This Is How Close We Are to a Baseball-Playing Robot

High-speed actuators and vision systems will combine to make an unstoppable baseball android

2 min read
This Is How Close We Are to a Baseball-Playing Robot
Image: Ishikawa Watanabe Laboratory

We’ve been writing about robots from the Ishikawa Watanabe Laboratory at the University of Tokyo for years. They’ve always had very cool demos, like robots throwing balls, robots tracking balls, robots catching balls, robots hitting balls, and robots running really really fast

I’d just sort of figured that these demos were simply fun and interesting ways of highlighting the capabilities of high-speed actuators and vision systems.

Evidently, I don’t know anything, because it’s now totally obvious that they’re working on a humanoid robot that plays baseball.

Here’s what the researchers say:

We have been developing robotic systems that individually achieve fundamental actions of baseball, such as throwing, tracking of the ball, batting, running, and catching. We achieved these tasks by controlling high-speed robots based on real-time visual feedback from high-speed cameras. Before integrating these abilities into one robot, we here summarize the technical elements of each task.

“Before integrating these abilities into one robot.” I can’t even put into words how awesome that’s going to be, and putting awesome things into words is (supposedly) my full-time job.

In terms of the sport of baseball, the video above illustrates how much better a robot could be (potentially, of course) than a human. A robot pitcher could throw strikes (or anything else) with pinpoint, repeatable precision. But the advantage would almost certainly go to the robot batter, which will use its high-speed vision to detect spin and track the trajectory of the ball such that it can target the resulting hit anywhere it likes.

I’ll admit to being more of a fan of soccer than of baseball, but it seems that baseball (and sports in general) rely to some extent on randomness and chance to be exciting. When humans play baseball, they don’t have perfect control over where pitches or hits go. If they did, it wouldn’t be much of a game. So the question is, if robots like these start playing baseball, is that going to make the game more interesting, or less?

Either way, we’re incredibly excited to see how this project progresses. The Ishikawa Watanabe Laboratory makes some amazing systems, and putting them all together into a baseball-playing android is going to be the most amazing thing yet.

Ishikawa Watanabe Laboratory ]

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