Ask HN: What are the modern approaches to robotic control?

#1

Post by bistable » Wed, Jun 08, 2016, 6:43 PM UTC

I'm eager to find references on modern approaches to robotic control.

The coordinated robots from Boston Dynamics (acquired by Google) impress the most, with their ability to react quickly to perturbation and move competently over difficult terrain.

I assume they are not solving inverse kinematics problems continuously, and also assume that much of their progress was made before the deep learning revolution, so maybe they don't even use neural networks either.

So are they using any reinforcement learning? I have no idea so would appreciate any quick summaries or pointers to relevant information.

What other companies are working in robotics at the same level as Boston Dynamics?

Approaches to robot perception, path planning (e.g. A*), and environmental mapping (e.g. SLAM) are also very interesting, but not the topics I'm interested in for this question.

Re: Ask HN: What are the modern approaches to robotic control?

#2

Post by sharemywin » Wed, Jun 08, 2016, 7:34 PM UTC

they use something called "force control" which I think uses a spring to act as some kind of tendon.

http://news.nationalgeographic.com/news/2003/03/0311_030313_...

http://web.mit.edu/spotlight/archives/troody.html

Mentions some of the engineers at Boston Dymanics including the inventor of troody. https://prezi.com/tn5kji7ehk3u/prezi-project/

Re: Ask HN: What are the modern approaches to robotic control?

#3

Post by sharemywin » Wed, Jun 08, 2016, 7:38 PM UTC

sharemywin wrote: post #2

they use something called "force control" which I think uses a spring to act as some kind of tendon. http://news.nationalgeographic.com/news/2003/03/0311_030313_... http://web.mit.edu/spotlight/archives/troody.html Mentions some of the engineers at Boston Dymanics including the inventor of troody. https://prezi.com/tn5kji7ehk3u/prezi-project/

more info here:

http://news.mit.edu/2001/dinosaur

We use series elastic actuators, or springs connected to motors, and low-stiffness control, so the joints are looser, and more biological."

HOW IT WORKS Troody, which weighs about ten pounds, has 16 joints and 36 sensors. "Every joint has a position and force sensor," Mr. Dilworth said. The robot also has a vestibular system -- the equivalent of an inner ear -- that it uses for balancing, and an onboard computer that automatically runs a walking control algorithm.

Re: Ask HN: What are the modern approaches to robotic control?

#4

Post by falcolas » Wed, Jun 08, 2016, 7:41 PM UTC

For more generalized information on how you bring a machine from state A to state B, you may want to read up on Control Systems [0], one of which is the PID controller [1]. It's used in everything from industrial water heaters to quadcopters. It wouldn't surprise me to see them also being used at some level with more advanced robotics.

[0] https://en.wikipedia.org/wiki/Control_system [1] https://en.wikipedia.org/wiki/PID_controller

Re: Ask HN: What are the modern approaches to robotic control?

#5

Post by sharemywin » Wed, Jun 08, 2016, 7:43 PM UTC

sharemywin wrote: post #3

sharemywin wrote: post #2

they use something called "force control" which I think uses a spring to act as some kind of tendon. http://news.nationalgeographic.com/news/2003/03/0311_030313_... http://web.mit.edu/spotlight/archives/troody.html Mentions some of the engineers at Boston Dymanics including the inventor of troody. https://prezi.com/tn5kji7ehk3u/prezi-project/

more info here: http://news.mit.edu/2001/dinosaur We use series elastic actuators, or springs connected to motors, and low-stiffness control, so the joints are looser, and more biological." HOW IT WORKS Troody, which weighs about ten pounds, has 16 joints and 36 sensors. "Every joint has a position and force sensor," Mr. Dilworth said. The robot also has a vestibular system -- the equivalent of an inner ear -- that i…

some more info:

http://sandbox.softroboticstoolkit.com/book/series-elastic-l...

Re: Ask HN: What are the modern approaches to robotic control?

#6

Post by fudged71 » Wed, Jun 08, 2016, 7:46 PM UTC

falcolas wrote: post #4

For more generalized information on how you bring a machine from state A to state B, you may want to read up on Control Systems [0], one of which is the PID controller [1]. It's used in everything from industrial water heaters to quadcopters. It wouldn't surprise me to see them also being used at some level with more advanced robotics. [0] https://en.wikipedia.org/wiki/Control_system [1] https://en.wikipedia.org/wiki…

One step further for linear motion control systems like CNCs and 3D Printers is a project called TinyG which effectively democratises the application of 6th-order jerk-controlled motion planning in real-time. https://github.com/synthetos/TinyG/wiki

Very natural looking movement from these systems! https://youtu.be/aucE49ZBXx0?t=46

Re: Ask HN: What are the modern approaches to robotic control?

#7

Post by pumpikano » Wed, Jun 08, 2016, 8:50 PM UTC

There is a surge of interest in learning control policies end-to-end. Many of Sergey Levine's recent papers are relevant: http://homes.cs.washington.edu/~svlevine/ (there are also some talks linked there).

Re: Ask HN: What are the modern approaches to robotic control?

#8

Post by stevendhansen » Wed, Jun 08, 2016, 8:52 PM UTC

falcolas wrote: post #4

For more generalized information on how you bring a machine from state A to state B, you may want to read up on Control Systems [0], one of which is the PID controller [1]. It's used in everything from industrial water heaters to quadcopters. It wouldn't surprise me to see them also being used at some level with more advanced robotics. [0] https://en.wikipedia.org/wiki/Control_system [1] https://en.wikipedia.org/wiki…

PID is a generalized control algorithm that performs poorly unless your system is entirely linear. It is overwhelmingly used in industry, however, because it is simple, and anyone can drop in a PID block and adjust three constants to get semi-OK response without understanding anything about the dynamics of the system they are controlling.

For serious control systems you can look up state feedback control, model predictive control, and nonlinear systems control (to name a few very broad categories out of many possible options).

Re: Ask HN: What are the modern approaches to robotic control?

#9

Post by dbcurtis » Wed, Jun 08, 2016, 9:04 PM UTC

Google "underactuated"

Re: Ask HN: What are the modern approaches to robotic control?

#10

Post by npmanor » Wed, Jun 08, 2016, 9:04 PM UTC

If you're interested in walking, the Florida Institute for Human and Machine Cognition (ihmc: http://robots.ihmc.us/) came in second place at the DARPA Robotics Challenge using force control and capture point dynamics. They do primarily software, but their walking is quite stable.