Somewhat jarring but really good (contradictory, I know) presentation format. A few tweaks and it would be perfect. Very nice project too.
RoboAgent: A universal agent with 12 Skills
11–20 of 23 posts
Re: RoboAgent: A universal agent with 12 Skills
#12Examples given are so underwhelming it actually kills my enthusiasm for robotics. Post comparible results to Boston Dynamics or you’re old news.
Where can I find Boston Dynamics' GitHub for open source resources I can use in my own products?
Re: RoboAgent: A universal agent with 12 Skills
#13Examples given are so underwhelming it actually kills my enthusiasm for robotics. Post comparible results to Boston Dynamics or you’re old news.
This is a negative comment that adds little to the conversation and belittles hard work being done. Comments like this is why many people are afraid to share their efforts - I ask that you consider people on the other side of the screen.
Also, Boston Dynamics largely uses classical non deep learning techniques. We're still exploring AI and deep learning techniques to hopefully create such performance.
Re: RoboAgent: A universal agent with 12 Skills
#14The 12 skills are
- Flap open/close (oven door)
- Slide open/close (drawer)
- Slide in/out (slideable shelf)
- Cap open/close (screw caps)
- Pick/place (for relatively easy situations on flat surfaces, not bin picking)
- Wipe
"Wipe" doesn't have a reverse operation, and #12 is not illustrated.
The main thing here is that the robot has much force sensing, and interpreting that data is hard. So they had people do this with a teleoperator with force feedback, and fed that into a machine learning system. What this is really about is how to use force feedback data effectively. People have struggled with this for key-in-lock and part assembly for decades.
Seems like good work on a longstanding hard problem, but not a breakthrough.
Re: RoboAgent: A universal agent with 12 Skills
#15Examples given are so underwhelming it actually kills my enthusiasm for robotics. Post comparible results to Boston Dynamics or you’re old news.
Can a Boston Dynamics robot do these tasks if you just ask it?
Re: RoboAgent: A universal agent with 12 Skills
#16The 12 skills are - Flap open/close (oven door) - Slide open/close (drawer) - Slide in/out (slideable shelf) - Cap open/close (screw caps) - Pick/place (for relatively easy situations on flat surfaces, not bin picking) - Wipe "Wipe" doesn't have a reverse operation, and #12 is not illustrated. The main thing here is that the robot has much force sensing, and interpreting that data is hard. So they had people do this…
> "Wipe" doesn't have a reverse operation
Wax on/Wax off obviously.
Re: RoboAgent: A universal agent with 12 Skills
#17Examples given are so underwhelming it actually kills my enthusiasm for robotics. Post comparible results to Boston Dynamics or you’re old news.
This is a negative comment that adds little to the conversation and belittles hard work being done. Comments like this is why many people are afraid to share their efforts - I ask that you consider people on the other side of the screen. Also, Boston Dynamics largely uses classical non deep learning techniques. We're still exploring AI and deep learning techniques to hopefully create such performance.
Quite the contrary, I think such comments are sorely needed in AI and its intersection with robotics. If we have a problem in Deep Learning today it’s that we’re over sharing. There are a ridiculous number of papers, and none of them add any value whatsoever to the literature. We’ve gone past the stage where people are sharing small incremental results and clogging the space, now they’re actively covering up their lack of new results with nice presentation, acronyms, buzzwords and making a paper out of it. We really need to be discouraging every run of the mill result from being published as a paper, and holding high standards for them (like say Boston Dynamics Tier) doesn’t seem like a bad idea!
Re: RoboAgent: A universal agent with 12 Skills
#18Earlier quoted context omitted.
This is a negative comment that adds little to the conversation and belittles hard work being done. Comments like this is why many people are afraid to share their efforts - I ask that you consider people on the other side of the screen. Also, Boston Dynamics largely uses classical non deep learning techniques. We're still exploring AI and deep learning techniques to hopefully create such performance.
Quite the contrary, I think such comments are sorely needed in AI and its intersection with robotics. If we have a problem in Deep Learning today it’s that we’re over sharing. There are a ridiculous number of papers, and none of them add any value whatsoever to the literature. We’ve gone past the stage where people are sharing small incremental results and clogging the space, now they’re actively covering up their la…
This work (RoboAgent) is not a run of the mill result. It might look not as shiny as Boston Dynamic does the demos, but it's an actual improvement of what's possible.
One of the biggest issues with Robotics is that it's really hard to program the robots. The ability to set the tasks to a robot with a language brings the complexity down and makes it potentially accessible to regular people. We are not there yet, but RoboAgent is a fine step towards that direction.
Let's hope that the code will be released soon as promised at https://github.com/robopen/roboagent/. RoboAgent is much better than RT-1, and comparable to RT-2. But the latter is not open-source, and so has a limited usefulness in advancing the state of art (unfortunately).
Dismissing great results only because they don't have a video with $100k production budget is not what science is about.
Re: RoboAgent: A universal agent with 12 Skills
#19Examples given are so underwhelming it actually kills my enthusiasm for robotics. Post comparible results to Boston Dynamics or you’re old news.
I don't think Boston Dynamics robots can do any of this on their own. The key here is that these skills are learned in a general manner. Nothing like the pre-programmed hard-coded choreography demonstrated by Boston Dynamics (which is still extremely impressive).
Re: RoboAgent: A universal agent with 12 Skills
#20The 12 skills are - Flap open/close (oven door) - Slide open/close (drawer) - Slide in/out (slideable shelf) - Cap open/close (screw caps) - Pick/place (for relatively easy situations on flat surfaces, not bin picking) - Wipe "Wipe" doesn't have a reverse operation, and #12 is not illustrated. The main thing here is that the robot has much force sensing, and interpreting that data is hard. So they had people do this…
Still no nunchuck skills, bowhunting skills, computer hacking skills...