Sim-to-Real: Learning Agile Locomotion For Quadruped Robots — mentioned by nicrusso7

Mon, 27 Jan 2020 22:30:30 GMT

Well the very first attempt this guys made (https://arxiv.org/pdf/1804.10332.pdf#subsection.6.1) was let the model learn from scratch (open loop, large bounds feedback). An agile galloping gait emerged automatically also in my simulation (https://github.com/nicrusso7/rex-gym#galloping-gait---from-s...), even if the gait was 'noisy'

Paper and discussion history. A mention is not an endorsement.

Sim-to-Real: Learning Agile Locomotion For Quadruped Robots — mentioned by candiodari

Fri, 16 Nov 2018 14:08:49 GMT

There have been quite a few papers on this probem. If you don't get your simulator AND your cost function right ... fun things happen. Things you probably didn't intend. Last year someone made a compilation paper about a series of fun techniques algorithms have used to satisfy the demands of their creators ... while not solving the problem. It was featured in popular mechanics. https://www.popularmechanics.com/technology/robots/a19445627... The way to solve it is something engineers hate for some reason. You explicitly design (and simulate) VERY bad hardware. What's bad hardware ? A camera…

Paper and discussion history. A mention is not an endorsement.

Sim-to-Real: Learning Agile Locomotion For Quadruped Robots · HackerPapers discussions

Sim-to-Real: Learning Agile Locomotion For Quadruped Robots — mentioned by nicrusso7

Sim-to-Real: Learning Agile Locomotion For Quadruped Robots — mentioned by candiodari