Thomas Lew

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

💻 DiffMPC code: github.com/ToyotaResearch…

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 📃 arxiv.org/abs/2510.06179

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. jobs.lever.co/tri/eef0e312-6… jobs.lever.co/tri/10f05961-0…

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ 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. youtube.com/watch?v=BEXFnr…

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).

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 💡

I'm excited to share new optimality conditions for nonlinear stochastic optimal control, and the first indirect shooting method for solving these problems! 📖 arxiv.org/abs/2502.06726 💡 How? Using rough path theory ⬇️

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 jobs.lever.co/tri/64226236-4…

Considering or just starting a PhD in robotics, optimization, ML, or control? If so, you may find this interview interesting: ieeexplore.ieee.org/abstract/docum… Thanks again to Rodolphe Sepulchre for the invitation! @IEEEorg @CSSIEEE

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! 📖 arxiv.org/abs/2307.03167

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 jobs.lever.co/tri/ab8a4367-0…

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

@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" arxiv.org/abs/2106.09125 with R. Bonalli, @drmapavone, and collaborators at UW

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