Thomas Lew

Research Scientist at @ToyotaResearch. Optimal Control, Machine Learning, Robotics. PhD @Stanford. Previously intern at @Google, @NASAJPL.

[Thomas Lew @thomas__lew]

👏This work was led by Emre Adabag, who did excellent work as an intern on our team at TRI last summer.

[Thomas Lew @thomas__lew]

DiffMPC has been accepted to #ICLR2026!
DiffMPC is a #GPU-accelerated #differentiable solver for model predictive control. It better leverages parallelism, runs faster than previous solvers, supports scalable learning with MPC, and is implemented in JAX
📃 https://t.co/lQtl5XBgaD

[Thomas Lew @thomas__lew]

💻 DiffMPC code: https://t.co/LgsJ3uUeWJ

[Thomas Lew @thomas__lew]

Our team at TRI is hiring research interns for the summer of 2026! An exciting opportunity to advance the state of the art in decision-making, learning, and perception and to deploy models and algorithms on high-performance cars.
https://t.co/YCiez9hyGH
https://t.co/agsD0Uawmb

[Russ Tedrake @RussTedrake]

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: https://t.co/AV2cmfeX40

One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the technology, and to share a lot of details for how we're achieving it.

https://t.co/EVFLJAY6Zu

[Thomas Lew @thomas__lew]

4/4) This work combines known pathwise approaches to SDEs from the mathematics & machine learning communities and ideas from indirect optimal control. We use proof techniques developed by Pontryagin and recent integrability results on rough paths (Cass, Friz, et al. ~2013).

[Thomas Lew @thomas__lew]

I'm excited to share new optimality conditions for nonlinear stochastic optimal control, and the first indirect shooting method for solving these problems!

📖 https://t.co/JdG5NSjQou
💡 How? Using rough path theory
⬇️

[Thomas Lew @thomas__lew]

3/4) As an application, we propose the first indirect shooting method for nonlinear stochastic optimal control: It converges much faster than a direct method on a regulation task. Why? Because it only searches over the initial conditions of the adjoint vector 💡

[Thomas Lew @thomas__lew]

Our team at TRI is hiring a research intern for the summer of 2025! An exciting opportunity to pursue research at the intersection of perception and control, and to deploy models and algorithms on high-performance cars
https://t.co/rcPpHvPYHG

[Thomas Lew @thomas__lew]

Considering or just starting a PhD in robotics, optimization, ML, or control? If so, you may find this interview interesting: https://t.co/5vmmWNXpCW
Thanks again to Rodolphe Sepulchre for the invitation! @IEEEorg @CSSIEEE

[Thomas Lew @thomas__lew]

Presenting our risk-averse trajectory optimization work at #ICRA2024 on Wednesday at 2.45pm in AX-206. Come have a chat about planning under uncertainty and optimization! 📖 https://t.co/bJqPPYR3kq

[Thomas Lew @thomas__lew]

Our team at TRI is hiring a research intern for this summer! An exciting opportunity to pursue research on machine learning and control and deploy models and algorithms on high-performance cars https://t.co/bsQQBkIl4W

[Thomas Lew @thomas__lew]

@IEEECDC2023 @drmapavone Thank you to all my amazing collaborators!

[Thomas Lew @thomas__lew]

I'm excited to share that we just received two outstanding paper awards at @IEEECDC2023 !

[Thomas Lew @thomas__lew]

@IEEECDC2023 @drmapavone and the Control Systems Magazine Outstanding Paper Award for "Convex Optimization for Trajectory Generation: A Tutorial on Generating Dynamically Feasible Trajectories Reliably and Efficiently" https://t.co/j60OT25KpS with R. Bonalli, @drmapavone, and collaborators at UW