K.D.M. Jayawardhana
My personal web pageexpressing my interest and past work.
About me.
I’m Masters student from University of Moratuwa. Intested in improving robots capabilites and make robots smater. My supervisor is Dr A.M. Harsha.S. Abeykoo.
Education
MSc by research at Uinversity of Moratuwa. - [2019 - 2023] Thesis topic: Haptic based surface stiffness identification using machine learning
Bachler of Science (Hons) Specelised in Electrical Engineering at University of Moratuwa - [2013 - 2017] Intake 2013 , Batch 12, Graduation year 2017
Abeykoon, A. H. S., Wijewardhana, W. M. T. G., Senevirathne, E. H., & Jayawardhana, K. D. M. (2020). Vibration suppression of force controllers using disturbance observers. In Vibration Control and Actuation of Large-Scale Systems (pp. 57-89). Academic Press. Springer
Projects
Haptic based surface stiffness identification using machine learning
Vision-based approaches are extensively employed in research to classify objects. However, there are specific characteristics of deformable objects that are challenging to classify using vision-based sensors. Examples include vegetables that may seem fresh externally but are rotten internally, ripe or unripe fruits, and objects designed to mimic real-life objects. In such cases, the texture or feel of the object may reveal distinct characteristics or its state, which may facilitate classification.
Unfortunately, the majority of object classification studies rely solely on sensory information for classification. The objective of my research is to introduce additional features for object classification and identify the optimal performing feature set. Furthermore, we aim to use time series forest classifier machine learning models to classify the objects.
Publication
Dewapura, Praveena W., KD Malith Jayawardhana, and AM Harsha S. Abeykoon. “Object Identification using Support Vector Regression for Haptic Object Reconstruction.” 2021 3rd International Conference on Electrical Engineering (EECon). IEEE, 2021.
BibTeX
@inproceedings{dewapura2021object, title={Object Identification using Support Vector Regression for Haptic Object Reconstruction}, author={Dewapura, Praveena W and Jayawardhana, KD Malith and Abeykoon, AM Harsha S}, booktitle={2021 3rd International Conference on Electrical Engineering (EECon)}, pages={144–150}, year={2021}, organization={IEEE} }
Project repositories
Force controller and hardware setup. GitHub
Data anlysis and feature creation. GitLab
Classification & feature importance. GitHub
Additional information
The summary of the project can be found here.
Data acquisition video footage
Operation of a grid connected microgrid with a variable load bus and a diesel generator set
Microgrids can helps to stabilise the national grid and absorb much renewable power. So, to export and import energy at predefined levels at steady phase, micro-grids need to adapt to a dynamic governor control to the swing bus. In our project we designed and developed a diesel generator governor which responds to the load changes inside the microgrid and keeps a steady phase of electricity export or imports to the national electricity grid. Developed governor is tested on an 11kVA diesel generator which is connected to the PI transmission line model with multiple 3 kVA loads.
Publication
Lakshitha, M. K. G., Jayawardhana, K. D. M., Boralessa, M. A. K. S., Rohitha, W. G. R. W., Hemapala, K. T. M. U., Lucas, J. R., … & Porawagamage, G. D. (2017, April). Operation of a grid connected microgrid with a variable load bus and a diesel generator set. In 2017 Innovations in Power and Advanced Computing Technologies (i-PACT) (pp. 1-6). IEEE.
BibTeX
@inproceedings{lakshitha2017operation, title={Operation of a grid connected microgrid with a variable load bus and a diesel generator set}, author={Lakshitha, MKG and Jayawardhana, KDM and Boralessa, MAKS and Rohitha, WGRW and Hemapala, KTMU and Lucas, JR and De Silva, Narendra and Porawagamage, GD}, booktitle={2017 Innovations in Power and Advanced Computing Technologies (i-PACT)}, pages={1–6}, year={2017}, organization={IEEE} }
Additional information
format https://learning-dynamic-manipulation.cs.princeton.edu/
List of answers to unknown questions.
Python motor controllers https://pypi.org/project/pypot/2.11.8/