Pinned Tweet
In case the cicadas haven't told you, fall is just around the corner.
See what we've done this summer!
Read the latest Michigan Robotics newsletter:
umrobotics.substack.com/p/a-…

ALT Text over a background of a researcher wearing an ankle exoskeleton at the top of a rounded modern concrete staircase in front of the Robotics Building. Text: "A robot that climbs plant stems, knee exoskeleton to ease arthritis, and the public's trust in AI. Plus mentoring almost every FIRST Robotics team in Michigan."
We invite applications and nominations for the position of Department Chair.
Find out more about this position and tenure-track faculty positions:
robotics.umich.edu/about/job…
We invite applicants to join our mission to accelerate advances in robotics for the benefit of society.
We're looking for a new Department Chair to lead in defining the discipline of robotics.
We're also hiring tenure track faculty.
Find out more:
robotics.umich.edu/about/job…
We're looking for a new Department Chair.
And tenure-track faculty.
Join us in our mission of creating the next generation of robotics and roboticists as force-multipliers for the benefit of society.
Learn more and apply: robotics.umich.edu/about/job…
Join our faculty!
@UMRobotics is searching for both:
• A new Department Chair to lead and shape the future of robotics.
• Tenure track faculty in the area of Human-Centered AI.
Get all the information and apply: robotics.umich.edu/about/job…
Michigan Robotics retweeted
SKF is accepted for @NeurIPSConf as spotlight!
Wow, I didn't expect it. Kudos to AC and reviewers for valuing basic research. We feel extra rewarded and motivated!
A tour de force by my student Kaito Iwasaki and collaborators for nonlinear non-Gaussian Bayesian filtering, SKF.
Moment representation + score matching -> solving linear systems. It exactly recovers information from KF for linear-Gaussian systems.
arxiv.org/abs/2605.16644
Michigan Robotics retweeted
NEW ARTICLE: “Small robot propulsion: low-power twisting enables hopping, swimming.”
The mechanism works on challenging surfaces such as slippery cloth and grass-covered ground, producing frog-like motion. news.engin.umich.edu/2026/09…
Michigan Robotics retweeted
Congrats to @XinYe_Eva for her paper receiving the HFES HART Best Student Paper Runner-Up Award!
#HFES2026 @HFES @umsi @UMRobotics #securityrobot
Congrats @XinYe_Eva on a new HFES paper — Trusting Security Robotic Authority
#HFES2026 @HFES
#Robots #Trust @umsi @HRI_Conference @ieeeras @BlackInRobotics @UMRobotics
doi.org/10.1177/107118132614… #HRI
Do you want a robot that’s too confident?
Or one that knows when to be uncertain about what’s ahead?
New work from @TheLuisMarques and @umicharmlab.
Michigan Robotics retweeted
Big congrats to @XinYe_Eva on our new paper, Mitigating Human–Security Robot Conflict Through Fairness. We found that distributive and informational fairness reduce conflict and boost security robot acceptance.
@umsi @UMRobotics @BlackInRobotics
tandfonline.com/doi/full/10.…
Michigan Robotics retweeted
Congrats to MichealNayebare @kwameporterrob1 @roneglash @audreygbennett @guzdial
New paper: "Understanding online conversations through fractal dimension."
@umsi @UMichiganNews @BlackInRobotics @UMRobotics
link.springer.com/article/10…
Michigan Robotics retweeted
We just hit 1000 users on our Open Robotics @zulip server.
Zulip is our open source alternative to Discord.
We migrated late last year and the experience has been nothing short of fantastic; no bots, no spam, and threaded conversations!
⬇️⬇️⬇️
Michigan Robotics retweeted
Healthcare robots for older adults won’t succeed on novelty alone — design matters. Read our new article on the topic! @CarolQiaoning @Jessie_YangXi @umsi @BlackInRobotics @UMRobotics @ieeeras @HRI_Conference
doi.org/10.1007/s12369-026-0…
It's not yet September, but we have #IROS2026 on the mind.
Get tips for visiting Pittsburgh and the latest robotics research from Michigan roboticists in our IROS summary.
Read:
robotics.umich.edu/news/2026…
Michigan Robotics retweeted
We locally calibrate uncertainty in approximate dynamics models! By conditioning on latent observation embeddings, states, and actions, we enable uncertainty-aware planning in u̲n̲s̲e̲e̲n̲ test environments!
More on this @wafr_conf paper w/ @TheLuisMarques @UMRobotics below ⬇
Thank you Ilir for spreading the word! We'll be sharing more courses in the future.
The University of Michigan put their entire robotics degree on GitHub.
Not one course. The whole curriculum.
ROB 101 — Computational Linear Algebra for Robotics
ROB 311 — How to Build Robots and Make Them Move
ROB 501 — Mathematics for Robotics
ROB 530 — Mobile Robotics
Every lecture video on YouTube. Every textbook on GitHub. Every problem set, every exam, every line of code.
Professor Jessy Grizzle said it best when they launched it:
"Linear algebra has become the language of computer vision, machine learning, robotics, and autonomy."
So instead of making students wait four semesters of calculus before touching a robot... they built a curriculum that starts with the math that actually matters, applied to real robotics problems from day one.
This is what open education looks like when a top-10 engineering school decides to mean it.
Free. GitHub. YouTube.
📌 [github.com/michiganrobotics]
Follow for more robotics resources!
——
Weekly robotics and AI insights.
Subscribe free: 22astronauts.com
Michigan Robotics retweeted
Stroke remains a leading cause of adult disability. It is responsible for high personal and public costs, with an annual total of $56.2 billion in the United States, including the cost of acute hospital care, rehabilitation, and days of missed work. professional.heart.org/en/sc…
Rehabilitation plays a key role in reducing disability and promoting quality of life after stroke.
The goal of rehabilitation is for patients with stroke to be restored as closely as possible to normal form
and independent functioning, minimizing required assistance and promoting a high quality of life.
✍🏼@alicen_whitaker @CVCatMCW @NeuroscienceMCW @MedicalCollege @dukemedschool @duke_Oto @duke_neurology @duke_brain @dukehealth @AbilityLab @uutah @NeuRRoLab @UMichPMR @umichmedicine @UMichResearch @UMKines @umflintdpt @UMRobotics
@UMneurosciences @UMBME @umichme @IowaPT
Michigan Robotics retweeted
What if robot hands could acquire dexterity once, then reuse it to learn downstream tasks much faster?
Introducing ADEPT: a pre-training & post-training paradigm using RL entirely in sim, then zero-shot deploying visuo-tactile policies in the real world.
đź”—adept-dexterity.github.io with Dex team @NVIDIAAI
Michigan Robotics retweeted
Robotics at University of Michigan is on 🔥!
Plus, it's completely open-sourced and free.
@UMRobotics put their entire robotics program on GitHub.
Everything. Code. Textbooks. Examples. Simulations.
That's what inside:
→ ROB 101: Computational Linear Algebra. Foundation course on the math that actually powers robots.
→ ROB 201: Calculus for the Modern Engineer. They wrote a textbook from scratch (GPL-licensed, on GitHub) because standard calculus doesn't address what engineers need.
→ ROB 204: Introduction to Human-Robot Systems. How humans and robots actually interact.
→ ROB 311: How to Build Robots and Make Them Move. The gap between theory and practice.
→ ROB 501: Mathematics for Robotics. Graduate-level rigor with code examples and interactive Jupyter notebooks.
If you want to learn robotics math from one of the world's best robotics departments, it's free.
Over 2,800 GitHub stars on the math courses alone.
Thousands of people learning robotics, just because it's open for everyone :)
This is how you build the next generation of roboticists.
đź”— Access it here: github.com/michiganrobotics
~~
♻ Join the weekly robotics newsletter, and never miss any news → ziegler.substack.com
Michigan Robotics retweeted
After 4 wonderful years, I'm signing off from NVIDIA. Working at NVIDIA's Seattle Robotics Lab was an absolute pleasure. Amazing collaborators, a great research environment, and friendships I'll keep for life.
Before I start at @UMRobotics next year, I'm joining @proceptionAI to lead the effort to build the dexterous manipulation learning stack. Proception is a full-stack
robotics startup that is already shipping robot hands and data-collection gloves.
I believe solving dexterous manipulation requires co-designing the entire stack: hardware, software, and AI. Proception is one of the few places where you can
actually do that.
We're building the best dexterous manipulation system in the world — hands, data, and policies together. If that's the problem you want to work on, come build with us. Links below.



















