Artificial Intelligence in Engineering最新文献

New approaches for the development of shop floor control systems are needed to introduce better response to unanticipated disturbance situations and a better handling of ‘reconfiguration’ in production environments. In this paper, a development approach for agent-based shop floor control systems is presented, that uses co-ordination concepts as observable in insect colonies. In this scheme, agents operate within an information distribution environment, where information is made available in the form of ‘artificial pheromones’. Pheromone concepts from insect colonies and their mapping into a control system architecture are presented, a test bed implementation is discussed.

We present a concept of novel self-reconfigurable robotic system made of homogeneous autonomous robotic modules. Each robotic module has only two DOF, however a group of this module is able to change its connective configuration by changing their local connections. A cluster of the modules, thus can metamorphose into arbitrary configuration according to the surrounding environment or desired specification. Not only this ability of structural metamorphosis, the combined modules have functionality of robotic system which is capable of generating complicated motion.

Emergence of stable gaits in locomotion robots is studied in this paper. A classifier system, implementing an instance-based reinforcement-learning scheme, is used for the sensory-motor control of an eight-legged mobile robot and for the synthesis of the robot gaits. The robot does not have a priori knowledge of the environment and its own internal model. It is only assumed that the robot can acquire stable gaits by learning how to reach a goal area. During the learning process the control system is self-organized by reinforcement signals. Reaching the goal area defines a global reward. Forward motion gets a local reward, while stepping back and falling down get a local punishment. As learning progresses, the number of the action rules in the classifier systems is stabilized to a certain level, corresponding to the acquired gait patterns. Feasibility of the proposed self-organized system is tested under simulation and experiment. A minimal simulation model that does not require sophisticated computational schemes is constructed and used in simulations. The simulation data, evolved on the minimal model of the robot, is downloaded to the control system of the real robot. Overall, of 10 simulation data seven are successful in running the real robot.

The paper gives a concise overview of the present state of work in the project ‘Methodology of Emergent Synthesis’. Starting with the conceptual questions concerning analysis, synthesis and emergence in the realm of artifacts, a critical overview is given of reductionism and of the problems with self-referential character of the artifactual environment. The concepts of syntax and semantics are used to distinguish between different kinds of emergence. The pieces of ongoing research work in the project are exposed using a three-fold classification with respect to the completeness of our knowledge of the environment and the specification of the purpose of the artifact. The capabilities of the related techniques are also discussed.

This paper presents results of an ongoing interdisciplinary study to develop a computational theory of creativity for engineering design. Human design activities are surveyed, and popular computer-aided design methodologies are examined. It is argued that semiotics has the potential to merge and unite various design approaches into one fundamental theory that is naturally interpretable and so comprehensible in terms of computer use. Reviewing related work in philosophy, psychology, and cognitive science provides a general and encompassing vision of the creativity phenomenon. Basic notions of algebraic semiotics are given and explained in terms of design. This is to define a model of the design creative process, which is seen as a process of semiosis, where concepts and their attributes represented as signs organized into systems are evolved, blended, and analyzed, resulting in the development of new concepts. The model allows us to formally describe and investigate essential properties of the design process, namely its dynamics and non-determinism inherent in creative thinking. A stable pattern of creative thought — analogical and metaphorical reasoning — is specified to demonstrate the expressive power of the modeling approach; illustrative examples are given. The developed theory is applied to clarify the nature of emergence in design: it is shown that while emergent properties of a product may influence its creative value, emergence can simply be seen as a by-product of the creative process. Concluding remarks summarize the research, point to some unresolved issues, and outline directions for future work.

Recent, highly advanced artifact systems make it more complex and unpredictable to understand how they are used by human under a particular situation. Disastrous errors would occur when the methods of interactions deviate from what are expected at the design stage by the designer, who is different from the user. This paper presents a method by which human dynamic interactions with the externally provided tasks can be simulated. We concentrate on the resource-bounded human situation awareness, which is a complex phenomenon occurring at the interface between the human internal cognitive processes and the external environment. Finally, this is applied to the analysis of the high-tech aircraft accident that occurred in Columbia in 1995, which is a well-known accident caused by the discoordination between the human and the automated aircraft.

A new fuzzy controller for stabilizing series-type double inverted pendulum systems is proposed based on the SIRMs (Single Input Rule Modules) dynamically connected fuzzy inference model. The controller deals with six input items. Each input item is provided with a SIRM and a dynamic importance degree (DID). The SIRM and the DID are set up such that the angular control of the upper pendulum takes the highest priority order over the angular control of the lower pendulum and the position control of the cart when the relative angle of the upper pendulum is big. By using the SIRMs and the DIDs, the control priority orders are automatically adjusted according to control situations. Simulation results show that the controller stabilizes series-type double inverted pendulum systems of different parameter values in about 10.0 s for a wide range of the initial angles.

This paper presents an account of the design of a low-cost Internet-based teleoperation system implemented on China's Internet. Using a multimedia-rich human-computer interface, combining predictive displays and graphical overlays, a series of simple tasks were performed within a simulated space environment scenario. Internet clients anywhere can monitor the robotic workspace, talk with technicians, and control the Arm/Hand integrated system with 15 DOF located in lab to perform tasks (such as grasping a vessel, pouring a liquid, and peg-in-hole assembling, etc.). Our main contributions are to establish a foundation for teleoperated science and engineering research, and we have addressed some issues involving the time-delay associated with the Internet. We also developed several key software adaptation technologies and products used for Internet-Based teleoperation, compatible with the BH-III dexterous hand, BH1 6-DOF mechanical arm and five-finger 11-DOF data glove, constructed in our laboratory. This system has been successfully tested and applied in remote robotic education (Virtual Laboratories) system via China's Internet using our Master/Slave architecture, which combines mixed modes of remote monitor/manipulate and local autonomous control.

This research presents an application of the relatively new approach of ant colony optimization (ACO) to address a production-sequencing problem when two objectives are present — simulating the artificial intelligence agents of virtual ants to obtain desirable solutions to a manufacturing logistics problem. The two objectives are minimization of setups and optimization of stability of material usage rates. This type of problem is NP-hard, and therefore, attainment of IP/LP solutions, or solutions via complete enumeration is not a practical option. Because of such challenges, an approach is used here to obtain desirable solutions to this problem with a minimal computational effort. The solutions obtained via the ACO approach are compared against solutions obtained via other search heuristics, such as simulated annealing, tabu search, genetic algorithms and neural network approaches. Experimental results show that the ACO approach is competitive with these other approaches in terms of performance and CPU requirements.