@AUTOLab_Cal

Automation Lab @Cal @UCBerkeley directed by Prof. @Ken_Goldberg

 Berkeley, CA
autolab.berkeley.edu/
Joined April 2016
  • Tweets40
  • Following99
  • Followers366
2Media
Reactivating this Twitter account for the AUTOLab @UCBerkeley with 30+ brilliant students advancing research in robotics and automation advised by Prof @Ken_Goldberg affiliated w/Berkeley AI Research (BAIR) Lab @Berkeley_AI, @BerkeleyIEOR, @Berkeley_EECS autolab.berkeley.edu
3
19
Very cool work on leveraging German Shepherd mocap data to learn style rewards!
Alejandro Escontrela
@alescontrela30 Mar 2022
Excited to present our recent work which leverages 4.5s of mocap data to train policies that exhibit natural locomotion strategies, complete tasks, and overcome Sim2Real. All without requiring complex reward functions Link: bit.ly/3hpvbD6 (1/6)
1
JAXopt v0.2 is out! github.com/google/jaxopt/rel… The main highlight of this release is an implementation of OSQP, a GPU-friendly quadratic programming solver. Our implementation of course supports implicit differentiation ;) Thanks to our intern Louis Béthune for the hard work.

Release jaxopt-v0.2 · google/jaxopt

New features Quadratic programming solvers jaxopt.CvxpyQP, jaxopt.OSQP, jaxopt.BoxOSQP and jaxopt.EqualityConstrainedQP Iterative refinement New examples Resnet example with Flax and JAXopt. Bu...

github.com
5
38
1
209
Kudos to @obviousvc for demonstrating something far from obvious: progressive values and profitable ventures can be highly compatible.
Obvious Ventures
@obviousvc30 Nov 2021
We're optimistic about the near future. One in which values-based leaders are reimagining trillion-dollar sectors while delivering extraordinary impact. To us, the idea is obvious. Come see why in our 2021 World Positive Report. obvious.com/wpr2021
1
5
Mark your calendars for this NeurIPS workshop on 12/13
Ashwin Balakrishna@ashwinb969 Dec 2021
Interested in safe and robust learning for control? Come check out our NeurIPS 2021 Workshop on Safe and Robust Control of Uncertain Systems (Website: sites.google.com/view/safe-r……) on 12/13 from 8 AM - 4 PM PST! You can register here: neurips.cc.

SafeRL 2021

Call for Papers Control and decision systems are becoming a ubiquitous part of our daily lives, ranging from serving advertisements on the internet to controlling autonomous physical systems such as...

sites.google.com
2
Interested in safe and robust learning for control? Come check out our NeurIPS 2021 Workshop on Safe and Robust Control of Uncertain Systems (Website: sites.google.com/view/safe-r……) on 12/13 from 8 AM - 4 PM PST! You can register here: neurips.cc.

SafeRL 2021

Call for Papers Control and decision systems are becoming a ubiquitous part of our daily lives, ranging from serving advertisements on the internet to controlling autonomous physical systems such as...

sites.google.com
1
8
3
27
AUTOLab retweeted
Max Fu
@letian_fu2 Dec 2021
Can a robot teach itself to grasp complex objects? Learned Efficient Grasp Sets (LEGS) can help robots efficiently learn to grasp novel, out-of-distribution objects. Research from @AUTOLab_Cal @UCBerkeley. Paper, website: sites.google.com/view/legs-e… (1/8)
1
12
2
20
Thank you @Ini_fadelli for a great summary of our work on this new robotics problem with @ToyotaResearch @AUTOLab_Cal techxplore.com/news/2021-11-… @techxplore_com

Real2sim2real: A self-supervised learning technique applied to planar robot casting

Over the next few decades, robots could be introduced into human environments, including homes, offices and retail spaces. Among other things, robotic systems could be used to tidy up spaces and make...

techxplore.com
7
28
Robots can be designed to be symbiotic with workers, freeing us to focus on the myriad of tasks AI can’t do well. Proud that this is an axiom for @AmbiRobotics.
AmbiRobotics@AmbiRobotics23 Nov 2021
We always ask ourselves: how does this make the user feel? We remain rooted in our core beliefs as we rapidly deploy #AI-powered #sorting systems throughout the #supplychain. We see #robots as smart tools, empowering people to handle more than ever before.
1
1
18
What’s the future of food? Polyculture farming is more sustainable than monoculture, but requires more labor. Could robots help? New results w/ AlphaGarden using “Real2Sim2Real” learning from @AUTOLab_Cal @UCBerkeley. Data, paper, and presentation: sites.google.com/berkeley.ed… (1/9)
2
10
18
Unlike fly-fishing, shuffleboard, and bowling, Planar Robot Casting allows self-supervised learning. This real-world robot control problem includes nondeterminism, surface friction, and deformable materials, and it's relatively easy to set up; hoping others study it also:
Raven Huang@RavenHuang49 Nov 2021
Planar Robot Casting for deformable materials aims to achieve a desired final state from one dynamic launching action. Our work from @AUTOLab_Cal @Berkeley_AI learn it using a self-supervised “Real2Sim2Real” framework. Data, paper, and presentation: tinyurl.com/robotcast (1/8)
4
30
Planar Robot Casting for deformable materials aims to achieve a desired final state from one dynamic launching action. Our work from @AUTOLab_Cal @Berkeley_AI learn it using a self-supervised “Real2Sim2Real” framework. Data, paper, and presentation: tinyurl.com/robotcast (1/8)
2
7
1
20
Come check out our poster (3-15) at #CoRL2021 tomorrow evening!
Michael Laskey@Michaellaskey78 Nov 2021
Excited to present our work at #CoRL2021 this week. Our paper shows a promising approach to achieve sim2real transfer for perception. w/ @ToyotaResearch @berkeley_ai (1/7) sites.google.com/view/simnet…
2
4
Fun to be in London with @jeff_ichnowski @ashwinb96 @brthananjeyan @ryan_hoque @yahavigal @AleEscontrela & Justin Kerr from @AUTOLab_Cal checking out @anickali’s elegant floating robots @tatemodern, eating Yorkshire pudding and looking fwd to robotics rendezvous this week:
Conference on Robot Learning@corl_conf6 Apr 2021
The Conference on #Robot #Learning 2021 will be held on Nov 8-11 in London, UK & virtually. Exciting new changes, including: - both regular and blue sky paper submission types, and - use of #openreview June 18th is the submission date! Find out more: robot-learning.org/
6
29
Why is generalization hard in RL? Can "just adding more data" fix it? Turns out that in general, the answer is no. In a new blog post, @its_dibya discusses this question: bair.berkeley.edu/blog/2021/… Trying to generalize induces a POMDP, even if the problem is an MDP!

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

The BAIR Blog

bair.berkeley.edu
3
76
8
343
An inspiring talk by @Ken_Goldberg from @Cal_Engineer on robot assisted surgery. @imperialcollege
3
1
26
It’s notoriously difficult to model the mechanics of compliant robot jaw tips during grasping! We found that a new tool from computer graphics can help. IPC-GraspSim, from @AUTOLab_Cal @UCBerkeley. Paper, data, video: sites.google.com/berkeley.ed… (1/9)
1
10
2
40
📝 The graduate admission application is open! 📆 Deadlines: ✔️ PhD: 12/1/21 ✔️ MIMS: 1/6/22 ✔️ 5th Year MIDS: Early (app fee waived!) - 11/4/21; Final - 3/2/22 ✔️ MIDS & MICS: rolling throughout the year! Grad app: bit.ly/3zsoOVZ
1
2
1
8
Great paper from our lab on grasping transparent objects will be presented at @corl_conf in London next month
Yahav Avigal@yahavigal28 Oct 2021
To help robots grasp transparent objects such as glassware and test-tubes, Dex-NeRF combines grasp analysis from Dex-Net with Neural Radiance Fields (NeRF). To appear in #CoRL2021 @UCBerkeley @Berkeley_AI @AUTOLab_Cal. Data, paper, and video: sites.google.com/view/dex-ne… (1/10)
2
“…What started in 2017 as an email discussion and later a Facebook Group has grown into a global movement of 3,800 members in more than 50 countries. Black in AI works in academics, advocacy, entrepreneurship, financial support, and summer research programs.”
This Post is from an account that no longer exists. Learn more
7
30
'basketball_in_hoop'; one of many new tasks joining the #RLBench family of 100+ tasks in V1.2. Coming early November! 🤖 RLBench is still the hardest manipulation sim-benchmark to date due to its large-scale focus on vision, sparse rewards, and multi-stage tasks.
16
101
Load more