🎵They call me the wanderer, yeah the wanderer, I roam around around around around🎵 #UWAllen’s Nick Walker & Amal Nanavati wrote in IEEE Spectrum about what they learned from giving robot Kuri autonomy to explore its surroundings University of Washington #WednesdayWander spectrum.ieee.org/wandering-robo…

“This award means so much to me because it recognizes things I did in my career beyond my research that I did not expect to be recognized for.” University of Washington #UWAllen professor Maya Cakmak on her @CRA_WP Anita Borg Early Career Award & making research more inclusive news.cs.washington.edu/2022/09/01/peo…

LLMs encode 1D tokens, vision transformers encode 2D image patches, but what's the right formulation for 6-DoF manipulation transformers? Maybe 3D voxel patches? 🧵Checkout our #CoRL22 paper – PerAct👇 Paper & Colab: peract.github.io

What can language do for robotics? What can robotics do for language? Join us for the LangRob workshop at #CoRL2022!

Super excited to share that I'll be joining the Michigan Robotics Department University of Michigan as an Assistant Professor in Fall 2023! My lab will focus on building interactive autonomy for #robots working with and around people. Spread the word for interested students and collaborators 😎

Ever wondered🤔where does data come from for 𝐎𝐟𝐟𝐥𝐢𝐧𝐞 𝐑𝐞𝐢𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 for 𝐫𝐞𝐚𝐥-𝐰𝐨𝐫𝐥𝐝 𝐫𝐨𝐛𝐨𝐭𝐢𝐜𝐬? Multi-task data is easy to collect and can bridge the generalization gap. Project page: sites.google.com/view/real-orl/ (1/n)

Patrick Lancaster will be presenting our work on proximity sensing for pose estimation during in-hand manipulation today at 15:10 in Room 17 at #IROS2022! paper: arxiv.org/abs/2204.02371 video: youtu.be/Ct9k0mSmAYs

Automatically generate 4000 novel objects and their grasps from only 20 objects? Come and check out our #CoRL22 paper ISAGrasp! Paper: arxiv.org/pdf/2210.13638… Website: sites.google.com/view/implicita…

Excited to share work on generalizable dexterous grasping! The key insight is that creating content in sim can be expensive. By using a generative model to modify shapes, we can generate diverse object content and train policies to grasp unseen objects with a robot hand! 🧵(1/5)

status: roadtrip to Bend to attend ACM UIST. I will be presenting about our software kit for social robots! fun fact: Bend ranks nmbr 3 on US cities with the most craft breweries per capita 🍻 paper: dl.acm.org/doi/10.1145/35… Maya Cakmak Elin Björling ☮️ Allen School UW Human Centered Design & Engineering (HCDE) UW Robotics

Annoyed that existing motion generation systems promise the world but leave you with endless parameter tuning? Announcing Motion Policy Networks (MπNets)! 🤖🦾🪩   Website (code, data): mpinets.github.io Paper: arxiv.org/abs/2210.12209   W/ Adithya Murali, Clemens Eppner, et. al

It's wonderful to finally share ProjectEMAR robot platform. Huge shout out to Maya Cakmak for software development and to patrícia alves-oliveira for pushing this project forward. #teamwork FLEX-SDK: An Open-Source Software Development Kit for #socialrobots dl.acm.org/doi/10.1145/35…

How does Amazon leverage Robotics and AI in production in Fulfillment? I gave a Distinguished Seminar at Carnegie Mellon University detailing our work. Check out the entire talk video here: cs.cmu.edu/calendar/16260… Here's a summary 🧵. (1/n)

I am recruiting PhD students to join us in the Washington Embodied Intelligence and Robotic Development Lab (WEIRD) weirdlab.cs.washington.edu at Allen School. We work on robot learning, especially RL in the real world! Check out tinyurl.com/guptauw for details (1/3)

Let’s do 🍒 Cherry Picking with Reinforcement Learning goodcherrybot.github.io - 🥢 Dynamic fine manipulation with chopsticks - 🤖 Only 30 minutes of real world interactions - ⛔️ Too lazy for parameter tuning = off-the-shelf RL algo + default params + 3 seeds in real world

Robot manipulation fails are the pits. So a team of University of Washington #UWAllen + CMU Robotics Institute researchers developed CherryBot, an efficient, generalizable reinforcement learning system for performing fine manipulation tasks using chopsticks.👇🍒 UW Robotics UW Engineering #UWinnovates

🏆 we are so grateful to receive the Best Paper Award The HRI Conference for our work on robot-assisted social dining for people with motor impairments. This work would have been impossible without Tyler Schrenk! Co-authored w Amal Nanavati, Ethan K Gordon, Siddhartha Srinivasa, Maya Cakmak 🍗

Can we narrow the reality gap for vision-based tactile sensors? We present Tactile Diffusion for generating synthetic tactile images. On real Braille reading task with a DIGIT sensor, a classifier trained with our model outperforms other data adaptation approaches. (1/5)

The cover photo seems familiar! Our MuSHR project is featured as one of 20 best robotics projects powered by Jetson Nano. Here’s what MuSHR has recently been up to: youtu.be/p2XAi_MyYwc UW Robotics Allen School

“No matter what culture we belong to, there are moments at the table that can be compared to a sacred ritual”: patrícia alves-oliveira on #UWAllen researchers’ work with Tyler Schrenk to center dining’s social aspects in robot-assisted feeding systems 🤖🍽️: news.cs.washington.edu/2023/05/18/set… 1/2