Abstracts Computer Science

Add abstract

Want to add your dissertation abstract to this database? It only takes a minute!

Search abstract

Search for abstracts by subject, author or institution

Share this abstract

Developing agile motor skills on virtual and real humanoids

by Sehoon Ha

Institution: Georgia Tech
Year: 2015
Keywords: Physics-based animation; Optimal control; Optimization algorithm
Posted: 02/05/2017
Record ID: 2132030
Full text PDF: http://hdl.handle.net/1853/54355


Abstract

Demonstrating strength and agility on virtual and real humanoids has been an important goal in computer graphics and robotics. However, developing physics- based controllers for various agile motor skills requires a tremendous amount of prior knowledge and manual labor due to complex mechanisms of the motor skills. The focus of the dissertation is to develop a set of computational tools to expedite the design process of physics-based controllers that can execute a variety of agile motor skills on virtual and real humanoids. Instead of designing directly controllers real humanoids, this dissertation takes an approach that develops appropriate theories and models in virtual simulation and systematically transfers the solutions to hardware systems. The algorithms and frameworks in this dissertation span various topics from spe- cific physics-based controllers to general learning frameworks. We first present an online algorithm for controlling falling and landing motions of virtual characters. The proposed algorithm is effective and efficient enough to generate falling motions for a wide range of arbitrary initial conditions in real-time. Next, we present a robust falling strategy for real humanoids that can manage a wide range of perturbations by planning the optimal contact sequences. We then introduce an iterative learning framework to easily design various agile motions, which is inspired by human learn- ing techniques. The proposed framework is followed by novel algorithms to efficiently optimize control parameters for the target tasks, especially when they have many constraints or parameterized goals. Finally, we introduce an iterative approach for exporting simulation-optimized control policies to hardware of robots to reduce the number of hardware experiments, that accompany expensive costs and labors. Advisors/Committee Members: Liu, C. Karen (advisor), Turk, Greg (committee member), Rossignac, Jarek (committee member), Ueda, Jun (committee member), Yamane, Katsu (committee member).

Add abstract

Want to add your dissertation abstract to this database? It only takes a minute!

Search abstract

Search for abstracts by subject, author or institution

Share this abstract

Relevant publications

Book cover thumbnail image
Prediction of Upper Body Power of Cross-Country Sk...
by Ozciloglu, Mustafa Mikail
   
Book cover thumbnail image
Bitcoins Mining, Transaction, Security Challenges and Futur...
by Zahid, Muhammad Aslam
   
Book cover thumbnail image
Applying User-Centered Interface Design Methods to...
by Mburu, Lucy Waruguru
   
Book cover thumbnail image
Head-Order Techniques and Other Pragmatics of Lamb...
by Troullinos, Nikos B.
   
Book cover thumbnail image
Visualization of Interface Metaphor for Software An Engineering Approach
by Katre, Dinesh S.
   
Book cover thumbnail image
Indoor Wireless Metering Networks A Collection of Algorithms Enabling Low Power/Low ...
by Altan, Nicola
   
Book cover thumbnail image
Automated Generation of Geometrically-Precise and ...
by Mekni, Mehdi
   
Book cover thumbnail image
A Study on the Tone-Reservation Technique for Peak...
by Butt, Umer Ijaz