L. M. Camarinha-Matos, L. Seabra Lopes, and J. Barata. Execution monitoring in assembly with learning capabilities. In Proceedings of the IEEE International Conference on Robotics and Automation, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....is its horizontal organization. Determining explanations for detected execution failures can become very complex when errors are propagated. The proposed approach to modeling errors in terms of taxonomic and causal links aims at handling this complexity. Further information can be found in [2, 32, 8], with [6] describing the basic learning machinery. Transportation and Navigation In addition to actual manufacturing tasks occuring in a factory, transportation of both raw material and fabricated workpieces is an important issue. Driver less transport systems are designed to handle these ....

L. M. Camarinha-Matos, L. Seabra Lopes, and J. Barata. Execution monitoring in assembly with learning capabilities. In Proceedings of the IEEE International Conference on Robotics and Automation, 1994.

....Seabra Lopes, L. 1991) Sistema Integrado de Indu o, Technical Report GR RT SD 7 91, U. N. de Lisboa. Seabra Lopes, L. L.M. Camarinha Matos (1993) Learning in Assembly Task Execution, Proc. of the II European Workshop on Learning Robots , Turin, Italiy, 1993, pp. 129 142. Seabra Lopes, L. Camarinha Matos, L.M. 1994) Learning to Diagnose Failures of Assembly Tasks, Proc. of the IFIP IFAC ISIR Int l Conf. on Artificial Intelligence in Real Time Control, Valencia, Spain, October 1994. Seabra Lopes, L. Camarinha Matos, L.M. sub. Automatic Generation of Diagnostic Knowledge for Autonomous Assembly , ....

Camarinha-Matos, L.M., L. Seabra Lopes, J. Barata (1994). Execution Monitoring in Assembly with Learning Capabilities, Proc. of the 1994 IEEE Int'l Conf. on Robotics and Automation, San Diego, California, May 1994.

....states that can occur in 2D contact problems. Wampler [36] and Samson et al. 10] describe some elementary compliant actions , with other than force sensors. On line contact state monitoring and task error correction is still a very challenging problem; some preliminary theories can be found in [37] [38] 39] 40] An important aspect of on line monitoring is the detection of sudden changes in the force and motion signals; surveys of existing techniques can be found, for example, in [41] 2] 42] 2 Theoretical foundations of the TFF This section discusses the physical and mathematical ....

L. M. Camarinha-Matos, L. Seabra Lopes, and J. Barata, \Execution monitoring in assembly with learning capabilities," in Proc. IEEE/RSJ Int. Conf. Intel. Robots and Systems, 1992.

.... features in automation systems flexibility, adaptability, versatility relaxing cell structuration constraints and leading to the concept of Flexible Manufacturing Systems (FMS) To accommodate the wide range of product processing techniques in a FMS more versatile machines must be included [1,11]: easily integratable CNC machines, multi operation devices, robots with multiple tools end effectors, modular fixtures and feeders. A rich sensorial environment and advanced communication infrastructures (and related protocols: MAP MMS, fieldbus, are other important hardware requirements ....

....integration; etc. With these concerns in mind, we have proposed an architecture for evolutive supervision of robotized assembly tasks, that includes, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures [1]. Particular attention was given to the acquisition of knowledge about the tasks and the environment to support monitoring, diagnosis and error recovery. Modeling execution failures through taxonomies and causal networks plays a central role in diagnosis and recovery. A generic training ....

[Article contains additional citation context not shown here]

Camarinha-Matos, L.M., L. Seabra Lopes, J. Barata (1994) Execution Monitoring in Assembly with Learning Capabilities, Proc. IEEE Int'l Conf. on Robotics and Automation, San Diego.

....the incorporation of machine learning paradigms in terms of obtaining a supervision system that is able to learn the necessary knowledge to perform its function. In terms of research this project was very profitable. A number of publications in journals, conferences and workshops can be mentioned [23, 13, 6, 10, 7, 8, 11, 5, 14, 9, 20, 24, 25, 26, 22, 23, 23, 112, 119, 120, 116, 118, 117, 115, 110, 114, 111, 113, 109, 89, 88, 87, 82, 84, 85, 86, 83]. 4 RESULTS 23 Three PhD thesis and one MsC thesis, addressing different areas in the workpackage, are approaching its conclusion. An overview of the main results will now be given. 4.3.1 Results in Assembly Migration from and or integration of legacy systems is one of the most challenging ....

....of the robot control language is that it does not provide guarded movements. Since communication via teach pendant (TP) is very fast, the solution was to develop and run a TP emulator on a dedicated PC and decompose each motion command into a series of increments, executing them via the emulator [26, 22, 89]. As it is not easy to make acquisition of large quantities of sensorial data in Unix workstations, and, on the other side, concurrency in Unix affects the sensor sampling rate, a monitoring program is run in another dedicated PC, where a data I O board was installed. This program checks ....

[Article contains additional citation context not shown here]

L. M. Camarinha-Matos, L. Seabra Lopes, and J. Barata. Execution monitoring in assembly with learning capabilities. In Proceedings of the IEEE International Conference on Robotics and Automation, 1994.

....recovery will tend to consist of simple reflexive actions. At the upper levels recovery will require more extensive diagnosis and planning. The architecture of an Intelligent Execution Supervisor should reflect the hierarchical structure of the plans. At each plan level, the main functions are [1]: Dispatching and Global Coordination The global coordination activities performed by a high level controller include dispatching actions to the executing agents, driven by the scheduled task plan, synchronization of the agents activities and with external events, and information sharing. ....

....taxonomic. At each level of the taxonomy, cause effect relations between different types of errors should be added. Typically, execution failures are caused by system faults, external exceptions or other past execution failures, although, in general, errors of the three kinds may cause each other [1]. Determining explanations for detected execution failures can become very complex when errors propagate. Modeling errors in terms of taxonomic and causal links aims at handling this complexity [1,6] 3.1 Learning of Conceptual Hierarchies As emphasized above, the difficulty in hand coding the ....

[Article contains additional citation context not shown here]

Camarinha-Matos, L.M., L. Seabra Lopes, J. Barata (1994) Execution Monitoring in Assembly with Learning Capabilities, Proc. of IEEE Int'l Conf. on Robotics and Automation, San Diego.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC