You Can't Stop Robots With Furniture Barricades Anymore

This Georgia Tech robot is smart enough to shove furniture out of the way to get where it wants to go

3 min read
Georgia Tech robot moving furniture
Image: Georgia Tech

It used to be that even sophisticated mobile robots could be easily defeated by using (say) a table to block its way. The robot would sense the table, categorize it as an obstacle, try to plan a path around it, and then give up when its planner fails. This works because robots generally don’t know what most objects are, or how they work, or what you can do with them: They just get turned into obstacles to be avoided, because in most cases, that’s the easiest and safest thing to do.

You can’t normally use a table across a hallway to deter a human, because humans understand that tables are physical objects that can be moved, and the human will just pull the table out of the way and keep on going. Even if the table doesn’t behave exactly the way we’d expect it to (like, one of the wheels is stuck), we can adapt, and figure it out. 

At IROS 2016 in South Korea, Jonathan Scholz from Google DeepMind and collaborators from Georgia Tech presented a paper on “Navigation Among Movable Obstacles with Learned Dynamic Constraints,” which gives mobile manipulators this same capability. They can recognize objects in their way, and get inventive with physics-based tricks to get where they need to go.

Georgia Tech’s Krang robot is able to use a physics engine to understand and predict how objects will behave, and then use that knowledge to adaptively move those objects around to reach its goal

The problem of moving through an object-filled space is very common in domestic environments like homes and offices, where things can be cluttered in unpredictable ways. Unlike structured environments (factories and labs and such), you can’t always predict and model exactly how domestic environments will be cluttered, which makes it much harder for robots to figure out how to get around them. So, even if your robot is clever enough to move objects out of the way, it also needs to be able to adapt when objects that it expects to move in one way either move in a different way, or don’t move at all.

At Georgia Tech, a team of researchers led by Professors Charles L. Isbell and Henrik I. Christensen (who’s since moved to UC San Diego) has been teaching their Golem Krang robot how to move in an object-filled space by combining a Navigation Among Movable Obstacle (NAMO) path-planner with Physics-Based Reinforcement Learning (PBRL). Essentially, Krang is able to use a physics engine to understand and predict how objects will behave, and then use that knowledge to adaptively move those objects around to reach its goal. Here’s an example of how it works, using two tables (each with a mass of about 35 kilograms) that have individually lockable casters:

Success! Here’s one more example, where Krang first tries to brute force its way through both tables, and then has to replan when it doesn’t work;

Krang has no idea what the constraints are on these tables when it starts trying to move them: Every time one of the tables doesn’t move as expected (whether it’s completely stuck or just has one locked caster), Krang updates its physical model of the table, and then comes up with the next best solution that incorporates these new constraints. It’s using the exact same codebase in both of the above videos, adapting as necessary to each situation. This kind of adaptive learning behavior is something that humans do all the time, and it’s going to be an essential skill as mobile robots enter the unstructured environments of our homes and offices. 

For Krang to actually do this kind of thing in a real unstructured environment, it’ll have to be weaned off of a six-camera overhead vision system and some pre-programmed manipulation policies, but that’s what the researchers are working on next. And as for the best way to keep a robot from going where you don’t want it to, I’d recommend a closed door with a round knob followed by a flight of stairs covered in black carpet. That should keep most of them out—for now.

“Navigation Among Movable Obstacles With Learned Dynamic Constraints,” by Jonathan Scholz, Nehchal Jindal, Martin Levihn, Charles L. Isbell, and Henrik I. Christensen from Google DeepMind and Georgia Tech was presented this month at IROS 2016 in South Korea.

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

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

"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.

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