By Topic

Automation, Robotics and Applications (ICARA), 2011 5th International Conference on

Date 6-8 Dec. 2011

Filter Results

Displaying Results 1 - 25 of 80
  • [Front matter]

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | PDF file iconPDF (81 KB)  
    Freely Available from IEEE
  • Mobile robots in the engineering education setting

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (646 KB) |  | HTML iconHTML  

    Demand for engineering graduates is steadily growing around the world. Attracting more students into engineering has become a task of an emerging importance. Mobile robotics is an excellent tool to fascinate young boys and girls while drawing their interests to such fields as mechanical, electrical, electronic, control and computer engineering. It also allows keeping and further developing this interest during the years of study. This paper presents low- to medium-complexity autonomous mobile robots that could be directly employed at school and university levels to introduce to engineering or be used as platforms for further development by the students. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A distributed multi-UAV path planning approach for 3D environments

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1254 KB) |  | HTML iconHTML  

    During rescue scenarios it is indispensable to obtain an overview of the situation. Unmanned aerial vehicles (UAVs) can gather the necessary information in a fast and efficient way. This paper presents an approach for path planning in 3D environments offering a solution to explore disaster areas including, e. g., partially or completely destroyed buildings. Using multiple UAVs decreases the time needed to receive a complete overview if the problem of coordination and task allocation is solved. We present an approach for the use of multiple UAVs. The UAVs work in a distributed manner without any central coordination instance and cover the exploration of terrains as well as goal-oriented path planning. When using multiple UAVs redundant exploration is avoided through the use of inter-UAV-communication. The approach is based on potential fields and uses the simplicity of the gradient method to calculate paths for fast exploration of the terrain. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-free linear quadratic tracking control for unmanned helicopters using reinforcement learning

    Page(s): 19 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (359 KB) |  | HTML iconHTML  

    This paper addresses the autonomous flight control system of an unmanned helicopter. We adopt a model-free discrete linear quadratic tracking (LQT) control architecture based on reinforcement learning algorithm by rewriting the Q-learning approach. From input and output data, the linear quadratic optimal gain is directly found without system identification procedure. Least square method is adopted in order to estimate the Q-value and the parameters related to optimal control gain. This methodology does not access to an exact model of the system and can be applied to full flight envelop maneuvering from hovering to aggressive flight with small modification. We constructed numerical simulations to evaluate the proposed algorithm with a discrete linear model of the unmanned helicopter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Omnidirectional bearing-only see-and-avoid for small aerial robots

    Page(s): 23 - 28
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1980 KB) |  | HTML iconHTML  

    Motivated by the growing interest in unmanned aerial system's applications in indoor and outdoor settings and the standardisation of visual sensors as vehicle payload. This work presents a collision avoidance approach based on omnidirectional cameras that does not require the estimation of range between two platforms to resolve a collision encounter. It will achieve a minimum separation between the two vehicles involved by maximising the view-angle given by the omnidirectional sensor. Only visual information is used to achieve avoidance under a bearing-only visual servoing approach. We provide theoretical problem formulation, as well as results from real flight using small quadrotors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced process automation using automation agents

    Page(s): 34 - 39
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (775 KB) |  | HTML iconHTML  

    Current process automation solutions have a limited capability concerning agile adaptation in a dynamic environment as well as in the case of unexpected internal and external disturbances. Distributed intelligent control systems based on agent technologies are seen as a promising approach to handle the dynamics in large complex systems. In this paper, we present a multi-agent system architecture capable to answer to the major requirements in the process domain. The architecture is based on agents with diverse responsibilities and tasks and additionally separates the control software of agents controlling hardware components into two levels, the high level control and the low level control. Our system architecture has also the ability to flexibly reschedule allocated jobs in the case of resource breakdowns in order to minimize downtimes and resulting costs. The system is currently tested and evaluated in the Odo Struger Laboratory at the Automation and Control Institute. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Concept of Cellular Transport Systems in facility logistics

    Page(s): 40 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (972 KB) |  | HTML iconHTML  

    The proposed concept of a Cellular Transport System shows the possibilities to increase the flexibility and changeability of facility logistics systems and enhances the ease of use of complex decentralized control systems. This contribution shows how to enhance these issues compared to conventional facility logistics systems, e.g. static conveyors, by using an autonomous vehicle swarm. Cellular Transport Systems are based on dedicated (cellular) material handling entities. Generally, these cells consist of autonomous transport vehicles (ATVs) or autonomous conveying modules. Various functions such as advanced sensor/actuator interoperation, highly reliable communication, localization and energy management are implemented in each of this cells, facilitating different forms of adaptive, anticipatory and collective behavior. Furthermore, Swarm Intelligence enables the creation of a collective that interacts and cooperates amongst each other in order to solve complex tasks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of Smart Floor for multi-robot system

    Page(s): 46 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1130 KB) |  | HTML iconHTML  

    In this paper, we suggest a new information space concept called Smart Floor. Smart Floor is the floor storage of specific information intended for route guidance of a mobile robot. A mobile robot can reach its goal position using the information in Smart Floor as well as automatically update information for a changing environment. We constructed Smart Floor using RFID tag packaging and fabricated a mobile robot mounted with a passive RFID tag in ultra high frequency (UHF) bandwidth. The passive RFID tag is inexpensive and does not require a power supply. The primary information saved and stored in Smart Floor is direction-values and Q-values. These values are the result of applying Q-learning in an arbitrary position to the goal position in the Grid world. The research will help from Smart Floor and aid in the development of various applications for multi-robot application. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge driven mobile robots applied in the disassembly domain

    Page(s): 52 - 56
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1866 KB) |  | HTML iconHTML  

    Mobile robots can be used as a motivating and interesting tool to perform laboratory experiments within the context of mechatronics, microelectronics and control. Considering the disassembly as a vital and prospective industry domain, we use the mobile robots to automate the disassembly process. In our system, each mobile robot has particular skills and is supervised by an agent with related objectives and knowledge. An agent has an ontology-based world model, which is responsible to maintain the knowledge about the robot's activities in relation to its environment as well as to its underlying software parts. The ontology is used to represent a specification of an agent's domain knowledge. The system functionality is tested with three mobile robots having a task to disassembly a particular Lego construct. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Test case generation approach for industrial automation systems

    Page(s): 57 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (704 KB) |  | HTML iconHTML  

    The need for increasing flexibility of industrial automation system products leads to the trend to shift functional behavior from hardware solutions to software components. This trend causes an increasing complexity of software components and the need for comprehensive and automated testing approaches to ensure a requested quality level. Nevertheless, a key task in software testing is to identify appropriate test cases typically requiring high effort for test case generation and rework effort for adapting test cases in case of requirements changes. Semi-automated derivation of test cases based on models, like UML, can support test case generation. In this paper we introduce an automated test case generation approach for industrial automation applications which are specified by UML state chart diagrams. In addition we present a prototype application of the presented approach for a sorting machine. Major results showed that state charts (a) can support efficient test case generation and (b) enable automated code generation of test cases and code for the industrial automation domain. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A closed-loop crash warning system based on heterogeneous cues

    Page(s): 63 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (847 KB) |  | HTML iconHTML  

    The area of human machine interaction has been immersed into transportation research for many years and has embraced in intelligent transportation systems for the development of next-generation active safety systems in recent years. It has long been identified that the driver distraction plays a major role in traffic accidents and application of imaging technologies to detect and predict such critical situations has become attractive. This paper presents a closed-loop image based solution to detect critical driver behaviors and produce warning signals when safety critical situations arise. The system tracks driver upper body, eye movements and external objects using multiple cameras in a vehicle to determine the driving risk. Current implementation detects three risky driving behaviors, namely, texting, drinking and reach to grab objects while driving, and combines them with gaze movement to determine the crash severity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Action annotated trajectory generation for autonomous maneuvers on structured road networks

    Page(s): 67 - 72
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3650 KB) |  | HTML iconHTML  

    This paper presents a simple path-planning method with low computational cost for autonomous vehicles driving on structured road networks. Characteristics of the road structure are exploited for efficient planning and evaluation. Instead of using a global state machine, necessary actions for maneuvers are generated online and are annotated into the trajectory itself. The method has been tested with our vehicle “MadeInGermany” over several thousand kilometers driving autonomously in urban city scenarios and highway tracks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic model of autonomous ground vehicle for the path planning module

    Page(s): 73 - 77
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (471 KB) |  | HTML iconHTML  

    This paper discusses the importance of kinematic and dynamic constraints in a path planning module. The kinematic and dynamic models are taken into account to model the actual mobile robot including the torques provided by the motors and the restriction to the robot mobility induced by the constraints. The dynamic model of the mobile robot is simulated and compared with the behaviour of a real Pioneer 3DX mobile robot. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimized route network graph as map reference for autonomous cars operating on German autobahn

    Page(s): 78 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (780 KB) |  | HTML iconHTML  

    This paper describes several optimization techniques used to create an adequate route network graph for autonomous cars as a map reference for driving on German autobahn or similar highway tracks. We have taken the Route Network Definition File Format (RNDF) specified by DARPA and identified multiple flaws of the RNDF for creating digital maps for autonomous vehicles. Thus, we introduce various enhancements to it to form a digital map graph called RND-FGraph, which is well suited to map almost any urban transportation infrastructure. We will also outline and show results of fast optimizations to reduce the graph size. The RNDFGraph has been used for path-planning and trajectory evaluation by the behavior module of our two autonomous cars “Spirit of Berlin” and “MadeInGermany”. We have especially tuned the graph to map structured high speed environments such as autobahns where we have tested autonomously hundreds of kilometers under real traffic conditions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Voice command interpretation for robot control

    Page(s): 90 - 95
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (505 KB) |  | HTML iconHTML  

    This paper presents some initial results from an analysis of performance of a voice command interpretation and authorisation system using voiceprint to identify the human-commander. Two approaches based on human voice related algorithms are proposed. Mel-frequency cepstral coefficient (MFCC) and perceptual linear predictive (PLP) are two feature extraction methods that are closely mimic the human auditory system. The two methods were applied to the proposed system to determine their suitability for use in a commander recognition system. Vector Quantization (VQ) with Linde-Buzo-Gray (LBG) iterative algorithm was used for clustering for the classification of commanders. The performance of the algorithms was evaluated to compare between two methods in MATLAB simulation environment based on, false rejection rate (rejecting an authorised commander), false acceptance rate (accepting unauthorised commander) and the execution time. Based on the initial results, both methods achieved accurate classification and PLP method has shown better execution time and lower false-acceptance rate compared to the MFCC. The combined approach (MFCC-PLP) did not show considerable improved performances to the individual feature models PLP and MFCC without incurring high computational costs that will compromise the performance of the speaker recognition tasks. Therefore, PLP method is the best candidate for command-recognition system to be developed in the second phase of this research. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • American Sign Language recognition system for hearing impaired people using Cartesian Genetic Programming

    Page(s): 96 - 99
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (423 KB) |  | HTML iconHTML  

    American Sign Language (ASL) is a well developed and standard way of communication for hearing impaired people living in English speaking communities. Since the advent of modern technology, different intelligent computer-aided applications have been developed that can recognize hand gestures and hence translate gestures into understandable forms. In this paper, ASL based hand gesture recognition system is presented that uses evolutionary programming technique called Cartesian Genetic Programming (CGP). Hand gesture images representing different English alphabets are used to train the CGP based system and then it is tested for a different set of images. The sign recognition accuracy obtained is around 90%. Also, a chat application is proposed with a possible solution to boost the accuracy of the recognition up to 100%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gesture recognition using Microsoft Kinect®

    Page(s): 100 - 103
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (861 KB) |  | HTML iconHTML  

    Gesture recognition is essential for human - machine interaction. In this paper we propose a method to recognize human gestures using a Kinect® depth camera. The camera views the subject in the front plane and generates a depth image of the subject in the plane towards the camera. This depth image is then used for background removal, followed by generation of the depth profile of the subject. In addition to this, the difference between subsequent frames gives the motion profile of the subject and is used for recognition of gestures. These allow the efficient use of depth camera to successfully recognize multiple human gestures. The result of a case study involving 8 gestures is shown. The system was trained using a multi class Support Vector Machine. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling of Human Upper Body for Sign Language Recognition

    Page(s): 104 - 108
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (390 KB) |  | HTML iconHTML  

    Sign Language Recognition systems require not only the hand motion trajectory to be classified but also facial features, Human Upper Body (HUB) and hand position with respect to other HUB parts. Head, face, forehead, shoulders and chest are very crucial parts that can carry a lot of positioning information of hand gestures in gesture classification. In this paper as the main contribution, a fast and robust search algorithm for HUB parts based on head size has been introduced for real time implementations. Scaling the extracted parts during body orientation was attained using partial estimation of face size. Tracking the extracted parts for front and side view was achieved using CAMSHIFT [24]. The outcome of the system makes it applicable for real-time applications such as Sign Languages Recognition (SLR) systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Delayed absolute difference (DAD) signatures of dynamic features for sign language segmentation

    Page(s): 109 - 114
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (600 KB) |  | HTML iconHTML  

    In sign language segmentation, individual gestures are extracted out of a continuous stream and then matched with models for recognition. We have hypothesized an improvement in word segmentation without affecting the language naturalness by incorporating a novel set of segmentation features (pause, repetition and directional variations). To analyze these segmentation features, a unified tool (DAD signature) is presented that encodes the segmentation features in form of distinct patterns. It is shown that the DAD signature can easily detect the pauses, repetitions and reversal of direction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical control scheme for coordinated motion of mobile manipulators

    Page(s): 115 - 120
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (691 KB) |  | HTML iconHTML  

    Mobile manipulators are becoming more widespread, with growing commercial and scientific interest in their use. The addition of a mobile base to a manipulator greatly extends the workspace of the manipulator, but introduces complex control problems involving coordination of base and manipulator motion while simultaneously ensuring platform stability and good manipulability during task execution. This paper describes a hierarchical control scheme for a mobile manipulator designed to maintain manipulability and stability performance metrics within specified thresholds during the execution of manipulation tasks. We demonstrate the effectiveness of our control scheme by applying it to control of a simulated nonholonomic base with a 6 degree-of-freedom manipulator. Our simulation results show that the controller successfully completes a manipulation task involving multiple end-effector targets, and maintains stability and manipulability to the desired thresholds throughout. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Characterisation of a motor driver with over-current protection and speed feedback

    Page(s): 127 - 132
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (818 KB) |  | HTML iconHTML  

    Urban search and rescue robots are becoming more prolific and widely used. However, these robots are still being developed for specific environments and situations. The research being undertaken at Massey University is part of a larger collaboration to produce a multi-tiered robotic system for urban search and rescue. The first major hurdle of a mobile robotic system is mobility. While this research will ignore the difficulty of hazardous terrain, stable and controllable maneuverability is still required. To achieve this, a motor controller system has been designed and developed. Each controller will control a wheel of the robot and maintain a speed determined by a central computer. The motor controller requires the ability to control the motor speed and check that the current drawn is not too high as to damage the motors or other hardware. This paper outlines the structure of this motor controller system as well as the testing undertaken to determine the PID constant for the control loop. The testing has resulted in a set of PID constants that control the system, within pre-defined metrics, very effectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vertical motion simulation and analysis of USM underwater glider

    Page(s): 139 - 144
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (997 KB) |  | HTML iconHTML  

    This paper describes the mathematical model and analysis of motion in a vertical plane for USM underwater glider. The underwater glider is a highly efficient autonomous underwater vehicle which glides through the ocean water column in saw-tooth pattern. It uses buoyancy for propulsion by controlling ballast pump and internal moving mass. In this research work, we have designed the mathematical model and studied the motion characteristics of USM underwater glider. The simulation was programmed using Matlab and the results demonstrate the downward motion of USM underwater glider based on the longitudinal model for two different glide angles. The results show the position of glider, linear and angular velocities of the glider, angle of attack, position of internal moving mass and ballast rate. With the resulting glider behavior in this open-loop control output, we will extend the control approach in order to create an efficient biologically inspired control algorithm for an optimized USM underwater glider. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A visual AGV-urban car using Fuzzy control

    Page(s): 145 - 150
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1682 KB) |  | HTML iconHTML  

    The goal of the work described in this paper is to develop a visual line guided system for being used on-board an Autonomous Guided Vehicle (AGV) commercial car, controlling the steering and using just the visual information of a line painted below the car. In order to implement the control of the vehicle, a Fuzzy Logic controller has been implemented, that has to be robust against curvature changes and velocity changes. The only input information for the controller is the visual distance from the image center captured by a camera pointing downwards to the guiding line on the road, at a commercial frequency of 30Hz. The good performance of the controller has successfully been demonstrated in a real environment at urban velocities. The presented results demonstrate the capability of the Fuzzy controller to follow a circuit in urban environments without previous information about the path or any other information from additional sensors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive control of two wheel inverted pendulum robot based on particle swarm optimization

    Page(s): 151 - 156
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1044 KB) |  | HTML iconHTML  

    Research on two wheel inverted pendulum (TWIP) robot become an interest of many researcher due to its highly nonlinearity characteristic. TWIP offers extensive research diversity from modeling to control method. In control engineering, tuning of TWIP, which is a linear time invariant (LTI) system, has been well studied. In contrast, this paper emphasizes on time variant system of TWIP. Particle swarm optimization (PSO) is employed for adaptive tuning of the TWIP. To avoid instable problem due to wide search space area used, integral absolute error (IAE) mesh is considered, which is important to ensure that the region where TWIP operates is stable and optimal. Simulation result shows the effectiveness of the proposed approach in enabling online PSO tuning scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic feature extraction and image classification using genetic programming

    Page(s): 157 - 162
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (638 KB) |  | HTML iconHTML  

    In this paper, we propose a multilayer domain-independent GP-based approach to feature extraction and image classification. We propose two different structures for the system and compare the results with a baseline approach in which domain-specific pre-extracted features are used for classification. In the baseline approach, human/domain expert intervention is required to perform the task of feature extraction. The proposed approach, however, extracts (evolves) features and generates classifiers all automatically in one loop. The experiments are conducted on four image data sets. The results show that the proposed approach can achieve better performance compared to the baseline while removing the human from the loop. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.