AI learns to WALK 3D (Part 2)

AI learns to WALK 3D (Part 2)

Get an Exclusive NordVPN deal here: It’s risk-free with Nord’s 30-day money-back guarantee!


Art created by

You may also like...

44 Responses

  1. Code Bullet says:

    Thanks again to NordVPN for sponsoring this video. Get an Exclusive NordVPN deal here:
    It’s risk-free with Nord’s 30-day money-back guarantee!

  2. Steven Ingram says:

    I think the proprioception idea is a good one, but I don’t think its enough alone. In us humans, that sense is combined with the inner ear (which conveys a sense or roll, pitch and yaw) and vision (which provides directional targeting). So along with a sense of proprioception, you need to simulate an inner ear and a “cone of vision.” Alas, you would have to train AIs to this task incrementally though. For example – you’d have to start training vision first (where it looks for a target in its cone of vision, and if it’s not there, it turns its head/body until it finds it). The inner ear should already be working for this part of the training (so a sense of perceived direction and range emerges). And once it’s learned to look at a target, then you can then try to train them to walk. As long as they learn to rotate themselves to look at the target first – they should walk forwards towards it.

    Moral of the story? They should look before they leap. 😀

    • BrokenLord321 says:

      Aka make it learn to stand then look at something

    • Steven Ingram says:

      PS. The reason I recommended the cone (instead of trying to calculate a volume of space and identifying objects within it for example) is because I believe the cone approach would simplify the task. If it’s a game object (even if it is invisible and non-clip) you can detect when it interacts with other objects. So the logic reduces to:

      If vision cone interacts with target, then target has been seen.

      But the cool part is, anything in the environment that interacts with that cone the AI can “see.” So it can be aware of and react to more than just the target. 🙂

    • Steven Ingram says:

      ​@themonkeyman2547 I think it was being kind of efficient in its own way… I mean, it technically didn’t exert any effort to get moving, it just fell (backwards) in the right direction and then applied just enough force to keep it stumbling instead of falling down. LOL

    • Martiddy - Sama says:

      @Thedarkbunnyrabbit But having less movements doesn’t necessarily always means consuming less energy. For example, jumping with one leg only probably require less movements than using both legs to walk, but it’s less energy efficient than just walking like a normal person.

    • Thedarkbunnyrabbit says:

      @themonkeyman2547 I was thinking rewarding it for minimal movements made to get to the target would be good to minimize the random flailing. Penalize it for moving away, Penalize it more for falling. Reward it for moving toward the target, reward it more for having its chest face the target, reward it even more the lower the number of moves it has to take to reach the target.

  3. Stupit says:

    Seeing the time lapses of the AI in their individual cubes feels disturbingly dystopian

  4. lightdark00 says:

    Part three? We still need to see them walk like humans.

  5. D.J. Price says:

    Dude! Two videos in less than a week! Oh my GOD. That never happens. Looks like the AI that writes the script for the videos has been fine-tuned quite a bit…

  6. Armand de Sillègue says:

    At 0 hours of training, the AI behaves remarkably like a newborn infant. The movements are random because it has yet to develop “awareness” of its limbs and how to use them. I just thought it was a really interesting comparison.

    • VIBaJ 16 says:

      @Keyser Soju I bet it would eventually learn to use some glitch in the physics system to gain a huge amount of speed

    • Oosh21 says:

      I also trained my kids to walk by punishing them if anything but their feet touched the ground.

    • Visyix says:

      So from the whole beginning I was just an AI

    • RockyRoad Magic says:

      @Keyser Soju I doubt it. Newborns move on to walking eventually because crawling is more tiring, and hurts the hands and knees after a while, and also probably because they see everybody else walking. Without the punishment for parts other than feet touching the ground to simulate the discomfort of the first two reasons, it would not have any reason to stop crawling

    • Keyser Soju says:

      Imagine if he just left the crawling AI to learn for generations, I wonder if any of them would’ve evolved to walking like how a human learn to crawl first then learns to walk.

  7. ShadowDrakken says:

    Give them a reward for moving in the direction of their front, a reward for keeping their shoulder height up (but penalized for shrugging XD), and a penalty that increases the longer their toes are on the ground without their heels also touching the ground, and make them have a vision cone for finding the target they have to move to 😀

    • Adam says:

      Your comment made me realize this is pretty much exactly what pain does for humans.

      Maybe penalize the AI slightly any time it overextends or over taxes its joints? Cause that shit would hurt if a human tried it.

    • Elin Hulldin says:

      @goldfndr Yes, that worked for me. I tried to walk like them and my neck started hurting after 5 seconds, so I turned around.

    • H4PPY says:

      What about friction? Wouldn’t it be easier?

    • goldfndr says:

      No need for a reward for moving in the direction of their front. Instead, penalize exponentially for head pivoting away from neutral.

    • Thk says:

      perhaps the toe stance discouragement could begin if there is 1 to 3 seconds of toe touch without a heel touch (possibly also the reverse to discourage heel walking too) making the foot a little rounded in the back and with a flexible front section (toes) might also help to better match real feet. as for rewarding standing, reward head above shoulders, shoulders above torso, torso above legs, upper arm above lower arm, upper leg above lower leg, lower leg above foot (probably by failure hurting score, rather than success helping it much)

  8. chrayez says:

    I wonder what would have happened if the “touching the floor” punishment were a reduction in score instead of immediate failure…

  9. Bahaa AlRoud says:

    i wanna see a part 3 where they walk like you know humans

  10. Black Ryan says:

    3:42 – I’m saying though…This part was silly. I laughed so hard. But that sound track was pretty epic. Whoever produced that worked really hard. Probably was not anything easy about editing that part of the video either with the timing and all.

Leave a Reply

Your email address will not be published. Required fields are marked *