d3ad social login

[d3ad]

tags labelled 'robot' e

please login to post
@barray on Tue Sep 28 23:01:47 UTC 2021 said: &e
I've seen a very similar #bug in #humanoid #robotics several times, I believe both being due to an insufficient #primitive being used to store #time https://www.hanselman.com/blog/the-code-.. The one that happened most recent was the use of a `long` value to store time, which would overflow and cause the #motion #planning to really get confused and the #robot would try to kill itself in a creative way before #crashing !
@barray on Tue Sep 28 01:02:17 UTC 2021 said: &e
I might try to catch this #hackaday #chat on #robot #dogs - it could be *very* interesting: https://hackaday.com/2021/09/27/robot-do.. This is something I've wanted to build for a while "when I have some time" (a phrase all too common during this #phd ).
@barray on Sun Sep 19 00:36:15 UTC 2021 said: &e
I remember working on a #linefollow #robot for an #undergraduate #course at #university - I essentially ended up developing some kind of very #hacked " #neuralnetwork ": https://hackaday.com/2021/09/18/line-fol.. I hadn't really learned about #pid at this point, but after some time I started to #reinvent the idea of a #pid #controller from scratch. It's really great when we can come to the same conclusions through different methods!
@barray on Tue Aug 24 05:36:13 UTC 2021 said: &e
This #atomic #mech #robot is pretty insane: https://orangebeanindiana.com/2021/04/09.. Sounds like something that could be used in some #war to answer a serious problem, like crossing highly #radioactive land or dealing with some large #vehicle like a #tank ...
@barray on Fri Aug 20 06:09:18 UTC 2021 said: &e
I think #elonmusk has officially bitten off more than he can chew by declaring he will start working on a #humanoid #robot https://electrek.co/2021/08/19/tesla-bot.. He has *absolutely* no idea how much of a #mammoth undertaking it is - arguably its much harder than #autonomous #driving ... Some people are estimating it will take *at least* 5-10 years to get *anything* working at all - and I think that is right. And as for a #market for this robot...
@barray on Sun Aug 01 20:13:03 UTC 2021 said: &e
Very cool #bipedal #robot #demo https://hackaday.com/2021/08/01/ostrich-.. It's a bit of #pr - but still a cool project.
@barray on Mon Jul 26 19:58:57 UTC 2021 said: &e
Cool little #robot #quadruped featured on #hackaday https://hackaday.com/2021/07/26/little-q.. I've had ideas for building something larger for quite a while now. I am quite impressed with the #inversekinematics the robot has. It's a shame the #servos are unreliable - but the idea certainly has legs (pun intended). Robot #dogs rule!
@barray on Wed Jul 21 19:54:07 UTC 2021 said: &e
Very cool #robotics project using a #simulation to improve real-world performance of a #walking #robot https://hackaday.com/2021/07/21/zerobug-.. #zerobug is a very cool #homebuilt robot. Building robots is often easier than people think, it just takes time!
@barray on Fri Jul 16 02:59:51 UTC 2021 said: &e
Very cool #idea for a #robot #tracks https://youtube.com/watch?v=sC1OkWSt5_I
@barray on Sun Jun 20 21:59:49 UTC 2021 said: &e
Very nice #dog #robot for $2700 being publicized over on #ieee https://spectrum.ieee.org/automaton/robo.. A few problems I see though: 1. Zero serious use cases, 2. Very heavy at 12kg, 3. No mention of a programming #api , 4. No mention of #repair or #maintenance (which will be 100% needed after just a few weeks). I feel like the idea of this robot is better than the robot itself.