Earlier we introduced a novel framework for implementation of Adaptive Autonomy (AA). This study presents an expert system realization of the AA framework, referred to as Adaptive Autonomy Expert System (AAES). The pr...
详细信息
Color image histograms are very useful tools for content based image retrieval (CBIR) that can be applied on features such as colour, texture and shape. As these kinds of histograms results with large variations betwe...
详细信息
Color image histograms are very useful tools for content based image retrieval (CBIR) that can be applied on features such as colour, texture and shape. As these kinds of histograms results with large variations between neighbouring bins, they seem so sensitive to any kind of changes such as noise, illumination. To overcome this problem, in this paper, fuzzy linking histogram approach based on OWA aggregation operator is proposed, which is capable of projecting 3-dimensional (L*a*b*) colour histograms into single-dimension. The proposed method have been evaluated and compared with five other related methods in retrieving similar images from the common dataset which is available on http://***/~konkonst. The experimental results on 100 images within two categories of Cat and Sky reveals better performance of the proposed method in comparison with the other mentioned methods.
This research letter introduces a novel framework for the implementation of Adaptive Autonomy for intelligent Electronic Devices (TEDs). The study aims at achieving an optimum function allocation between IEDs and huma...
详细信息
Similarities between foot stability in single support phase of dynamic legged locomotion and dynamic grasp during nonprehensile carrying of an object on a palm are studied. Both foot stability and dynamic grasp condit...
详细信息
ISBN:
(纸本)9781424420575
Similarities between foot stability in single support phase of dynamic legged locomotion and dynamic grasp during nonprehensile carrying of an object on a palm are studied. Both foot stability and dynamic grasp conditions are driven mathematically. Then it is shown that these two conditions share the same basic dynamical concepts. It is also revealed that dynamic grasp and foot stability conditions have structurally the same equations when the palm -in object manipulation- and the ground -in legged locomotion- are horizontal. In this situation, parameters of the equations are very similar. It is demonstrated that the effects of violation of foot stability and dynamic grasp conditions are behaviorally the same. In addition to analytical discussions, some simulation examples in ADAMS are provided to validate the presented models and the results.
Automated terrain classification for electric powered wheelchairs (EPWs) has two primary motivations. First, certain terrains (e.g., sand and gravel) make wheelchair mobility more difficult. To alleviate this problem ...
详细信息
ISBN:
(纸本)9780889867406
Automated terrain classification for electric powered wheelchairs (EPWs) has two primary motivations. First, certain terrains (e.g., sand and gravel) make wheelchair mobility more difficult. To alleviate this problem the wheelchair control system can be manually tuned for maximum speeds and/or accelerations to help adapt to various terrains. Terrain classification can then be used to automate the switch from one control mode to another. Second, terrain classification can help yield a better understanding of the surfaces traversed by various groups of wheelchair users. This can provide the data needed to develop wheelchairs geared to specific groups of users. This paper presents an algorithm for vibration-based terrain classification on EPWs. This algorithm has been shown to be highly accurate in offline analysis of experimental data. Future work will stress online implementation and algorithm improvements.
This project incorporates modular robots as building blocks for furniture that moves and self-reconfigures. The reconfiguration is done using dynamic connection/disconnection of modules and rotations of the degrees of...
详细信息
ISBN:
(纸本)9781424420575
This project incorporates modular robots as building blocks for furniture that moves and self-reconfigures. The reconfiguration is done using dynamic connection/disconnection of modules and rotations of the degrees of freedom. This paper introduces a new approach to self-reconfiguration planning for modular robots based on the graph signature and the graph edit-distance. The method has been tested in simulation on two type of modules: YaMoR and M-TRAN. The simulation results shows interesting features of the approach, namely rapidly finding a near-optimal solution.
Learning in multi-agent environments where each agent's action directly affects other agents would be an important matter and a complicated task. To reduce the learning time and simplifying the learning process, i...
详细信息
ISBN:
(纸本)9781424412631;1424412633
Learning in multi-agent environments where each agent's action directly affects other agents would be an important matter and a complicated task. To reduce the learning time and simplifying the learning process, it is suitable to learn individual skills and then provide cooperation and coordination utilizing the learned individual skills. In the approach proposed in this paper, agents benefit from their individual knowledge obtained in the individual learning phase to cooperate with other agents. Cooperative object pushing system is used as a testbed to our proposed method where cooperation and coordination between agents are needed in these systems. Agents independently learn to push the object to the target by using the proposed fuzzy reinforcement learning method. Agents attain their cooperative behaviors properly making use of the coded knowledge in the Q-table. Simulation and experimental results show that by interpreting the knowledge in the Q-table, agents can achieve high level behaviors with a high degree of cooperation.
This paper presents the practical experience gained in the process of implementing the human-centered automation design methodology to an electric power utility management automation function, along with the analytica...
详细信息
This paper presents the practical experience gained in the process of implementing the human-centered automation design methodology to an electric power utility management automation function, along with the analytical discussions on the implementation challenges. This report of implementation challenges and the discussions made on the methods devised to conquer those challenges lead to an alternative approach to the original approach to the well-known human-centered automation design model in the literature.
Smart cooperation of human and computer agents should be harmonized by adapting the automation level of the cybernetic systems to the changing environmental and peripheral situations. This paper presents an adaptive a...
详细信息
Smart cooperation of human and computer agents should be harmonized by adapting the automation level of the cybernetic systems to the changing environmental and peripheral situations. This paper presents an adaptive autonomy methodology that is based on an extension of a well-known human-automation interaction model, as well as the expert judgment technique and the performance shaping factors concept. The method is implemented to a power distribution automation system, and the results are discussed through a scenario-based approach. Then, the performance of the proposed methodology and the effectiveness of adaptive autonomy are shown by the wide span of the changes in the resulting automation levels. The trends of the automation levels are investigated versus the criticality of the situations and the automation stages. The application-oriented matters are also discussed to stress on the context-based nature of the human-centered automation models.
作者:
Omid ShakerniaYi MaT. John KooShankar SastryDept. of Electrical Engineering & Computer Science
University of California at Berkeley Berkeley CA94720-1774 U.S.A. Tak-Kuen John Koo received the B.Eng. degree in 1992 in Electronic Engineering and the M.Phil. in 1994 in Information Engineering both from the Chinese University of Hong Kong. From 1994 to 1995
he was a graduate student in Signal and Image Processing Institute at the University of Southern California. He is currently a Ph.D. Candidate in Electrical Engineering and Computer Sciences at the University of California at Berkeley. His research interests include nonlinear control theory hybrid systems inertial navigation systems with applications to unmanned aerial vehicles. He received the Distinguished M.Phil. Thesis Award of the Faculty of Engineering The Chinese University of Hong Kong in 1994. He was a consultant of SRI International in 1998. Currently he is the team leader of the Berkeley AeRobot Team and a delegate of The Graduate Assembly University of California at Berkeley. He is a student member of IEEE and SIAM. S. Shankar Sastry received his Ph.D. degree in 1981 from the University of California
Berkeley. He was on the faculty of MIT from 1980-82 and Harvard University as a Gordon McKay professor in 1994. He is currently a Professor of Electrical Engineering and Computer Sciences and Bioengineering and Director of the Electronics Research Laboratory at Berkeley. He has held visiting appointments at the Australian National University Canberra the University of Rome Scuola Normale and University of Pisa the CNRS laboratory LAAS in Toulouse (poste rouge) and as a Vinton Hayes Visiting fellow at the Center for Intelligent Control Systems at MIT. His areas of research are nonlinear and adaptive control robotic telesurgery control of hybrid systems and biological motor control. He is a coauthor (with M. Bodson) of “Adaptive Control: Stability Convergence and Robustness Prentice Hall 1989.” and (with R. Murray and Z. Li) of “A Mathematical Introduction to Robotic Manipulati
In this paper, we use computer vision as a feedback sensor in a control loop for landing an unmanned air vehicle (UAV) on a landing pad. The vision problem we address here is then a special case of the classic ego-mot...
详细信息
In this paper, we use computer vision as a feedback sensor in a control loop for landing an unmanned air vehicle (UAV) on a landing pad. The vision problem we address here is then a special case of the classic ego-motion estimation problem since all feature points lie on a planar surface (the landing pad). We study together the discrete and differential versions of the ego-motion estimation, in order to obtain both position and velocity of the UAV relative to the landing pad. After briefly reviewing existing algorithm for the discrete case, we present, in a unified geometric framework, a new estimation scheme for solving the differential case. We further show how the obtained algorithms enable the vision sensor to be placed in the feedback loop as a state observer for landing control. These algorithms are linear, numerically robust, and computationally inexpensive hence suitable for real-time implementation. We present a thorough performance evaluation of the motion estimation algorithms under varying levels of image measurement noise, altitudes of the camera above the landing pad, and different camera motions relative to the landing pad. A landing controller is then designed for a full dynamic model of the UAV. Using geometric nonlinear control theory, the dynamics of the UAV are decoupled into an inner system and outer system. The proposed control scheme is then based on the differential flatness of the outer system. For the overall closed-loop system, conditions are provided under which exponential stability can be guaranteed. In the closed-loop system, the controller is tightly coupled with the vision based state estimation and the only auxiliary sensor are accelerometers for measuring acceleration of the UAV. Finally, we show through simulation results that the designed vision-in-the-loop controller generates stable landing maneuvers even for large levels of image measurement noise. Experiments on a real UAV will be presented in future work.
暂无评论