Marsupial Robot Team Monitors Rivers From Water and Air

An autonomous boat and hexacopter cooperate to autonomously navigate and map rivers

2 min read
Marsupial Robot Team Monitors Rivers From Water and Air

I know what you're thinking right now, because I was thinking it too as soon as I saw the phrase "marsupial robot team:" you're thinking about robot koalas. Or robot kangaroos. Or maybe robot wombats. As awesome as that would be, today you're going to have to make do with something only slightly less awesome, which is this duo of a robotic boat and a hexacopter that cooperate to collect data on rivers and lakes.

The "marsupial" bit refers to the hexacopter, which uses the boat as (to stretch the metaphor slightly into the absurd) a pouch. With enough solar cells and good weather, the boat could power both itself and the hexacopter, extending its operating time significantly, or in the absolute best case, indefinitely. The whole thing runs ROS, and looks to be capable of very robust autonomous navigation, but the really cool part is how the boat and the hexacopter can team up and combine the data sets that they collect to create far more comprehensive and accurate maps than either could alone. 

A particular aspect to be taken into account is the interaction of robots to take the best of the complementary visual perspectives they have of the environment. The goal is to use an aerial perspective to promote on-water safe navigation. In the application scenario, the robotic team, moving downriver, assesses a series of environmental variables. In case a pollution indicator is triggered the aerial platform is asked to perform a local survey. This information is passed on to a remote control centre, where a human operator is monitoring and configuring the mission.

The project is called RIVERWATCH, and it was part of ECHORD (the European Clearing House for Open Robotics Development) up until it actually started working, at which point it was transferred over to UNINOVA in Portugal. This is ongoing research, with several recent IEEE publications (w00t!), so we're certainly looking forward to some additional robotic marsupialness. Like maybe a submarine? Or a UGV? Or, a rocket?

 [ RIVERWATCH ] and [ ECHORD ] via [ Hackaday ]

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less