on Law of Control (Contreras, 2007). A second group is called Appearance Based methods rely on basic image processing techniques, and consist of detecting pixels different in appearance than that of the ground and classifying them as obstacles. The algorithm performs in real-time, provides a highresolution obstacle image, and operates in a variety of environments (DeSouza & Kak, 2002). The main advantages of these two conventional methods are their ease of implementation and high availability for real time applications. However optical flow based methods suffer from two major problems, which are the illumination problem that varies with time and the

A Collective Behaviour Framework for Multi-agent Systems

This paper addresses a novel framework that employs a decentralized strategy for collective behaviours of multi-agent systems. The framework proposes a new aggregation behaviour that focusses on letting agents on the swarm agree on attending a group and allocating a leader for each group. As the leader starts moving towards a specific goal in a particularly cluttered environment, other members are enabled to move while keeping themselves coordinated with the leader and the centre of gravity of the group.

Autonomous Vehicle Navigation Using Vision and Mapless Strategies: A Survey

This survey addresses the existing state of knowledge related to vision-based mobile robots, especially including their background and history, current trends, and mapless navigation. This paper not only discusses studies relevant to vision-based mobile robot systems but also critically evaluates the methodologies which have been developed and that directly affect such systems.This survey addresses the existing state of knowledge related to vision-based mobile robots, especially including their background and history, current trends, and mapless navigation. This paper not only discusses studies relevant to vision-based mobile robot systems but also critically evaluates the methodologies which have been developed and that directly affect such systems.

An adaptive framework for mobile robot navigation

Collective behaviours observed in nature bring new methodologies in proposing control algorithms for robot groups to perform a variety of complex tasks. In this article, an adaptive algorithm, allowing the safe navigation of a group of robots in a collective manner, is proposed. The algorithm, inspired from the adaptive particle swarm optimization technique, proposes an efficient control approach to overcome both static and moving obstacles. Accordingly, compared to the conventional particle swarm optimization algorithm, the proposed system allows a robot or group of robots (swarm) to complete the goal while avoiding static and moving obstacles as well as dynamic targets in a safe and collective manner. The simulation results verify the overall performance and reliability of the proposed system.

Machine vision and fuzzy logic-based navigation control of a goal-oriented mobile robot

This work addresses a new goal oriented navigation framework for autonomous system. In the proposed work, a hybrid control system, comprising deliberative and behavior-based architectures, has been developed. Deliberative layer employs a monocular vision camera to obtain the position of the goal while behavior-based framework makes use of the motor schema technique for safe navigation. Fuzzy logic is also adopted in order to enhance the performance of the navigation system. A rigorous series of experiments has been conducted using two navigation methods, which are the proposed control system and the conventional navigation technique utilizing the potential field method for achieving the desired goals. Both systems are implemented in the simulated experiments using Stage simulator. By employing these two approaches, it is possible to present a comparison of the navigation results between the systems utilizing different navigation techniques. The experimental results reveal that the proposed system produces better navigation performance compared to the conventional method in terms of safe and successful navigation, with a smoother trajectory and consistent motion.

A robotic software for intelligent applications

Abstract This study addresses the development of a novel intelligent robotic software system which can control a low-cost five DOF robotic arm and allows the robot to be able to play Tic-Tac-Toe, a simple board game. The paper first aims to introduce proposed software and then details the application developed, including image processing, and decision making steps.

A Hybrid Architecture for Vision-Based Obstacle Avoidance

This paper proposes a new obstacle avoidance method using a single monocular vision camera as the only sensor which is called as Hybrid Architecture. This architecture integrates a high performance appearance-based obstacle detection method into an optical flow-based navigation system. The hybrid architecture was designed and implemented to run both methods simultaneously and is able to combine the results of each method using a novel arbitration mechanism. The proposed strategy successfully fused two different vision-based obstacle avoidance methods using this arbitration mechanism in order to permit a safer obstacle avoidance system. Accordingly, to establish the adequacy of the design of the obstacle avoidance system, a series of experiments were conducted. The results demonstrate the characteristics of the proposed architecture, and the results prove that its performance is somewhat better than the conventional optical flow-based architecture. Especially, the robot employing Hybrid Architecture avoids lateral obstacles in a more smooth and robust manner than when using the conventional optical flow-based technique.

A New Generalized Deep Learning Framework Combining Sparse Autoencoder and Taguchi Method for Novel Data Classification and Processing

Deep autoencoder neural networks have been widely used in several image classification and recognition problems, including hand-writing recognition, medical imaging, and face recognition. The overall performance of deep autoencoder neural networks mainly depends on the number of parameters used, structure of neural networks, and the compatibility of the transfer functions. However, an inappropriate structure design can cause a reduction in the performance of deep autoencoder neural networks. A novel framework, which primarily integrates the Taguchi Method to a deep autoencoder based system without considering to modify the overall structure of the network, is presented. Several experiments are performed using various data sets from different fields, i.e., network security and medicine. The results show that the proposed method is more robust than some of the well-known methods in the literature as most of the time our method performed better. Therefore, the results are quite encouraging and verified the overall performance of the proposed framework.