SIMULATING LIFTING MOTIONS USING ARTIFICIAL NEURAL NETWORKS
I would like to express my most heartfelt gratitude to Dr Qu Xingda, Associate Professor MAE, NTU for giving me the opportunity to participate in her research group and for her guidance throughout my project.
I would like to thank my co-supervisor Dr. Pina Marziliano Assistant professor EEE, NTU for her constant encouragement and support in the course of this research.
I thank all the Lab Staff in RRC including Mr Lim, Mr You and Ms Agnes for their constant support for my research.
I would like to thank NTU for having given me an opportunity to pursue my interest in this field of research by providing the necessary facilities.
Finally, I would like to thank my family members for their love and support.
Human motion simulation has never been done accurately. It is a major challenge for engineers and researchers to integrate humans in CAD systems. Human motion simulation has been used in various applications which have been successful. They have increased the effectiveness, safety and efficiency of the application. This dissertation primarily focuses on study of kinematics and posture of an individual while performing a lifting task especially the ones related to manual materials handling. The postures were predicted using Artificial Neural Networks. A set of inputs like target location were fed into the neural networks and the static postures were generated as output. The postures were predicted for two dimensional sagittally symmetric lifts as the number of degrees of freedom is less. The networks were trained using data captured from real human data involving lifting motions. The root mean square errors were calculated to validate the accuracy of the prediction.
The way in which people interact with the environment is complex. Their every day physical work includes sitting, standing, walking, lifting objects. These actions help the individual to interact with the environment. The actions are carried out by various muscles in the body that affects the human posture. The change in human posture with respect to time is human motion. Simulation of human motion has become important these days as the various CAD packages use it to animate motions. Engineers use this to
The physical interaction of people with their surroundings is constant and complex. As people sit, walk, lift boxes, sleep, or perform any other task, they must consciously or unconsciously perform physical actions, in the form of movements, to interact with their surroundings. These actions typically consist of coordinated muscle activations that impact the positions, velocities, and accelerations of various body parts and, consequently, the overall human posture at each point in time (i.e. human motion or movement).
Predicting human motion has become increasingly important as new software packages attempt to simulate the physical interaction between humans and their environment. Programs such as Jack (EDS, 2001), Deneb/ERGO (Delmia, 2001), and ANTHROPOS (Tecmath, 2001) assist designers by providing humanoids that can be manipulated and animated in a virtual environment. These tools allow task- and work-designers to create a digital mockup of working situations and make a variety of virtual humans interact with these mockups. The goal of this process is to discover problems in the human interaction with the proposed designs before these designs are built, thus reducing the risk of costly redesign processes and workforce injury.