Primary Research

Coverage Path Planning in 3D

We propose to use the navigation strategy that a human diver will execute when circumnavigating around a region of interest, in particular when collecting data from a shipwreck. In contrast to the previous methods in the literature, we are aiming to perform coverage in completely unknown environment with some initial prior information. Our proposed method uses convolutional neural networks to learn the control commands based on the visual input. Preliminary results and a detailed overview of the proposed method are discussed.

Reference:

Riverine Coverage With an Autonomous

This work leverages human expertise in river exploration and data collection strategies to automate and optimize these processes using autonomous surface vehicles (ASVs). In particular, three deterministic algorithms for both partial and complete coverage of a river segment are proposed, providing varying path length, coverage density, and turning patterns. Deployments on several segments of Congaree River in South Carolina, USA, resulted in total of more than 35km of coverage trajectories in the field.

Reference:

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 

Meander Based River Coverage by an Autonomous Surface Vehicles

This work is aimed to optimize scientific surveying operations performed by autonomous surface vehicles operating on the rivers. In this work we are tackling the problem  of how to combine implicit river speed information that river meanders encode to perform faster coverage.  When taking into account meanders the coverage time has been decreased in average by more than 20%. The deployments of the ASVs were performed on the Congaree River, SC, USA, and resulted in more than 27 km of total coverage trajectories.

Reference:

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

Multi-robot Dubins Coverage with Autonomous Surface Vehicles

This paper focuses on environmental monitoring of aquatic environments using multiple Autonomous Surface Vehicles (ASVs) with Dubin's constraint. We present two heuristics methods based on a variant of the traveling salesman problem—k-TSP—formulation and clustering algorithms that efficiently solve the problem. The proposed methods are tested both in simulations to assess their scalability and with a team of ASVs operating on a 200 km2 lake to ensure their applicability in real world.

Reference:

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

Efficient Multi-Robot Coverage of a Known Environment

Complete area coverage is the problem of moving an end-effector over all available space while avoiding existing obstacles. In such tasks, using multiple robots can increase the efficiency of the area coverage in terms of minimizing the operational time and increase the robustness in the face of robot attrition. As a result of this research we proposed two approximation heuristics that provide good coverage distribution between robots and minimize the workload per robot, meanwhile ensuring complete coverage of the area.

Reference:

Nare Karapetyan, Kelly Benson, Chris McKinney, Perouz Taslakian, Ioannis Rekleitis, Efficient Multi-Robot Coverage of a Known Environment, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017

Other Projects

Motion Planning in Underwater Environment

In order to perform efficient coverage important aspect to consider is how robot will move from specified waypoint A to waypoint B. And to tackle that problem we adapted a trajopt controller designed for manipulators to underwater domain for navigating around complex structures such a shipwrecks and unstructured obstacle dense areas. For reliable navigation, accurate state estimation is necessary. In the underwater domain, visual features that enable effective state estimation can be sparse or even absent in parts of the environment. Thus, motion plans for AUVs should account for the need to keep those features visible throughout their execution. The AquaVis method produces motions enabling AUVs to efficiently reach their goals while avoiding obstacles safely and maximizing the visibility of multiple objectives along the path within a specified proximity. 

Reference:

Control of Autonomous Surface Vehicles and Modeling External forces

Environmental monitoring of marine environments presents several challenges: the harshness of the environment, the often remote location, and most importantly, the vast area it covers. In order to efficiently explore and monitor currently known marine environments as well as reach and explore remote areas of interest, we worked on a design of an autonomous surface vehicle (ASV) with the power to cover large areas. Within this project we have designed a completely autonomous SV. Tackled the problem of how environmental forces such as speed of water current and wind affect the control of ASV, and build a model of those external forces based on which a feed-forward controller has been designed.

References:

Underwater State Estimation and Sensors

References: