Flexible Muscle-Based Locomotion for Bipedal Creatures on HackerTube: recommended by 1 Hacker News commenter across 1 month, 2017–2022.
demo · intermediate · evergreen
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.
“Which made me revisit this classic”
8 Hacker News comments link this video. Each one links back to its thread.
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: ▶ this video
in “Discovering Diverse Athletic Jumping Strategies” · View on HN
There is a paper on two-legged animals learning different methods of walking: ▶ this 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.
in “Java in the Browser” · View on HN
swangin.mp4 AKA "Flexible Muscle-Based Locomotion for Bipedal Creatures" also has a similar vibe: ▶ this video
in “Evolved Virtual Creatures (1994)” · View on HN
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: ▶ this video
in “Tesla Announces a Humanoid Robot “Tesla Bot”” · View on HN
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] ▶ this video [2] [link]
in “Researchers simulate a quadruped robot crossing a balance beam” · View on HN
This seems very useful work. But I wonder why it took so long to get here since [1] was published. [1] ▶ this video
in “Scalable Muscle-Actuated Human Simulation and Control” · View on HN
This was from 2013: ▶ this video I'm wondering what challenges we have solved since then, beside the mechanical implementation.
in “Getting some air, Atlas? [video]” · View on HN
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: ▶ this video Looks much smoother, because of muscle and nerve simulations. At 0:55 you can see the generations learning how to walk.
in “Google's DeepMind AI just taught itself to walk” · View on HN