Researchers have used reinforcement learning to teach a 5-tonne John Deere skid-steer loader to perform complex acrobatic manoeuvres autonomously. Trained in simulation and transferred to a real machine, the system can balance on two wheels, navigate rough terrain, spin, and control its bucket before landing safely.
The research demonstrates the potential of AI-driven automation for heavy construction and industrial machinery.
Video Credit: @leggedrobotics / @ETH
Paper: wevlv.co/4kltYys
#engineering #technology
27
flight GNC retweeted
TOMORROW is the GRASP SFI seminar featuring Dr. Zhengyi Luo (@zhengyiluo) who will be presenting “From Motion Tracking to World Action Models for Humanoids” from 3pm - 4pm.
More info: grasp.upenn.edu/events/fall-…
#GRASP #GRASPLab #GRASPSFI
flight GNC retweeted
Teaching robots new tasks just got a lot faster. 🤖
With Gemini 4 Hydrogen and the new robotics plugin for Google @Antigravity, you can connect a supported arm, practice in @MuJoCo simulation, and run tasks in the real world using plain conversation.
flight GNC retweeted
#L4DC2027 will be at KTH in Stockholm, Sweden! We are thrilled to announce our keynote speakers: Francis Bach, Alexandre Proutière, Aude Billard, and Stefano Soatto. We hope to see you there!
flight GNC retweeted
"A Beginner's Guide to Physical Networks" (by Aaron Winn, Eleni Katifori): arxiv.org/abs/2611.18758
new red-letter edition of Elementary Applied Topology!
full pdf on my website -- physical book for $15 from amazon...
www2.math.upenn.edu/~ghrist/…
short story:
* new chapter on background material (chapter 0)
* new chapter on persistence (chapter 6)
* so many errors... fixed!
* some new artwork...
this book, begun in 2009 when the field was emerging, means a great deal to me. it was always an art project more than a textbook; indeed, the minimalist images were and are the only exercises in the text. if you can figure out what the image means, you have figured out the math behind it.
i hope that keeping the pdf available on my site encourages a new generation of students to learn topology. though it might take some time, as the page count went up by a third. also, the bibliography has grown quite a bit, given the developments in the field...
m'kay, welp, inspired by @viditnanda and @AlexKontorovich , i have finally updated my 10-year-old website...
www2.math.upenn.edu/~ghrist/
flight GNC retweeted
I love linear dynamical systems and control theory
When I got into neuroscience, I had high hopes that all my Strogatz-level nonlinear dynamical systems knowledge could be put to use. The brain is highly nonlinear, and dynamic.
It'd be great to explain the brain solely in terms of limit cycles, bifurcations, and chaos.
But you drive a NDS with time-varying inputs, the transient properties of your vector field dominate the asymptotic structure.
One way to solve this is geometric control theory, which make use of lots of Lie stuff but appears to be a niche and mostly beyond my comprehension.
The alternative is standard control theory (which is mostly, or at least locally, linear). You pay a huge price by giving up nonlinearity, but as a reward you get an insanely expressive (complete?) theory for how inputs and internal dynamics interact.
So many intuitions become beautifully clear in linear dynamical systems world.
The exact correspondence between autoregressive, state-space, and convolution representations of dynamical systems.
Or, how truncated BPTT (at one time step) can learn arbitrarily long range dependencies and this is a property of observability and persistence of excitation not truncation.
Or, how LQR and KF are dual -- the same problem but with arrows flipped.
Or, how cleanly the translation between discrete and continuous time systems become (no Euler steps)
etc
What is Control Theory? A brief introduction through intuition and flows.
virati.github.io/blog/resear…
flight GNC retweeted
I think I've found the best visual introduction for index theory on the excellent youtube channel 'Virtually Passed' under the titled ''4.0 A better way to understand Differential Equations | Nonlinear Dynamics | Index Theory''.
Absolutely fantastic stuff
flight GNC retweeted
I am saddened to say that Karl Astrom, a towering figue in control theory, and a pioneer of adaptive control, passed away yesterday, Nov 12, at the age of 92.
I imagine that in this AI-crazed age, with its constant pursuit of "flavor-of-the-month", many may not be aware of his contributions. However, one can draw a clear arc from his work to many of the ideas currently prevalent in machine learning. As early as 1965 he wrote (what I assume is) the first paper on the control of partially-observed Markov decision processes, which play an important role in modern reinforcement learning:
Optimal control of Markov decision processes with incomplete state estimation, J. Math. Anal. Applic., 1965
His landmark paper with Wittenmark lays the foundations for "learning and control":
On self tuning regulators, Automatica, 1973
I have been personally indebted to him in multiple ways. When I was a second year graduate student I attended the 1993 Institute of Mathematics and its Applications (IMA) Workshop on Adaptive Control in Minnesota that he had been organizing with Graham Goodwin and PR Kumar. After a brief discussion of some of my research he go so excited that, midway through the workshop, he added me to the program. I got pummeled by the faculty after my talk (even though I was right and they were wrong 😀).
I last saw him two years ago at Lund, where he spent almost all of his career. He was still active, visited the department, and attended talks regularly, always asking pointed questions (though he had to sit in a chair next to the speaker in order to hear!).
Altogether a remarkably kind and generous human being. A true scholar. RIP Karl.
flight GNC retweeted
Replying to @vineettiruvadi
you might be interested in the work of Joe Moeller (who also appears to be collaborator of Jade) at Caltech, formalizing control theory / dynamical systems in the language of category theory, see e.g.
arxiv.org/abs/2502.15276
flight GNC retweeted
the full geometric deep learning book draft is now complete.
all chapters available online on our website (link in thread).
🫡
@mmbronstein @TacoCohen
flight GNC retweeted
Today I launch Separatrix 1.0: a free desktop app for nonlinear dynamics.
Type ẋ = f(x, y) and get the phase portrait, fixed points classified, Lyapunov exponents, orbit diagrams and bifurcations, copy it as LaTeX.
Offline, open source, Mac/Win/Linux.
uncrayon.github.io/separatri…
flight GNC retweeted
Best simulator in the world backed by a world class team!
MuJoCo 4 is released!
github.com/google-deepmind/m…
A new textbook co-authored by @GioeleZardini brings classical robotics and modern AI together and makes autonomous robotics accessible to learners everywhere. cee.mit.edu/3-questions-gioe…
flight GNC retweeted
Your nonlinear system operates across a range of conditions. Can your controller keep up?
Join David Dinh for F-16 Control Design in Dyad: From Nonlinear Plant to Gain-Scheduled MPC.
See the workflow in one environment: trim and linearize an F-16 model, design and test an LQG regulator, generate C code, then explore gain-scheduled PID and MPC across airspeed and altitude, with MPC respecting thrust and elevator limits.
The example is an aircraft. The methods also apply to motor drives, robots and process juliahub.com/events/f-16-con….
📅 November 19, 2026 | 12 PM EST
Register:
#Dyad #ControlDesign #ModelPredictiveControl
flight GNC retweeted
"Hidden Routes: What Nonlinear Control Teaches Us About AI Safety" (by Enrique Zuazua, in @TheSIAMNews): siam.org/publications/siam-n…





























