New York Tech Media
  • News
  • FinTech
  • AI & Robotics
  • Cybersecurity
  • Startups & Leaders
  • Venture Capital
No Result
View All Result
  • News
  • FinTech
  • AI & Robotics
  • Cybersecurity
  • Startups & Leaders
  • Venture Capital
No Result
View All Result
New York Tech Media
No Result
View All Result
Home AI & Robotics

MIT Engineers Showed a Robotic Cheetah How to Take One Giant Leap

New York Tech Editorial Team by New York Tech Editorial Team
October 22, 2021
in AI & Robotics
0
MIT Engineers Showed a Robotic Cheetah How to Take One Giant Leap
Share on FacebookShare on Twitter

The Massachusetts Institute of Technology (MIT) engineers have developed a ‘mini cheetah’ that can jump over irregular gaps with high speed and agility — and it can do it all in real-time!

The engineers installed a new technology that relies on a real-time video sensor that detects potential obstacles like gaps and holes and interprets them into instructions on how the cheetah should act to make this possible, according to an MIT press release. This vision system focuses on the depth of incoming terrain, which is sent into a neural network that “learns” from the experience and sends a target trajectory to a low-level controller that handles the bot’s 12 joints based on physical equations that describe the motion.

The innovative two-part technology means that the robot can go anywhere without needing to map the terrain first. And in the future, this could allow robots to venture into the woods on an emergency response mission or climb stairs to deliver medication to those in need.

An algorithm that ‘sees’

The researchers merged the best aspects of these robust, blind controllers with a separate module that handles vision in real-time to create their system.

“The hierarchy, including the use of this low-level controller, enables us to constrain the robot’s behavior so it is more well-behaved. With this low-level controller, we are using well-specified models that we can impose constraints on, which isn’t usually possible in a learning-based network,” explains Gabriel Margolis, a Ph.D. student in the lab of Pulkit Agrawal, professor in the Computer Science and Artificial Intelligence Laboratory at MIT, who took part in the study.

To train the neural network (high-level controller), the researchers utilized a trial-and-error method known as reinforcement learning by running simulations of the robot running across hundreds of different irregular terrains and rewarding it for successful crossings. This enabled the algorithm to learn which actions to do to get the most reward.

Then, the experiment was carried to the real world by using a set of wooden planks. They made a physical terrain and tested their control system with the mini cheetah, and it successfully traversed 90 percent of the terrains.

 

This comes hot on the heels of the news that researchers have attached a gun to a robotic dog just a week ago. And with robotics technologies advancing at this rate, it’ll probably only be a matter of time before the cheetah leaps out of the lab.


Credit: Source link

Previous Post

Home Alone is now a $250 Lego set, and it might be the most impressive fan-inspired model yet

Next Post

Climate crisis brings venture capital money back to clean tech

New York Tech Editorial Team

New York Tech Editorial Team

New York Tech Media is a leading news publication that aims to provide the latest tech news, fintech, AI & robotics, cybersecurity, startups & leaders, venture capital, and much more!

Next Post
Climate crisis brings venture capital money back to clean tech

Climate crisis brings venture capital money back to clean tech

  • Trending
  • Comments
  • Latest
Meet the Top 10 K-Pop Artists Taking Over 2024

Meet the Top 10 K-Pop Artists Taking Over 2024

March 17, 2024
Clubhouse will soon let you pin links to the top of rooms

Clubhouse will soon let you pin links to the top of rooms

October 23, 2021
10 Raunchy Movies on Netflix You Won’t Regret Watching

10 Raunchy Movies on Netflix You Won’t Regret Watching

May 20, 2024
Panther for AWS allows security teams to monitor their AWS infrastructure in real-time

Many businesses lack a formal ransomware plan

March 29, 2022
Zach Mulcahey, 25 | Cover Story | Style Weekly

Zach Mulcahey, 25 | Cover Story | Style Weekly

March 29, 2022
How To Pitch The Investor: Ronen Menipaz, Founder of M51

How To Pitch The Investor: Ronen Menipaz, Founder of M51

March 29, 2022
Startups On Demand: renovai is the Netflix of Online Shopping

Startups On Demand: renovai is the Netflix of Online Shopping

2
Robot Company Offers $200K for Right to Use One Applicant’s Face and Voice ‘Forever’

Robot Company Offers $200K for Right to Use One Applicant’s Face and Voice ‘Forever’

1
Menashe Shani Accessibility High Tech on the low

Revolutionizing Accessibility: The Story of Purple Lens

1

Netgear announces a $1,500 Wi-Fi 6E mesh router

0
These apps let you customize Windows 11 to bring the taskbar back to life

These apps let you customize Windows 11 to bring the taskbar back to life

0
This bipedal robot uses propeller arms to slackline and skateboard

This bipedal robot uses propeller arms to slackline and skateboard

0
Bloom Security and Cyera Turn Data Classification into Real-Time Enforcement at the Endpoint

Bloom Security and Cyera Turn Data Classification into Real-Time Enforcement at the Endpoint

October 22, 2026
Pluto Security Emerges From Stealth With $42M in Funding After Building an AI Security Community

Pluto Security Emerges From Stealth With $42M in Funding After Building an AI Security Community

October 13, 2026
man ordering at a drive thru

Accents, Engine Noise and “No Pickles”: Inside the Hardest Job in Voice AI

October 4, 2026
Essential Car Care Tips for Better Performance and Longer Life

Essential Car Care Tips for Better Performance and Longer Life

October 1, 2026
EB1A graphic design

EB1A Experts Surpasses 330+ Approvals Milestone Amid Rising 2026 EB-1A Approval Rates

September 30, 2026
Upwind team

Upwind Brings Aegis Into Its Cloud and AI Security Platform With New AI Labs

September 23, 2026

Recommended

Bloom Security and Cyera Turn Data Classification into Real-Time Enforcement at the Endpoint

Bloom Security and Cyera Turn Data Classification into Real-Time Enforcement at the Endpoint

October 22, 2026
Pluto Security Emerges From Stealth With $42M in Funding After Building an AI Security Community

Pluto Security Emerges From Stealth With $42M in Funding After Building an AI Security Community

October 13, 2026
man ordering at a drive thru

Accents, Engine Noise and “No Pickles”: Inside the Hardest Job in Voice AI

October 4, 2026
Essential Car Care Tips for Better Performance and Longer Life

Essential Car Care Tips for Better Performance and Longer Life

October 1, 2026

Categories

  • AI & Robotics
  • Benzinga
  • Cybersecurity
  • FinTech
  • New York Tech
  • News
  • Startups & Leaders
  • Venture Capital

Tags

AI AI QSRs AI security Automat-it AWS B2B marketing Bloom Security Business CISO CISO Whisperer Collaborations Companies To Watch Cybersecurity Drive-Thru Enterprise AI Entrepreneur Fetcherr Finance FINQ Fintech Funding Announcement Hi Auto HumanX Impala Investing Investors investorsummit israelitech Mate Security Mindset Minnesota omri hurwitz Perion PointFive PR QSR Real Estate start- up startupnation Startups Startups On Demand Tech Tech leaders VC venture capital
  • Contact Us
  • Privacy Policy
  • Terms and conditions

© 2024 All Rights Reserved - New York Tech Media

No Result
View All Result
  • News
  • FinTech
  • AI & Robotics
  • Cybersecurity
  • Startups & Leaders
  • Venture Capital

© 2024 All Rights Reserved - New York Tech Media