# Thomas Lew

I am a research scientist at the Toyota Research Institute, where I develop decision-making algorithms for autonomous systems. My research leverages tools from optimal and stochastic control, differential geometry, and machine learning, revealing insights for designing fast and reliable methods with optimality, accuracy, and adaptation guarantees. It was deployed on drones, spacecraft and Mars rover testbeds, rockets, and mobile robotic manipulators.

Previously, I received my PhD from Stanford University advised by Marco Pavone, completed research internships at Google Brain and NASA JPL, and studied at ETH Zurich and EPFL.

# My Research

Some problems I have been working on:

*Trajectory optimization under uncertainty*: How can we compute optimal trajectories for uncertain nonlinear dynamical systems that explicitly account for the risk of failure?*Forward reachability analysis*: How can we propagate uncertainty through complex systems (potentially with neural networks in the loop) in milliseconds and use it for planning and control? What accuracy can we expect? What problem structure can we exploit?*Reliable learning-based control*: How can a system safely (meta-)learn its dynamics, while handling the exploration-exploitation tradeoff and always satisfying constraints?*Resilient navigation*: How can a drone autonomously fly even if all its exteroceptive sensors have failed?*Vision-based control*: How can a robot achieve precise control from high-dimensional visual inputs while ensuring safe and zero-shot deployment?

## Preprints

**Estimating the Convex Hull of the Image of a Set with Smooth Boundary: Error Bounds and Applications**- T. Lew, R. Bonalli, L. Janson, M. Pavone -

**Under Review**- Feb 2023

Project Page / Paper / Code - We study the problem of estimating the convex hull of the image of a compact set with smooth boundary.

**Sample Average Approximation for Stochastic Programming with Equality Constraints**- T. Lew, R. Bonalli, M. Pavone -

**Under Review**- Jun 2022

Project Page / Paper / Code - We revisit the sample average approximation (SAA) approach for general non-convex stochastic programming and apply the method to stochastic optimal control problems.

## Publications

**Exact Characterization of the Convex Hulls of Reachable Sets**- T. Lew, R. Bonalli, M. Pavone -

**CDC**- Dec 2023

Project Page / Paper / Code - We give a finite-dimensional characterization of the convex hulls of reachable sets of nonlinear systems (dx/dt=f(x)+w).

**Risk-Averse Trajectory Optimization via Sample Average Approximation**- T. Lew, R. Bonalli, M. Pavone -

**RA-L**- Oct 2023

Project Page / Paper / Code - A sample-based approach to risk-averse trajectory optimization.

**Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization**- T. Lew, S. Singh, M. Prats, J. Bingham, J. Weisz, B. Holson, X. Zhang, V. Sindhwani, Y. Lu, F. Xia, P. Xu, T. Zhang, J. Tan, M. Gonzalez -

**ICRA**- Jan 2023

Project Page / Paper / Blog Post / Video - We propose an effective strategy for table wiping combining the strengths of reinforcement learning and whole-body trajectory optimization.

**Sequential convex programming for non-linear stochastic optimal control**- R. Bonalli, T. Lew, M. Pavone -

**ESAIM: COCV**- Oct 2022

Project Page / Paper / Code - We propose a sequential convex programming framework for non-linear finite-dimensional stochastic optimal control.

**Convex Optimization for Trajectory Generation: A Tutorial on Generating Dynamically Feasible Trajectories Reliably and Efficiently**- D. Malyuta, T. Reynolds, M. Szmuk, T. Lew, R. Bonalli, M. Pavone, B. Açıkmeşe -

**CSM**- Sep 2022 Project Page / Paper / Code - A comprehensive tutorial of convex trajectory optimization methods.

**Robust-RRT: Probabilistically-Complete Motion Planning for Uncertain Nonlinear Systems**- A. Wu, T. Lew, K. Solovey, E. Schmerling, M. Pavone -

**ISRR**- Sep 2022 Project Page / Paper / Code - We propose a robust sampling-based planner.

**A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis**- T. Lew, L. Janson, R. Bonalli, M. Pavone -

**L4DC**- Sep 2022 Project Page / Paper / Code / Video - We analyze an efficient sampling-based algorithm for general-purpose reachability analysis.

**Data-Driven Chance Constrained Control using Kernel Distribution Embeddings**- A. J. Thorpe*, T. Lew*, M. M. K. Oishi, M. Pavone -

**L4DC**- Sep 2022 Project Page / Paper / Code - We present a data-driven algorithm for efficiently computing stochastic control policies for general joint chance constrained optimal control problems.

**Analysis of theoretical and numerical properties of sequential convex programming for continuous-time optimal control**- R. Bonalli, T. Lew, M. Pavone -

**TAC**- Sep 2022

Project Page / Paper / Code - We analyze general SCP procedures for continuous-time optimal control.

**Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework**- T. Lew, A. Sharma, J. Harrison, A. Bylard, M. Pavone -

**T-RO**- Jun 2022

Project Page / Paper / Video / More Hardware Results - How can robots safely learn their dynamics?

**Nebula: Quest for robotic autonomy in challenging environments; team costar at the darpa subterranean challenge**- A. Agha-mohammadi et al -

**JFR**- Jun 2022 Project Page / Paper / CoSTAR-NeBula website - We present the algorithms, hardware, and software architecture deployed by the team CoSTAR in the DARPA SubT Challenge.

**Control Barrier Functions for Cyber-Physical Systems and Applications to NMPC**- J. Schilliger, T. Lew, S. Richards, S. Hänggi, M. Pavone, C. Onder -

**RA-L**- Apr 2021 Project Page / Paper - We propose a CBF formulation that accounts for delays.

**Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Sampling**- T. Lew, M. Pavone -

**CoRL**- Nov 2020

Project Page / Paper / Video / Code - New efficient sampling-based reachability analysis algorithms.

**Chance-Constrained Sequential Convex Programming for Robust Trajectory Optimization**- T. Lew, R. Bonalli, M. Pavone -

**ECC**- May 2020

Project Page / Paper / Code - We propose an algorithm for chance-constrained trajectory optimization.

**Learning-based warm-starting for fast sequential convex programming and trajectory optimization**- S. Banerjee, T. Lew, R. Bonalli, A. Alfaadhel, I. Alomar, H. Shageer, M. Pavone -

**AeroConf**- Mar 2020

Project Page / Paper / Code - We propose a learning-based strategy to warm-start trajectory optimization algorithms.

**Contact Inertial Odometry: Collisions are your Friends**- T. Lew*, T. Emmei*, D. Fan, T. Bartlett, A. Santamaria-Navarro, R. Thakker, A. Agha-mohammadi -

**ISRR**- Dec 2019

Project Page / Paper / Video - How can a drone fly blindly, when all its exteroceptive sensors have failed?

**Chance-Constrained Optimal Altitude Control of a Rocket**- T. Lew, F. Lyck, G. Müller -

**EUCASS**- Jul 2019

Project Page / Paper / Launch Video / ARIS website - We propose a control algorithm for a rocket to accurately stop at a target apogee.

**Investigation of specific wheel-terrain interaction aspects using an advanced single wheel test facility**- P. Oettershagen, T. Lew, A. Tardy, S. Michaud -

**ASTRA**- May 2019

Project Page / Paper - We identify limitations of wheel-soil interaction models and present a new method.

**Trajectory optimization on manifolds: A theoretically-guaranteed embedded sequential convex programming approach**- R. Bonalli, A. Bylard, A. Cauligi, T. Lew, M. Pavone -

**RSS**- May 2019

Project Page / Paper / Code - A new SCP trajectory optimization algorithm on manifolds.