Title: "Investigation on Data Concurrency for Sensory Fusion in Humanoid Robot"
         

Page(s): 45 - 49
Authors: ASHOK KUMAR RAMADOSS ††, K.MARIMUTHU ††

Abstract

We believe that a robot should model and recognize a set of grounded responses that are built from knowledge about the nature of the interaction situation, and should also be able to ground responses that are found by semantics-free contingency detection.To carry out Research on Humanoid Robot effectively first in the absence of hardware support then building a Humanoid Robot for achieving data concurency by integerating data by the fusion of sensory datas in the humanoid robot .Multi Sensor fusion Studies for Dynamics nad Kinematics therrby achieving Data Concurrency by sensory data integeration by sensor fusion for range detecting by vision and navigation using simulink model and humanoid robot prototype. Within the current framework, we can model and recognize grounded responses as events. As future work, we will investigatehow to attribute semantics to ungrounded responses through iterative interactions and finaly by sensor fusion.In this Research, we could present a simple and reliable approach of creating humanoid robot platform based on the ROBO OS and modeling language using ubunto linux . Another goal is to investigate the general potential of SFA for using it within sen-sorimotor loops which to our knowledge has not been considered until now. The application of SFA within sensorimotor loops is motivated by pointing out its relation to second-order Volterra filters. Our experiments show that the overall reactivity of the gait pattern increaseswithout any profound loss in stability, and that SFA appears to be suitable for the usage even at such levels of sensorimotor control that are directly involved into motor activity regulation.This work is concernedon sensitivity analysis of semiautonomy algorithm of humanoid robot to environmental sensorsí failures. The construction of the robot, semiautonomy algorithm and used sensors have been described. The algorithm bases on a reactive hybrid approach that merges data from different types of sensors and calculates resulting velocities. This algorithm takes also into account environmental sensorsí damage by modifying th behavior of robot in accordance to actual sensorsí set state of health. Simulation research using ROBOS/Simulink package and experimental testsí results of semiautonomy algorithm were presented. The experimentaltests were carried out in outdoor conditions. The research and tests were performed for normal environmental sensorsí operation and for selected sensorsí damage.On that basis, sensitivity of semiautonomy algorithm to selected environmental sensors damage was tested.