Home research People General Info Seminars Resources Intranet
| Algorithms & Applcations Group | Home | Research | Publications | People | Resources | News
Home Page for Chinwe Ekenna | Parasol Laboratory

Picture Chinwe Ekenna
PhD Student
Algorithms & Applications Group

Parasol Laboratory url: http://parasol.tamu.edu/~cekenna/
Department of Computer Science and Engineering email:
Texas A&M University office: 407E HRBB
College Station, TX 77843-3112 tel: (979) 847-8835
USA fax: (979) 458-0718

CV     Research Statement     Teaching Philosophy

Courses Currently Teaching

Spring 2016

About Me

I am a graduate student at Texas A & M University currently working with Professor Nancy Amato. I attained my BSc and Msc degree in computer science from Covenant University Nigeria. Our group works with Randomized motion planning algorithms and my research is focused on application of this algorithms to computational biology problems.

Motion planning involves the use of algorithms and methods in planning motions for objects.These algorithms help in identifying a valid path for and object so it can move from a start point to its destination without hitting obstacles and also avoid colliding with the walls of its set environment. Examples of this objects could be automobiles, assemble machines and search and rescue robots.

My research is specifically geared towards using this motion planning algorithms for highly articulated linkages. The technique I would be employing in the course of my research are sampling based motion planning. This method samples valid configurations of movable objects and connects them with simple local planning methods from which trajectories can be generated. I would be working on better methods to characterize and analyze these configurations. This research finds high applicability for work currently done in molecular motions in a bid to understand the cause of diseases such as Alziemers,Mad-Cow, Cystic Fibrosis.

Leadership Activities : I have been a mentoring and communications officer for the ACM-Women Organisation at Texas A & M University called Aggie Women in Computer Science (AWICS). Visit our webpage here to learn more.

Computational Biology:
Protein Folding
Protein folding has been studied extensively both by biochemist,physicists,computer scientist etc. Succesfully understanding the folding process,the biochemical interactions and energy flunctuations at each stage of the folding process would aid in finding a cure for currently incurable diseases such as the Alzheimer disease and mad cow disease which are the result of the misfolding of some proteins within the human genome. We model protein folding at its various stages using motion planning algortihms and simulate our proteins like robots having a high degree of freedom. We provide a protein folding server where proteins can be submitted and the folding motions analysed with pathways returned as results. Please visit our folding server
Motion Planning:
Adaptive Neighbor Connection
We present a general connection framework that adaptively selects a neighbor finding strategy from a candidate set of options. Our framework learns which strategy to use by examining their success rates and costs. It frees the user of the burden of selecting the best strategy and allows the selection to change over time.


Chinwe Ekenna, Shawna Thomas, Nancy Amato, "Adaptive Local Learning in Sampling Based Motion Planning for Protein Folding," Bio Med Central Systems Biology, 10(2):165--179, Aug 2016. Also, In The IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 61-68, Washington DC, USA, Nov 2015.
Journal(pdf, abstract) Proceedings(pdf, abstract)

Chinwe Ekenna, "Improved Sampling Based Motion Planning Through Local Learning," Ph.D. Thesis, Department of Computer Science and Engineering, Texas A&M University, Aug 2016.
Ph.D. Thesis(pdf, abstract)

Chinwe Ekenna, Diane Uwacu, Shawna Thomas, Nancy Amato, "Studying learning techniques in different phases of PRM construction," In Machine Learning in Planning and Control of Robot Motion Workshop (IROS-MLPC), Hamburg, Germany, Oct 2015.
Proceedings(pdf, abstract)

Chinwe Ekenna, Diane Uwacu, Shawna Thomas, Nancy Amato, "Improved Roadmap Connection via Local Learning for Sampling Based Planners," In Proc. IEEE Int. Conf. Intel. Rob. Syst. (IROS), pp. 3227-3234, Hamburg, Germany, Oct 2015.
Proceedings(pdf, abstract)

Chinwe Ekenna, Shawna Thomas, Nancy Amato, "Adaptive Neighbor Connection Aids Protein Motion Modeling," In Proc. RSS Workshop on Robotics Methods for Structural and Dynamic Modeling of Molecular Systems, Jul 2014.
Proceedings(ps, pdf, abstract)

Chinwe Ekenna, Shawna Thomas, Nancy Amato, "Adaptive Neighbor Connection using Node Characterization," Technical Report, TR14-005, Apr 2014. Also, Technical Report, TR14-005, Apr 2014.
Technical Report(pdf) Technical Report(pdf, abstract)

Chinwe Ekenna, Sam Ade Jacobs, Shawna Thomas, Nancy M. Amato, "Adaptive Neighbor Connection for PRMs: A Natural Fit for Heterogeneous Environments and Parallelism," In Proc. IEEE Int. Conf. Intel. Rob. Syst. (IROS), Tokyo, Japan, Nov 2013.
Proceedings(pdf, abstract)

Shawna Thomas, Lydia Tapia, Chinwe Ekenna, Hsin-Yi (Cindy) Yeh, Nancy M. Amato, "Rigidity Analysis for Protein Motion and Folding Core Identification," In Proc. of 2013 AAAI Wkshp. on Art. Int. and Robot. Meth. in Comp. Bio., Bellevue, WA, Jul 2013.
Proceedings(pdf, abstract)

Shuvra Nath, Shawna Thomas, Chinwe Ekenna, Nancy M. Amato, "A Multi-Directional Rapidly Exploring Random Graph (mRRG) for Protein Folding," In ACM Conference on Bioinformatics, Computational Biology and Biomedicine, pp. 44-51, Orlando, FL, USA, Oct 2012.
Proceedings(ps, pdf, abstract)