[xVedun]

This looks very cool! I wonder how close it is to the method that Boston Dynamics uses to control the their version. Did they simply train a machine learning algorithm for way longer than a hobbyist can or is there a ton of manual tweaking?

[317070]

Boston Dynamics (famously) does not use machine learning to control their robots. Maybe a little bit of computer vision, but all control is with more classical approaches.

[gene-h]

Boston Dynamics probably does some form of force control. That is controlling the force applied to the ground by the legs in addition to just the position the leg is moving. The actuators here appear to be purely position controlled.

[nicrusso7]

yeah the current motor model takes the desired position as input and convert it to torque (applying some 'noise' trying mimic the real motors).

[nicrusso7]

thanks! well, good question. I think it's a mix between ML (probably not just simulations but also directly learn from real-world experiences) and more classic approaches. There are some very interesting examples on the Google AI blog like this one (https://ai.googleblog.com/2020/04/exploring-nature-inspired-...)