P. Sikka and B. McCarragher, "Monitoring contact using clustering and discriminant functions," In Proceedings of the 1996.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....of contact formations) using a petri net. The controller detected the current discrete event and generated the velocity trajectory to achieve the next desired discrete event. More recently, refinements have been made to McCarragher s qualitative reasoning method of identifying contact formations [61]. Instead of using threshold values to distinguish between contact states, discriminant functions are used. Force data is first partitioned into classes using a clustering algorithm. Linear discriminant functions are then determined from the classified data. As an alternative to using geometric ....

P. Sikka and B. McCarragher, "Monitoring contact using clustering and discriminant functions," In Proceedings of the 1996.

....####### ####### ####### ####### ####### ####### ####### #### #### Fig. 1. An Example of Two Contact Formations whichBelong to the Same Class of Single Ended Contact Formations to precalculate the templates. Recent refinements use linear discriminant functions instead of thresholds [9]. Hovland and McCarragher proposed FFTs for capturing the dynamics of contact changes and Hidden Markov Models to model the resultant information [10] While they achieved a 97 success rate, they reported times of 0.5 0.6 seconds. Also, significant training is required for eachcontact ....

P. Sikka and B.J. McCarragher, "Monitoring contact using clustering and discriminant functions," in Proceedings of the 1996 IEEE International ConferenceonRobotics and Automation, Minneapolis, MN, Apr. 1996, vol. 2, pp. 1351-- 1356.

....first step, the process monitor samples the variable z and then quantises or discretises it into the variable Zq. For ex ample, in an assembly task, zq = The discretisation is performed using discriminant functions gvc based on the current contact state . The details of this step can be found in [30]. The second step of the process monitor consists of using a rule based system [3] to identify the process states and transitions based on a sequence of discre Discrete event Controller Contact state Network Rule based System I zqo i zq(O Forward Interface Discriminant Functions u(O c ....

P. Sikka and B.J. McCarragher. "Monitoring contact using clustering and discriminant functions", Proceedings of the 1996.

....task, z q = f xq ; f yq ; f xq ; f yq ] t . The discretization is performed using discriminant functions g fl c based on the current contact state fl c . The discriminant functions are also obtained from the data generated by human demonstration. The details of this step can be found in [ Sikka and McCarragher, 1996 ] The second step of the process monitor consists of using a rule based system [ Barr and Feigenbaum, 1981 ] to identify the process state fl based on a sequence of discretized variables. This process is described in detail in the next section. 3 Rule based Contact Monitoring Each contact ....

....classes for each component of the plant state vector z. These classes correspond to the discretized values for the variable. In this manner, the clusters are then used to learn the discriminant functions for each of the variables and for each contact state. This process is described in detail in [ Sikka and McCarragher, 1996 ] Finally, the rules for contact state and transition recognition must be obtained from the clustered data. First, for each state fl i , the clustered data is regrouped into sub traces corresponding to the sub traces in the set X fl i to obtain the set of sub traces X qfl i . Then, for each ....

Pavan Sikka and Brenan J. McCarragher. Monitoring contact using clustering and discriminant functions. In IEEE International Conference on Robotics and Automation, 1996.

....Information from different sensors are combined into one single outcome, with (hopefully) better resolution and reliability than could be produced by the single sensors individually. 4. Classification, also known as (template pattern) matching, labelling or event object pattern recognition, [10, 22, 21, 20, 35, 49, 74, 83, 79]. A (spatial or temporal) sequence of sensor signals is compared to logs of previous executions, or to models of the task, in order to find the best correspondence. 5. Sequence planning, or decision making, 2, 1, 14, 17] If the task controller has the option to choose between different ....

P. Sikka and B. McCarragher. Monitoring contact using clustering and discriminant functions. In IEEE Int. Conf. Robotics and Automation, pages 1351--1356, Minneapolis, MN, 1996.

....z and then quantises or discretises it into the variable z q . For example, in an assembly task, z q = F xq ; F yq ; F xq ; F yq ] t . The discretisation is performed using discriminant functions g fl c based on the current contact state fl c . The details of this step can be found in [30]. The second step of the process monitor consists of using a rule based system [3] to identify the process states and transitions based on a sequence of discre3 Rule based System Plant Discrete event Controller Forward Interface q z (t) g u g (t) t) c Discriminant Functions ) g g c v z z ....

P. Sikka and B.J. McCarragher. "Monitoring contact using clustering and discriminant functions", Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Minneapolis, 2228 April 1996, pp. 1351-1356.

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