Skip to content
Hallway
0:00 / 0:00

#darparoboticschallenge#humanoidrobots#moravec'sparadox

A Compilation of Robots Falling Down at the DARPA Robotics Challenge

IEEE Spectrum

162K subscribers • 4 videos on Hallway

YouTube
  • Recommended by 1 person: 1 on Hacker News.
  • May be out of date. Uploaded 11 years ago, in an area where tools change fast.

Beginner. No background in the topic needed.

3M views11 years ago1 recommendation

AI and machine learningHardwareComputer visionElectronics

A compilation of humanoid robots falling over during the 2015 DARPA Robotics Challenge Finals.

During a dry run before the DARPA Robotics Challenge Finals, not many robots fell over, so we went into Day 1 thinking that falls would be rare. They weren’t, and the possibility of falls kept everyone watching on the edge of our seats. Learn more: spectrum.ieee.org/darpa-robotics-challenge-robots-falling Edited by Erico Guizzo/IEEE Spectrum Footage courtesy of DARPA

Why it's here

1 person recommends this

What people say. Engineers frequently cite this compilation to illustrate Moravec's paradox and the immense difficulty of real-world physical robotics.

FabHKon Hacker News • Recommends

On “Sussman anomaly”

Moravec's paradox - stuff we thought is hard (chess, derivatives) is easy, while stuff we think is easy (face recognition, getting out of a car, opening a door) is really hard. link One of my favourite videos is this compilation of robots falling (failing) during the simplest tasks at the 2015 DARPA challenge: link to this video
View on Hacker News

Vorcin83on Hacker News • Mentions

On “Korea’s Team KAIST Wins the 2015 Darpa Robotics Challenge”

This 1 list of failures shows that some robots seem to "just" have hardcoded motions, for example for turning the valve. 1 link to this video
View on Hacker News

felippeeon Hacker News • Mentions

On “Toyota's Gill Pratt on Self-Driving Cars and the Reality of Full Autonomy”

Yup, there is a boatload of low level knowledge missing from any AI that we build. It is painfully visible with robots (and autonomous cars are robots as well), see DARPA challenge video which was then lead BTW by Gill Pratt: link to this video A lot of stuff we take for granted such a supporting oneself by a nearby wall when loosing balance, is completely out of reach of todays "AI".
View on Hacker News

FabHKon Hacker News • Mentions

On “Real-Time Recognition of Handwritten Chinese Characters”

…out it, that you can just read it. I mean, look at figures 5, 6, 7 in that article. For me, a nice illustration of Moravec's paradox of AI 1: what we think is difficult (chess, differentiation, ...) is easy, and what we think is easy (reading handwriting, putting an egg in the fridge, walking (!) and opening a door 2) is hard... 1 link 2 link to this video ("A Compilation of Robots Falling Down at the 2015 DARPA Robotics Challenge")…
View on Hacker News

Judgmentalityon Hacker News • Mentions

On “2 times 3 can sometimes equal 7 with Android's Neural Network API”

> I'd trust a machine to drive more accurately than most people I see on the highway. Humans aren't special, in fact more often than not we're sloppy, subject to fatigue, and a whole bunch of other negative things. Humans are much, much, much more capable than the absolute state-of-the-art robots when it comes to doing things in an uncontrolled environment. link to this video
View on Hacker News

FabHKon Hacker News • Mentions

On “The singularity is close?”

That reminds me of Moravec's paradox: What we thought was hard and difficult (and indicative of intelligence), such as playing Chess and computing derivatives, is actually quite easy, while a lot of things that we consider trivially easy (distinguish a dog from a cat, pick up an egg, read some squiggly text) are quite hard. link One of my favourite demonstration of that was the 2015 DARPA robot challenge, where one robot after the other failed at such difficult tasks as walking and opening a door. link to this video
View on Hacker News

FabHKon Hacker News • Mentions

On “An electric new era for Atlas”

We've come a long way from the 2015 DARPA Challenge, where the robots succeeded only in falling down: link to this video link
View on Hacker News

FabHKon Hacker News • Mentions

On “An electric new era for Atlas”

The progress since the 2015 DARPA challenge (where robots succeeded mostly in falling down) is impressive. Less than a decade! link to this video link
View on Hacker News

numpad0on Hacker News • Mentions

On “Unitree G1 Humanoid Agent”

It was always software. Humanoid robots could walk up and down stairs and use basic tools, in preprogrammed lab conditions and/or by manual teleoperations since 90s1, and in theory autonomously since 2010s2. Nowadays they just can, thanks to NVIDIA CUDA, but grabbing objects is still sketchy3. 1: link 2: link to this video 3: link
View on Hacker News

marcusveruson Hacker News • Mentions

On “Boston Dynamics shows off another major leap in humanoid mobility”

…lem seems far more doable today than it did 20 years ago, given all the progress we've made in machine vision and machine learning! We'll know that the robotics revolution is truly imminent when the big players start pouring capital into development. Tesla has already joined the fray. I expect more will follow in the next few years. 0 link 1 link to this video…
View on Hacker News