Simon Clavet

@profbof

Animation/Physics Researcher at Ubisoft Montreal

Montreal
Vrijeme pridruživanja: srpanj 2009.

Tweetovi

Blokirali ste korisnika/cu @profbof

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @profbof

  1. Prikvačeni tweet
    13. stu 2019.

    (1/5) Here’s a thread about some fun technology we (with and ), are working on at La Forge (our research lab inside Ubisoft Montreal). The TL;DR is that we trained a self-balancing physics-based character to follow interactive motion capture with DeepRL.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    30. sij

    Boston Dynamics' Atlas shows off its agility with a flawless gymnastic routine. Credit: Boston Dynamics

    Poništi
  3. proslijedio/la je Tweet
    Poništi
  4. 11. pro 2019.

    The trick is to convert inspiration and motivation into discipline. Then into habit.

    Poništi
  5. 14. stu 2019.

    The big highlight of my year was when my blue guy managed to randomly catch a cube:

    Poništi
  6. 14. stu 2019.

    I really hope these guys succeed in changing the language of machine learning. Context switching between c++ and python multiple times per day breaks my brain.

    Poništi
  7. 13. stu 2019.

    (5/5) Next week we’ll present this method at . The paper is titled “DReCon: Data-Driven Responsive Control of Physics-Based Characters”. My colleague Kevin Bergamin wrote a nice blog post with more details:

    Prikaži ovu nit
    Poništi
  8. 13. stu 2019.

    (4/5) If we just give rewards for going at the desired speed, he forgets the motion-captured style and looks a bit silly.🤷‍♂️

    Prikaži ovu nit
    Poništi
  9. 13. stu 2019.

    (3/5) After a day of training, he can withstand significant perturbations (but sometimes you just get too many cubes in the face…):

    Prikaži ovu nit
    Poništi
  10. 13. stu 2019.

    (2/5) randomly controls the white character. The blue ragdoll gets rewards when he follows correctly without falling. Here’s what it looks like while training:

    Prikaži ovu nit
    Poništi
  11. 28. lis 2019.

    I had an interview with an engineering student at Queens University. I talked about research at Ubisoft, , and which games I play with my kids:

    Poništi
  12. 28. lis 2019.

    Fun fact, this website contains a picture of the backside of my left ear:

    Poništi
  13. proslijedio/la je Tweet
    20. ruj 2019.

    Machine Learning, Kolmogorov Complexity, and Squishy Bunnies - why using Machine Learning for things we already know can sometimes make sense.

    Poništi
  14. 9. ruj 2019.

    Simulated robots learned to punch each other:

    Poništi
  15. proslijedio/la je Tweet
    6. srp 2019.

    The humanoid is practicing some kicks.

    Poništi
  16. 6. tra 2019.
    Poništi
  17. proslijedio/la je Tweet
    4. tra 2019.

    Spectacular work from Seoul National University on motion-mimicing DeepRL with a comprehensive full-body musculoskeletal model with 346 muscles, including predictive simulations of post-operative gaits. SIGGRAPH 2019 conditional accept.

    Poništi
  18. 3. tra 2019.
    Poništi
  19. proslijedio/la je Tweet
    28. ožu 2019.

    Boston Dynamics is starting to unveil our efforts in logistics. Find us at Promat (8 - 11 April) in Chicago to learn more - Booth S3347a

    Poništi
  20. 10. ožu 2019.

    Just like religion, the scientific method is a meme. But unlike religion, it doesn't have to use cheap tricks to survive and propagate...

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·