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 https://t.co/CyMJr5QFvb
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: https://t.co/w0lDgOfE0k
(1/6)
JAXopt v0.2 is out! https://t.co/aMzRcZG3Ky 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.
Interested in safe and robust learning for control? Come check out our NeurIPS 2021 Workshop on Safe and Robust Control of Uncertain Systems (Website: https://t.co/xE8iDYFV1W…) on 12/13 from 8 AM - 4 PM PST! You can register here: https://t.co/14KWRAIJLa.
Interested in safe and robust learning for control? Come check out our NeurIPS 2021 Workshop on Safe and Robust Control of Uncertain Systems (Website: https://t.co/xE8iDYFV1W…) on 12/13 from 8 AM - 4 PM PST! You can register here: https://t.co/14KWRAIJLa.
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: https://t.co/KnJMW4EsaU (1/8)
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.
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: https://t.co/Kjh1Zjn5mG (1/9)
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:
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: https://t.co/bKXQrYWh8e (1/8)
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: https://t.co/FBwQUrosQO
Trying to generalize induces a POMDP, even if the problem is an MDP!
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: https://t.co/3U3nT3FKFz (1/9)
📝 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: https://t.co/Fm1YKVt8Lb
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: https://t.co/0ab9xK9eIK
(1/10)
“…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.”
'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.