Tim Salzmann

PhD Student at TUM and Google DeepMind

[Tim Salzmann @TimSalzmann]

@fabiangruss Wichtig ist den täglichen Zwischen-Ramen zwischen Mittag und Abendessen nicht zu vergessen!

[Tim Salzmann @TimSalzmann]

@fabiangruss @Hacks0n Thank you!

[Tim Salzmann @TimSalzmann]

@fabiangruss Welcome to the dark side!

[Tim Salzmann @TimSalzmann]

@fabiangruss B is clearer than A to me. Still I find B too subtil for first time user to directly see (had to look for some seconds even tho I knew roughly what to look for). What about slightly different color coding either for the icon or entire posts even?!

[Tim Salzmann @TimSalzmann]

@roboticseabass @MarkusRyll Geometries and meshes could be (online) transformed into signed distance functions and similarly leveraged for collision avoidance. Not as flashy as an example tho 😉

[Tim Salzmann @TimSalzmann]

@fabiangruss Nice!

[Tim Salzmann @TimSalzmann]

@fabiangruss @goingonapp Would go with the middle one

[Tim Salzmann @TimSalzmann]

@A_Reichenbach_ @MarkusRyll @davsca1 @kaufmann_elia @jonarriza96 @drmapavone https://t.co/fhIFYpGOCH

Check out our new framework: L4CasADi! Makes it super easy to integrate PyTorch for control applications.

[Markus Ryll @MarkusRyll]

In our Real-time Neural MPC paper, we leverage network capacities 4000x larger in optimizations. We now release L4CasADi, which enables easy integration of PyTorch models in optimizations on CPU and GPU, supporting fast C code generation and seamless integration in Acados.

[Tim Salzmann @TimSalzmann]

@aetheru_ @MarkusRyll @davsca1 @drmapavone @kaufmann_elia @jonarriza96 Great! Feel free to reach out if you have questions or improvement suggestions!

[Tim Salzmann @TimSalzmann]

@MarkusRyll @davsca1 @drmapavone @kaufmann_elia @jonarriza96 L4CasADi Github
https://t.co/STJyiWpoXF

or just

pip install l4casadi —no-build-isolation

(Build dependencies must be installed first)

[Tim Salzmann @TimSalzmann]

@aetheru_ @MarkusRyll @davsca1 @drmapavone @kaufmann_elia @jonarriza96 Yes, correct! Any (differentiable and jit traceable) PyTorch model is supported (convolutions, transformers …). The framework is generic and does not assume a specific robotic platform or even a robotics application: Any control system that can profit from data-driven models.

[Tim Salzmann @TimSalzmann]

@PPuchaud @MarkusRyll @davsca1 @drmapavone @kaufmann_elia @jonarriza96 I am working on more descriptive dummy examples involving learned dynamics and objective functions. I will share them in the next couple of days.

[Tim Salzmann @TimSalzmann]

@PPuchaud @MarkusRyll @davsca1 @drmapavone @kaufmann_elia @jonarriza96 Prominent examples include learning the system dynamics function as in Real-Time Neural MPC, but learning the objective or the constraints is similarly supported. Generally, a data-driven L4CasADi model can replace every symbolic formulation (MX) in CasADi.

[Tim Salzmann @TimSalzmann]

@PPuchaud @casadi_software A concrete example of this would be https://t.co/aKHfeF0pVA

[Tim Salzmann @TimSalzmann]

@A_Reichenbach_ @MarkusRyll @davsca1 @kaufmann_elia @jonarriza96 @drmapavone The two recommendations I have: Try to trade small performance degradation for large runtime gains where possible. Stick to highly optimized individual frameworks for optimization and DL operations respectively.

[Tim Salzmann @TimSalzmann]

@aks1812 @MarkusRyll @davsca1 @kaufmann_elia @jonarriza96 @drmapavone For the gradients: while there are generally no guarantees, the worst case would be in OOD scenarios. There is lots of good work going on in OOD for NN:
https://t.co/6tIqDYMMZQ https://t.co/V2X7fHMioe

[Tim Salzmann @TimSalzmann]

@aks1812 @MarkusRyll @davsca1 @kaufmann_elia @jonarriza96 @drmapavone Both questions are very valid! While this paper is targeting the computational and feasibility aspect with empirical results, theoretical guarantees are an interesting research avenue. If you know prior work targeting your 2. remark (with or without DL) I would be interested.

[Tim Salzmann @TimSalzmann]

@natolambert @MarkusRyll @kaufmann_elia @drmapavone @davsca1 Hi Nathan, the paper is currently being worked over. Just had a peak at the new version - we do cite you there. Should be up on arxiv in the coming days.