No abstract

No abstract

With this work, it is intended to do the tracking and intrusive and expensive specialized hardware and requires analysis of the human motion, more specifically the gait. By contact with the person. Other studies and results are using computational vision, it has been acquired the trajectories compiled in [14].of defined control points in individuals' body, throughout time Our study's aim is to obtain gait signatures using and space. These results are to be used afterwards in gait computer vision techniques and to extract kinematics features specification of biped robots. I I Several types of movement and the phases that compose a for describing human motion and equilibrium. These results common system of capture and analysis of movement are are to be used afterwards in gait specification of biped robots. referenced. Then, methods used in image processing and a To achieve this, white light emitting diodes (LED) located on description of existing gait types are detailed. Finally, the several points on an individuals body were used and images implemented software is presented and the results analyzed.were captured during his locomotion in front of a web cam. Then, using properties of the body parts and guidance by Keywords -Balance, biped robotics, human gait, image anatomical knowledge, gait characteristics were extracted. A processing.2D stick figure is used to represent the human body model, and joint angles are calculated to describe the gait motion.

The real-time balance control of an eight-link biped robot using a zero moment point (ZMP) dynamic model is difficult due to the processing time of the corresponding equations. To overcome this limitation, two alternative intelligent computing control techniques were compared: one based on support vector regression (SVR) and another based on a first-order Takagi-Sugeno-Kang (TSK)-type neural-fuzzy (NF) network. Both methods use the ZMP error and its variation as inputs and the output is the correction of the robot's torso necessary for its sagittal balance. The SVR and the NF were trained based on simulation data and their performance was verified with a real biped robot. Two performance indexes are proposed to evaluate and compare the online performance of the two control methods. The ZMP is calculated by reading four force sensors placed under each robot's foot. The gait implemented in this biped is similar to a human gait that was acquired and adapted to the robot's size. Some experiments are presented and the results show that the implemented gait combined either with the SVR controller or with the TSK NF network controller can be used to control this biped robot. The SVR and the NF controllers exhibit similar stability, but the SVR controller runs about 50 times faster.