We develop algorithms and robotic systems that operate autonomously in complex, unstructured, and uncertain real-world environments, using both single-robot and multi-agent systems. Our research lies at the intersection of robotic decision-making, path planning, learning, and field robotics, with high impact real-world applications such as bathymetric mapping, aquaculture and wildlife monitoring.
Embedded Files
Potential Projects
Potential Projects
Project 1: Mission Planner
Project 1: Mission Planner
Developing novel algorithms for mission planning. Given different representation of the environment – bathymetric maps, satellite images, different constraints – minimal turns, energy constraints, and environmental conditions – wind, current, develop new mission plans that will efficiently survey the given area taking into account the constraints. The methods will be offline and online – adapting to the new changes of the environment and being capable of replanning. This project will be also exploring on how generative models can be used to learn from human preferences and from existing model-based approaches.
References:
Nare Karapetyan, Adam Braude, Jason Moulton, Joshua A. Burstein, Scott White, Jason M. O'Kane, and Ioannis Rekleitis, Riverine Coverage with an Autonomous Surface Vehicle over Known Environments, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 2019
Nare Karapetyan, Jason Moulton and Ioannis Rekleitis, Meander Based River Coverage by an Autonomous Surface Vehicle, Field and Service Robotics: Recent Advances in Research and Applications (FSR). Springer, Tokyo, Japan, 2019
Nare Karapetyan, Jason Moulton, Jeremy Lewis, Alberto Quattrini Li, Jason O'Kane, Ioannis Rekleitis, Multi-robot Dubins Coverage with Autonomous Surface Vehicles, In IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 2018
Project 2: Surface and Underwater Cooperation
Project 2: Surface and Underwater Cooperation
Developing novel algorithms for cooperative monitoring of marine environments - given area of interest how to visit each of the regions taking into account the cost of resurfacing of the underwater vehicle to perform a GPS fix. The project will aim to minimize the risk of underwater vehicle being detected and minimizing the overall cost of rendezvous and survey time. This project will also have hardware component that will be investigating different communication capabilities for surface and underwater vehicle.
Extra: In addition, new localization approaches for ASV can be explored to avoid unauthorized tracking.
References:
Nare Karapetyan, Ahmad Bilal Asghar, Amisha Bhaskar, Guangyao Shi, Dinesh Manocha and Pratap Tokekar; AG-Cvg: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV; IEEE/RSJ International Conference on Intelligent Robots and Systems (ICRA), 2024.
Ahmad Asghar, Guangyao Shi, Nare Karapetyan, Jean-Paul Reddinger, James Dotterweich, James Humann, and Pratap Tokekar; Risk-aware Recharging Rendezvous for a Collaborative Team of UAVs and UGVs. In IEEE International Conference on Robotics and Automation (ICRA), London, UK, 2023.
Guangyao Shi, Nare Karapetyan, Ahmad Bilal Asghar, Jean-Paul Reddinger, James Dotterweich, James Humann and Pratap Tokekar; Risk-aware UAV-UGV Rendezvous with Chance-Constrained Markov Decision Process, Conference on Decision and Control (CDC), Cancún, Mexico, 2022
Project 3: Ground Navigation
Project 3: Ground Navigation
Developing novel algorithms for monitoring a dynamic system with an objective of reducing disturbances caused to the system. The project will explore how to find navigable regions over ice, how to pursue the dynamic object, and how to perform camouflaged navigation. The project will delve into learning-based approaches for segmentation of the navigable regions and explore both model-based or model-free methods for trajectory generation. The application focus of the project is surveying a colony of penguins.
References:
Jing Liang, Kasun Weerakoon, Tianrui Guan, Nare Karapetyan and Dinesh Manocha, AdaptiveON: Adaptive Outdoor Navigation Method For Stable and Reliable Motions; Robotics and Automation Letters (RA-L), 2022
Kasun Weerakoon, Souradip Chakraborty, Nare Karapetyan, Amrit Singh Bedi and Dinesh Manocha; HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm, Conference of Robot Learning (CoRL), Auckland, NZ, 2022
Xiaomin Lin*, Nare Karapetyan*, Kaustubh Joshi, Tianchen Liu, Miao Yu, Pratap Tokekar and Ioannis Aloimonous; UIVNav: Underwater Information-driven Vision-based Navigation via Imitation Learning; EEE/RSJ International Conference on Intelligent Robots and Systems (ICRA), 2024 [*equal contributors].
Nare Karapetyan, James Johnson, and Ioannis Rekleitis, Human Diver Inspired Visual Navigation for Coverage Path Planning of Shipwrecks, Marine Technology Society Journal, "Best of OCEANS 2020" July/August issue 2021
Project 4: Automated Planning for Drift-Based Ocean Robots
Project 4: Automated Planning for Drift-Based Ocean Robots
Developing novel algorithms for monitoring a dynamic system with an objective of reducing disturbances caused to the system. The project will explore how to find navigable regions over ice, how to pursue the dynamic object, and how to perform camouflaged navigation. The project will delve into learning-based approaches for segmentation of the navigable regions and explore both model-based or model-free methods for trajectory generation. The application focus of the project is surveying a colony of penguins.
References:
Patrick McGuire, Michael Jakuba, and Jim Partan. "TideRider: A Low-Cost Coastal Profiling Float." In OCEANS 2023-Limerick, IEEE, 2023.
Nare Karapetyan, Jason Moulton and Ioannis Rekleitis, Meander Based River Coverage by an Autonomous Surface Vehicle, Field and Service Robotics: Recent Advances in Research and Applications (FSR). Springer, Tokyo, Japan, 2019
Nare Karapetyan, Jason Moulton, and Ioannis Rekleitis. "Dynamic autonomous surface vehicle control and applications in environmental monitoring." In OCEANS 2019 MTS/IEEE SEATTLE, IEEE, 2019.
Page updated
Google Sites
Report abuse