Marco Pavone

@MarcoPavoneSU

Vrijeme pridruživanja: studeni 2018.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @MarcoPavoneSU

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

  1. 20. pro 2019.

    Cool work with and Apoorva on meta learning for continuous adaptation

    Can we discover structure & meta-learn across it in unsegmented time series data? MOCA simultaneously detects changepoints & meta-learns across time for continuous adaptation Continuous Meta-Learning without Tasks w , Sharma,
    3 proslijeđena tweeta 14 korisnika označava da im se sviđa
    Poništi
  2. 3. stu 2019.

    Great work by !

    About to present the Trajectron, our work on multi-agent trajectory forecasting at ! If you're here, please stop by poster #109 this afternoon! If not, feel free to read the paper at
    Prikaži ovu nit
    2 korisnika označavaju da im se sviđa
    Poništi
  3. 28. lis 2019.

    I look forward to the AI Safety Session I am co-organizing tomorrow at 1-3pm with !

    I am co-organizing the AI Safety Session tomorrow at 1-3pm. Trying to answer "What does safety mean and what should we do about it?" Speakers: , , James Zou, Tino Cuellar, Moses Charikar, Ritchie Lee, Maxime Bouton, and Erika Strandberg.
    1 korisnik označava da mu se sviđa
    Poništi
  4. 30. ruj 2019.

    1 proslijeđeni tweet 5 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    1. kol 2019.

    We provide compelling motivation, from both a stability and data efficiency standpoint, for incorporating control-theoretic notions within learning as a means of context-driven hypothesis pruning. w/ Spencer M. Richards J-J Slotine 2/2

    1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    1. kol 2019.

    New paper (under review) on learning stabilizable dynamics for model-based RL, using control-theoretic regularization: Paper: Videos: Code: 1/2

    1 reply 4 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    25. srp 2019.

    Our gecko grippers are now in space, on their way to the ISS for experiments! Congrats to our fellow team members at , and to and for a successful launch and booster landing!

    1:06
    LIFTOFF! We're sending more than 5,000 pounds of science and supplies to the aboard 's Dragon spacecraft. Watch live:
    2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    22. srp 2019.

    Our paper on probabilistic multi-agent trajectory modeling was accepted to !! Check it out here: and see you in , !!

    3 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    8. svi 2019.

    And finally, we've developed algorithms for theoretically guaranteed robot trajectory optimization on manifolds using sequential convex programming and geometric embeddings. Link coming soon!

    1 proslijeđeni tweet 6 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    8. svi 2019.

    We merge Frank-Wolfe optimization with modern pathfinding techniques to build more efficient algorithms for scalable congestion-aware routing for autonomous mobility-on-demand systems.

    1 reply 1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. svi 2019.

    By combining deep reinforcement learning, cloud computing, and efficient embedded AI devices, we more effectively balance on-robot and cloud computation.

    1 reply 2 proslijeđena tweeta 4 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    8. svi 2019.

    We leverage advances in automatic differentiation and numerical methods to address some of the computational challenges present in problems like parameter estimation and robust control.

    1 reply 1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    8. svi 2019.

    Four papers just accepted to ! Details on each below.

    1 reply 2 proslijeđena tweeta 11 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    25. tra 2019.

    New paper on arXiv! In it, we focus on multi-human trajectory modeling with dynamic spatiotemporal graphs and obtain state-of-the-art results on the ETH and UCY datasets! Check it out here:

    4 proslijeđena tweeta 16 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    10. tra 2019.

    We're excited to announce that ASL is going to space! Working with our collaborators at , we verified the safety of our flight-qualified gecko gripper for the ISS Astrobee robot during EMI and acoustic testing at ! Stay tuned for more!

    7 proslijeđenih tweetova 17 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    15. ožu 2019.

    Today is the culmination of the Principles of Robotic Autonomy course, taught by Prof Marco Pavone. Tune in live to see the students' robots carry out autonomous food deliveries!

    4 proslijeđena tweeta 11 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    9. velj 2019.

    Our work on Guaranteed Sequential Trajectory Optimization (GuSTO) via sequential convex programming is headed to ! With Riccardo Bonalli, , and , pre-print link here: Video here:

    1 reply 4 proslijeđena tweeta 12 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    10. velj 2019.

    Our backward reachability-based curriculum for reinforcement learning will appear at ! Created with my excellent co-authors , , Mo Chen, and , check it out here: See you in Montreal!

    5 proslijeđenih tweetova 19 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    7. velj 2019.

    Our work on optimally trading off robustness, exploration, and exploitation in Bayes-adaptive planning was just accepted at ! With , Matt Tsao, and , link here:

    2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  20. 31. sij 2019.

    Excited to be promoted to Associate Professor with tenure! This is a recognition as much for the entire Stanford Autonomous Systems Laboratory, which I have the honor to direct: I take this opportunity to thank all my collaborators throughout these years.

    2 proslijeđena tweeta 11 korisnika označava da im se sviđa
    Poništi

@MarcoPavoneSU još nije objavio nijedan Tweet.

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:

    ·