Thanh Ly

Thanh Ly

Acting Head of Reinforcement Learning Department, VinRobotics

MSE in Robotics, University of Pennsylvania · Vingroup Scholar

About

I'm a roboticist based in Hanoi, currently leading the reinforcement learning engineering team at VinRobotics under Dr. An Thai Le, and contributing to a portion of our research. What drew me into this field was always the same moment: watching something that only ever existed in simulation take its first real step in the physical world. That curiosity took me from mechatronics in Ho Chi Minh City to a master's in robotics at the University of Pennsylvania as a Vingroup Scholar, advised by Prof. Rahul Mangharam, and now to helping build humanoid robots that can carry, balance, and adapt the way people do.

Outside of that, I'm usually planning the next trip; I like being somewhere new often enough that home stays interesting when I get back.

Education

MSE in Robotics

University of Pennsylvania, Philadelphia, USA

Vingroup Scholar

BEng in Mechatronic Engineering, summa cum laude

Ho Chi Minh City University of Technology (HCMUT–VNU), Vietnam

Thesis: Integration of an Industrial Robot with a 3D Scanning Stereo Vision System Using Gray Code and Phase Shift

Experience

Acting Head of Reinforcement Learning Department

04/2026 – Present

VinRobotics, Hanoi, Vietnam

Leading the RL engineering team and directing production deployment, while contributing to select research projects.

Senior Reinforcement Learning Engineer

12/2025 – 03/2026

VinRobotics, Hanoi, Vietnam

Built multi-physics simulation and distributed GPU RL training pipelines for humanoid robots.

R&D Software Engineer — Reinforcement Learning

06/2025 – 11/2025

VinRobotics, Hanoi, Vietnam

Trained RL policies for humanoid locomotion, achieving stable walking and disturbance recovery on hardware.

Research Assistant

05/2024 – 05/2025

University of Pennsylvania, Philadelphia, USA

Generated synthetic datasets and built multi-view pose estimation pipelines for robot perception.

Teaching Assistant — Computer Vision & Computational Photography

08/2024 – 12/2024

University of Pennsylvania, Philadelphia, USA

Led lab sessions on multi-view geometry, camera calibration, and image-based reconstruction.

Earlier Experience

Process Engineer — Power Control & Information Systems

01/2023 – 05/2023

Procter & Gamble, Ho Chi Minh City, Vietnam

Built digital twins and ML models to optimize factory energy consumption.

Technology Specialist

07/2022 – 12/2022

Vingroup Big Data Institute (VinBigData), Hanoi, Vietnam

Researched depth estimation and built vision-based safety monitoring for construction sites.

Undergraduate Research Assistant

04/2021 – 06/2022

Ho Chi Minh City University of Technology, Vietnam

Built structured-light 3D reconstruction and PointNet-based bin-picking segmentation pipelines.

Undergraduate Technical Intern

02/2021 – 08/2021

Intel, Ho Chi Minh City, Vietnam

Supported equipment qualification and data analysis for chipset production.

Research

Service humanoid traversing structured terrain while carrying a payload, guided by terrain affordance cost maps

TACT-ful CoRL 2026, under review

A perceptive locomotion system for payload-robust humanoid walking. Multi-channel terrain cost maps guide a GPU-parallel foothold planner, with virtual wrench injection enabling payload-compliance training without force sensors. Achieves 1.0 m/s on stairs with 20 cm risers and zero-shot transfer to a physical humanoid carrying up to 20 kg.

Project page →
Heavy humanoid yielding compliantly to external forces at arbitrary contact sites across wiping, squatting, and cooperative transport tasks

CompliantWBC CoRL 2026, under review

Whole-body compliance for a 70 kg heavy humanoid under high-payload and external-force scenarios. A multi-site impedance reference controller, variational force latent encoder, and bounded residual mechanism jointly edit impedance equilibria — validated on surface wiping, force reaction, loaded squatting, and cooperative transport with a 0.98 success rate.

Project page →

Publications

Under Review

  1. Thanh Ly, Truong-Duy Dang, Chien Le, Tan-Dzung Do, Phuong Tuan Dat, Cuc T. Trinh, Vien Anh Ngo, and An T. Le, “TACT-ful: Multi-Channel Terrain Affordance and Compliance Training for Payload-Robust Perceptive Humanoid Locomotion,” Conference on Robot Learning (CoRL), 2026. Under review. Project page
  2. Tan-Dzung Do, Cuc T. Trinh, Phuong Tuan Dat, Truong-Duy Dang, Chien Le, Thanh Ly, Vien Anh Ngo, and An T. Le, “Whole-Body Compliance for Heavy Humanoids via Force Latent Estimation and Residual Impedance Targets,” Conference on Robot Learning (CoRL), 2026. Under review. Project page

Peer-Reviewed

  1. P. Thanh Ly, Q. Chi Nguyen, N. Duy Hung Nguyen, P.-T. Pham, and K.-S. Hong, “Structured-Light-Based 3D Scanning System for Industrial Manipulator in Bin-Picking Application,” Australian & New Zealand Control Conference (ANZCC), 2022, pp. 34–39.
  2. N. Duy Hung Nguyen, P.-T. Pham, P. Thanh Ly, L. H. Nguyen, and Q. Chi Nguyen, “Bin-Picking Solution for Industrial Robots Integrating a 2D Vision System,” International Conference on High Performance Big Data and Intelligent Systems (HDIS), 2022, pp. 266–270.

Awards & Scholarships

Videos

Perceptive Locomotion for Payload-Robust Walking

Humanoid Platform: Global Debut

Load-Bearing Locomotion: Heavy Payload Transport

Dexterous Manipulation: Human–Robot Collaborative Painting

Stereo Vision Bin-Picking (Undergraduate Thesis)

Beyond Research

When I'm not in the lab, you'll usually find me traveling — exploring new places is my favorite way to reset.