Technology 3 min read

Robots Get MacGyver-Esque Problem-Solving Skills

Robots are training to learn how to make the tools they need to solve a problem using available resources and some MacGyver-like skills.

Image courtesy of Shutterstuck

Image courtesy of Shutterstuck

The title character of the hit TV show MacGyver was a quintessential 80s action hero.

Angus MacGyver, played by actor Richard Dean Anderson, was a secret agent with a never-ending supply of pseudo-scientific tricks, and a fair share of cheesy lines.

With whatever stuff that happens to be lying around, MacGyver could knock together something to save the day. He can disarm a nuclear bomb with a simple paperclip!

Some people can find themselves in a critical situation that requires MacGyver-like skills. It happened during the Apollo 13 mission in 1970, for example.

The three astronauts used socks, suit parts, plastic bag, duct tape, and other random stuff to construct a carbon dioxide filter to save their lives.

It took the Apollo 13 astronauts several days to assemble the makeshift filter as they received step-by-step instructions. But what if they had robots to instruct them or build it for them?

Tool-MacGyvering Robots

The Robot Autonomy and Interactive Learning (RAIL) at Georgia Tech is a research lab with many projects on robotic systems that can interact with, adapt to, and learn from human environments.

One of the projects focuses on imparting robots with tool-making and problem-solving skills, à la MacGyver: Tool MacGyvering, Autonomous Tool Construction Using Geometric and Attachment Reasoning.

Inspired by the Apollo 13 incident, RAIL researchers set out to make robots able to understand the problem at hand and solve it using available resources.

“This work looks at enabling robots to construct tools using parts available to them when the tools that they need for a task are either inaccessible or just unavailable to the robot,” says Georgia Tech Ph.D. student Lakshmi Nair in the video below.

Crafty and resourceful robots would assist humans in some decision-making and time-sensitive tasks. Besides, robots don’t let the gravity of the situation impair their judgment.  Nair said:

“We’d like robots to be able to assist humans in these situations by suggesting possible solutions. And since robots are often free of the cognitive stress humans often encounter in these situations, they can come up with interesting solutions that might work.”

The MacGyver Test

Today’s robots can use some tools or can be programmed to make some predefined tools. But they can’t make the tools they need for a specific situation they’d encounter in the complex human environments.

RAIL’s tool MacGyvering project promises robots able to construct complicated builds in the future, but it’s not the only research effort in this regard.

A team at Tufts University proposed The MacGyver Test, an evaluation framework to assess robots’ MacGyver-Esque creativity, as a practical alternative to the Turing Test.

This framework is intended “to answer the question of whether embodied machines can generate, execute, and learn strategies for identifying and solving seemingly-unsolvable real-world problems.”

“The idea is to present an agent with a problem that is unsolvable with the agent’s initial knowledge and observing the agent’s problem-solving processes to estimate the probability that the agent is being creative.”

Read More: Origami-Inspired Rollbot Could Be The Future Of Soft Robots

Found this article interesting?

Let Zayan Guedim know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Zayan Guedim

Trilingual poet, investigative journalist, and novelist. Zed loves tackling the big existential questions and all-things quantum.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.