Navigation methods for office delivery robots need to take various sources of uncertainty into account in order to get robust performance. In previous work, we developed a reliable navigation technique that uses parti...
详细信息
Navigation methods for office delivery robots need to take various sources of uncertainty into account in order to get robust performance. In previous work, we developed a reliable navigation technique that uses partially observable Markov models to represent metric, actuator, and sensor uncertainties. this paper describes an algorithm that adjusts the probabilities of the initial Markov model by passively observing the robot's interactions with its environment. the learned probabilities more accurately reflect the actual uncertainties in the environment, which ultimately leads to improved navigation performance. the algorithm, an extension of the Baum-Welch algorithm, learns without a teacher and addresses the issues of limited memory and the cost of collecting training data. Empirical results show that the algorithm learns good Markov models with a small amount of training data.
20 papers submitted to the internationalconference on Systems Analysis, Modelling and Simulation are presented. the papers are mainly devoted to the applications of the modelling, simulation and computer simulation m...
详细信息
20 papers submitted to the internationalconference on Systems Analysis, Modelling and Simulation are presented. the papers are mainly devoted to the applications of the modelling, simulation and computer simulation methods to the problems of control systems, controllability, control theory, cognitive systems, artificial intelligence, learning systems, brain models, neural networks, lubricants (including such biological materials as synovia), military electronic countermeasures, ore (mineral) treatment, cardiology, design, image analysis, biotechnology, chemostats, sensitivity analysis, robotics, automation. the mathematical models and techniques include statistical methods, integration, solving integral and differential equations, linear self-adjoint operators, iterative methods, discriminant analysis, algorithms, optimization.
For more than a decade, the productivity of knowledge workers has been going down. In addition, the knowledge work content of products and services is increasing;this is creating a productivity crisis. Knowledge worke...
详细信息
For more than a decade, the productivity of knowledge workers has been going down. In addition, the knowledge work content of products and services is increasing;this is creating a productivity crisis. Knowledge worker productivity can be increased by using better methods for defining, planning and controlling processes, not just production processes, but mainly Support processes where most knowledge workers are employed. the adoption of a process management culture is discussed, and highlighted in the context of two examples.
this paper describes the outline of the package which gives 'good' feasible schedules for production systems. Such schedules are produced by systematic search using the simulator incorporated in the package. I...
详细信息
ISBN:
(纸本)0780308913
this paper describes the outline of the package which gives 'good' feasible schedules for production systems. Such schedules are produced by systematic search using the simulator incorporated in the package. In the simulator, production systems are modeled by generalized Petri nets, and both forward and backward simulations can be carried out. these two alternatives offer us an earliest start schedule and a latest start schedule, respectively. As methods of making systematic search, a branch-and-bound method and heuristic methods using priority rules are incorporated at present, while the simulated annealing method and the genetic algorithm are left as future possibilities. It is assured by numerical experiments that the package can give reasonable solutions within reasonable computational time for several problems of comparatively small size.
A method is described for the recognition of partially occluded 2-D objects. this method considers a set of corners, parallel lines, and so on as typical features of an object. Possible candidate models are estimated ...
详细信息
A method is described for the recognition of partially occluded 2-D objects. this method considers a set of corners, parallel lines, and so on as typical features of an object. Possible candidate models are estimated from these features, and structural matching is performed between these models and features obtained from a picture by checking the combinations of various features. Even if the whole structure is not obtained due to a partial occlusion, the system can infer an object if some unique features of the object are obtained. Partial shapes and extracted lines are matched in detail with model candidates when they are limited to one or a few.< >
暂无评论