Most of work on motion of mobile robots is to generate plans for avoiding obstacles or perform some meaningful and useful actions. In modern robot theatres and entertainment robots the motions of the robot are scripted and thus the performance or behavior of the robot is always the same. In this work we want to propose a new approach to robot motion generation. We want our robot to behave more like real people. People do not move in mechanical way like robots. When a human is supposed to execute some motion, these motions are similar to one another but always slightly or not so slightly different. We want to reproduce this property based on the introduced by us new concept of probabilistic regular expression, a method to describe sets of interrelated similar actions instead of single actions. Our goal is not only to create motions for humanoid robots that will look more naturally and less mechanically, but also to program robots that will combine basic movements from certain library in many different and partially random ways. While the basic motions were created ahead of time, their combinations are specified in our new language. Although now our method is only for motions and does not take inputs from sensors into account, in future the language can be extended to input/output sequences, thus the robot will be able to adapt the motion in different ways, to some sets of sequences of input stimuli. The inputs will come from sensors, possibly attached to limbs of controlling humans from whom the patterns of motion will be acquired.
| Identifer | oai:union.ndltd.org:pdx.edu/oai:pdxscholar.library.pdx.edu:open_access_etds-1193 |
| Date | 01 January 2011 |
| Creators | Bhutada, Aditya |
| Publisher | PDXScholar |
| Source Sets | Portland State University |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Dissertations and Theses |
Page generated in 0.0151 seconds