International Journal of Advanced Robotic Systems
Volume 1 Number 4 December 2004 |
Learning to Automatically Detect Features for Mobile Robots Using Second-Order Hidden Markov Models, Page 231-244 Abstract: In this paper, we propose a new method based on Hidden Markov Models to interpret temporal sequences of sensor data from mobile robots to automatically detect features. Hidden Markov Models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (such as neural networks) are their ability to model noisy temporal signals of variable length. We show in this paper that this approach is well suited for interpretation of temporal sequences of mobile-robot sensor data. We present two distinct experiments and results: the first one in an indoor environment where a mobile robot learns to detect features like open doors or T-intersections, the second one in an outdoor environment where a different mobile robot has to identify situations like climbing a hill or crossing a rock.
A Dynamical Training and Design Simulator for Active Catheters, Page 245-250 Abstract: This work addresses the design of an active multi-link micro-catheter actuated by Shape Memory Alloy (SMA) micro actuators. This may be a response to one medical major demand on such devices, which will be useful for surgical explorations and interventions. In this paper, we focus on a training and design simulator dedicated to such catheters. This simulator is based on an original simulation platform (OpenMASK). The catheter is a robotic system, which is evaluated by a dynamical simulation addressing a navigation task in its environment. The design of the prototype and its mechanical model are presented. We develop an interaction model for contact. This model uses a real medical database for which distance cartography is proposed. Then we focus on an autonomous control model based on a multi-agent approach and including the behaviour description of the SMA actuators. Results of mechanical simulations including interaction with the ducts are presented. Furthermore, the interest of such a simulator is presented by applying virtual prototyping techniques for the design optimization. This optimization process is achieved by using genetic algorithms at different stages with respect to the specified task.
FDMS with Q-Learning: A Neuro-Fuzzy Approach to Partially Observable Markov Decision Problems, Page 251-262 Abstract: Finding optimal solutions to Partially Observable Markov Decision Problems is known to be NP-hard. This paper describes a novel neuro-fuzzy approach to obtain fast, robust and easily interpreted solutions by utilizing a combination of several learning techniques including neural networks, fuzzy decision making and Q-learning.
The Automated Threaded Fastening Based on On-line Identification, Page 263-272 Abstract: The principle of the thread fastenings have been known and used for decades with the purpose of joining one component to another. Threaded fastenings are popular because they permit easy disassembly for maintenance, repair, relocation and recycling. Screw insertions are typically carried out manually. It is a difficult problem to automat. As a result there is very little published research on automating threaded fastenings, and most research on automated assembly focus on the peg-in-hole assembly problem. This paper investigates the problem of automated monitoring of the screw insertion process. The monitoring problem deals with predicting integrity of a threaded insertion, based on the torque vs. insertion depth curve generated during the insertions. The authors have developed an analytical model to predict the torque signature signals during self-tapping screw insertions. However, the model requires parameters on the screw dimensions and plate material properties are difficult to measure. This paper presents a study on on-line identification during screw fastenings. An identification methodology for two unknown parameter estimation during a self-tapping screw insertion process is presented. It is shown that friction and screw properties required by the model can be reliably estimated on-line. Experimental results are presented to validate the identification procedure.
Research on a Novel Parallel Engraving Machine and its Key Technologies, Page 273-286 Abstract: In order to compensate the disadvantages of conventional engraving machine and exert the advantages of parallel mechanism, a novel parallel engraving machine is presented and some key technologies are studied in this paper. Mechanism performances are analyzed in terms of the first and the second order influence coefficient matrix firstly. So the sizes of mechanism, which are better for all the performance indices of both kinematics and dynamics, can be confirmed and the restriction due to considering only the first order influence coefficient matrix in the past is broken through. Therefore, the theory basis for designing the mechanism size of novel engraving machine with better performances is provided. In addition, method for tool path planning and control technology for engraving force is also studied in the paper. The proposed algorithm for tool path planning on curved surface can be applied to arbitrary spacial curved surface in theory, control technology for engraving force based on fuzzy neural network(FNN) has well adaptability to the changing environment. Research on teleoperation for parallel engraving machine based on B/S architecture resolves the key problems such as control mode, sharing mechanism for multiuser, real-time control for engraving job and real-time transmission for video information. Simulation results further show the feasibility and validity of the proposed methods.
Recursive Backstepping Stabilization of a Wheeled Mobile Robot, Page 287-294 Abstract: This research is aimed to the development of a dynamic control to enhance the performance of the existing dynamic controllers for mobile robots. System dynamics of the car-like robot with nonholonomic constraints were employed. A Backstepping approach for the design of discontinuous state feedback controller is used for the design of the controller. It is shown that the origin of the closed loop system can be made stable in the sense of Lyapunov. The control design is made on the basis of a suitable Lyapunov function candidate. The effectiveness of the proposed approach is tested through simulation on a car-like vehicle mobile robot.
Exploring Open-Ended Design Space of Mechatronic Systems, Page 295-302 Abstract: To realize design automation of mechatronic systems, there are two major issues to be dealt with: open-topology generation of mechatronic systems and simulation or analysis of those models. For the first issue, we exploit the strong topology exploration capability of genetic programming to create and evolve structures representing mechatronic systems. With the use of ERCs (ephemeral random constants) in genetic programming, we can evolve the sizing of mechatronic system components together with the system structures simultaneously. The second issue, simulation and analysis of those system models, is made more complex when the systems are mixed-energy-domain systems. We take advantage of bond graphs as a tool for multi- or mixed-domain modeling and simulation of mechatronic systems. Because there are many considerations in mechatronic system design that are not completely captured by a bond graph, it is beneficial to generate multiple solutions, allowing the designer more latitude in choosing a model to implement. The approach in this paper is capable of providing a variety of design choices to the designer for further analysis, comparison and trade-off study. The approach is shown to be efficient and effective and is demonstrated in an example of open-ended real-world mechatronic system design application, a typewriter re-design problem.
|
ARS Web 2004 |