Kasun Weerakoon

Ph.D. Student 

University of Maryland, College Park, MD

About Me

I am a Ph.D. candidate at the Department of Electrical & Computer Engineering, University of Maryland, College Park. Currently, I'm pursuing my Ph.D. as a graduate research assistant at the GAMMA Lab supervised by Prof. Dinesh Manocha. My dissertation research focuses on autonomous robot navigation in complex outdoor environments. I received the University of Maryland Graduate School's Outstanding Graduate Research Assistant Award for the Academic year 2022-23 and George Harhalakis Outstanding Systems Engineering Graduate Student Award for the year 2023-24. 

My research interests include,

I have experience in developing autonomous navigation algorithms and porting them to real robot platforms such as  Turtlebot 2, Clearpath Husky, Jackal, Boston Dynamics Spot, and Ghost Vision 60.

E-mail: kasunw@umd.edu

LinkLinkedInGitHubTwitter

Education

PhD in Electrical & Computer Engineering

University of Maryland, College Park.

Aug. 2019 - Current

M.Sc. in Electrical Engineering

University of Maryland, College Park.

Aug. 2019 - May 2024

B.Sc.(Hons.) in Electrical & Electronic Engineering

University of Peradeniya, Sri Lanka.

Jan. 2014 - Sep. 2017

Recent Projects / Publications

1. Vision Language Model (VLM) based Perception for Contextual and Scene aware Navigation

K. Weerakoon, M. Elnoor, G. Seneviratne, V. Rajagopal, S. H. Arul , J. Liang, M. Jaffar and D. Manocha, "BehAV: Behavioral Rule Guided Autonomy Using VLMs for Robot Navigation in Outdoor Scenes", accepted in ICRA 2025.

[Project][Paper][Code]

A. J. Sathyamoorthy, K. Weerakoon, M. Elnoor, A. Zore, B. Ichter, F. Xia, J. Tan and D. Manocha, "CoNVOI: Context-aware Navigation using Vision LanguageModels in Outdoor and Indoor Environments," in IEEE/RSJ Intelligent Robots and Systems conference (IROS), 2024.

[Project][Paper]

2. Deployable Navigation Policies using Online and Offline Reinforcement Learning (RL)

K. Weerakoon, A. J. Sathyamoorthy, M. Elnoor, and D. Manocha, “VAPOR: Legged Robot Navigation in Unstructured Outdoor Environments using Offline Reinforcement Learning” in International Conference on Robotics and Automation (ICRA),  2024. 

[Project][Paper][Code]

K. Weerakoon*, Souradip Chakraborty*, Nare Karapetyan, Adarsh Jagan Sathyamoorthy, Amrit Singh Bedi, Dinesh Manocha, “HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm” in Conference on Robot Learning (CoRL),  2022. 

[Project][Paper]

K. Weerakoon, A. J. Sathyamoorthy, U. Patel, and D. Manocha, “TERP: Reliable planning in uneven outdoor environments using deep reinforcement learning,” International Conference on Robotics and Automation (ICRA),  2022,  pp. 9447-9453. 

[Project][Paper][Code]

K. Weerakoon, A. J. Sathyamoorthy, and D. Manocha, “Sim-to-Real Strategy for Spatially Aware Robot Navigation in Uneven Outdoor Environments,” in ICRA Workshop on Releasing Robots into the Wild: Simulations, Benchmarks, and Deployment, 2022.

[Paper]

Jing Liang, Kasun Weerakoon, Tianrui Guan, Nare Karapetyan, Dinesh Manocha, “AdaptiveON: Adaptive Outdoor Navigation Method For Stable and Reliable Actions,”  in IEEE Robotics and Automation Letters, vol. 8, no. 2, pp. 648-655, Feb. 2023.

[Project][Paper] 

3. Multi-modal Perception for Robot Navigation in Unstructured and Forested Environments

K. Weerakoon, A. J. Sathyamoorthy, J. Liang, T. Guan, U. Patel, and D. Manocha, “GrASPE: Graph based Multimodal Fusion for Robot Navigation in Outdoor Environments” in IEEE Robotics and Automation Letters,  2023. 

[Project][Paper]

A. J. Sathyamoorthy, K. Weerakoon, T. Guan, Mason Russell, Damon Conover, Jason Pusey, and D. Manocha, “VERN: Vegetation-aware Robot Navigation in Dense Unstructured Outdoor Environments,”  in IEEE/RSJ Intelligent Robots and Systems conference (IROS),  2023. 

[Project][Paper] 

A. J. Sathyamoorthy*, K. Weerakoon* , M. Elnoor,  Mason Russell, Jason Pusey, and D. Manocha, “MIM: Indoor and Outdoor Navigation in Complex Environments Using Multi-Layer Intensity Maps” in International Conference on Robotics and Automation (ICRA),  2024. 

[Project][Paper]

A. J. Sathyamoorthy, K. Weerakoon, T. Guan, J. Liang, and D. Manocha, “TerraPN: Unstructured terrain navigation through Online Self-Supervised Learning,” accepted for IEEE/RSJ Intelligent Robots and Systems conference (IROS),  2022. 

[Project][Paper] 

Tianrui Guan, Divya Kothandaraman, Rohan Chandra, Adarsh Jagan Sathyamoorthy, Kasun Weerakoon, Dinesh Manocha, “GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments,” in IEEE Robotics and Automation Letters, vol. 7,  no. 3, pp. 8138-8145,  July 2022.

[Project][Paper] 

4. Proprioception and Pseudo Haptic Sensing for Legged Robot Navigation in Unstructured Terrains

M. Elnoor, K. Weerakoon, A. J. Sathyamoorthy, T. Guan, V. Rajagopal and D. Manocha, "AMCO: Adaptive Multimodal Coupling of Vision and Proprioception for Quadruped Robot Navigation in Outdoor Environments,"  in IEEE/RSJ Intelligent Robots and Systems conference (IROS),  2024.

[Project][Paper]

M. Elnoor, A. J. Sathyamoorthy, K. Weerakoon, and D. Manocha, "ProNav: Proprioceptive traversability estimation for legged robot navigation in outdoor environments," in IEEE Robotics and Automation Letters, 2024.

[Project][Paper]