HackerTube

Flexible Muscle-Based Locomotion for Bipedal Creatures

Goatstream1 HN recommenders · 2017–2022
1.9M views · demo · evergreen · Uploaded 2013-11-25

A 2013 research demo of simulated bipedal creatures whose natural gaits are found by optimizing muscle-based controllers, with no motion capture or keyframe animation. It shows physics-based walking and running emerging from musculoskeletal models.

HN cites it as an earlier, smoother precedent whenever new learned-locomotion or simulated-walking work appears.

Animation & visual effectsRoboticsComputer graphics & rendering

Watch on YouTube

8 comments from Hacker News

@anotheryou2017 · in “Google's DeepMind AI just taught itself to walk”

Clearly needs some energy constraint factored in to look less like monty python :) I also wonder if the gravity is realistic. A similar video from 2013: [VIDEO] Looks much smoother, because of muscle and nerve simulations. At 0:55 you can see the generations learning how to walk.

CitesView on HN
@amelius2018 · in “Getting some air, Atlas? [video]”

This was from 2013: [VIDEO] I'm wondering what challenges we have solved since then, beside the mechanical implementation.

CitesView on HN
@amelius2019 · in “Scalable Muscle-Actuated Human Simulation and Control”

This seems very useful work. But I wonder why it took so long to get here since [1] was published. [1] [VIDEO]

CitesView on HN
@amelius2020 · in “Researchers simulate a quadruped robot crossing a balance beam”

Since we have machine-learning based walking models for several years now, see e.g. [1] or [2], I'm wondering why walking isn't yet a solved problem by now (?) [1] [VIDEO] [2] [LINK]

CitesView on HN
@npilk2021 · in “Discovering Diverse Athletic Jumping Strategies”

Very interesting. I guess it shouldn't be too surprising that the Fosbury Flop seems to be the optimal high jump method, even if it wasn't developed until the 1960s. I didn't see the link to the video with animations at first! It's here in case anyone else missed it: [LINK] Which made me revisit this classic: [VIDEO]

RecommendsView on HN
@elihu2021 · in “Tesla Announces a Humanoid Robot “Tesla Bot””

I would hope that they can use a framework that's general enough to adapt to other form factors. So, making a humanoid is a way of giving themselves a difficult enough initial problem that they're less likely to be fooled by early success: the humanoid robot will have to self-balance, walk, open doors, and do a lot of the complex things that humans do without thinking in order to be considered a minimum-viable product. In the long run if this pans out, I'd expect to see farming and weeding hexapods, equipment-hauling centaurs, wheeled platforms with arms for getting around office spaces, construction bots with long-fingered hands and asymmetrical multi-jointed appendages, and so on. If the AI has a general capacity for motor-skill learning, then you can just give it whatever body is most optimal for the task at hand. I'm reminded of this video on training an AI to walk through simulation: [VIDEO]

CitesView on HN
@rzzzt2022 · in “Evolved Virtual Creatures (1994)”

swangin.mp4 AKA "Flexible Muscle-Based Locomotion for Bipedal Creatures" also has a similar vibe: [VIDEO]

CitesView on HN
@rzzzt2022 · in “Java in the Browser”

There is a paper on two-legged animals learning different methods of walking: [VIDEO] (or [LINK] for the slightly better known "music video" version). Soda Constructor's wikipedia page also links to a 3D applet named "Springs World 3D", I was playing with that one back in the day.

CitesView on HN