Chuong (Vance) Nguyen

I obtained my Ph.D. in Robotics from Department of Aerospace and Mechanical Engineering at University of Southern California, Los Angeles. I worked on Aggressive Maneuvers and Dynamic Locomotion on Legged Robots under the direction of Prof. Quan Nguyen at the Dynamic Robotics and Control Laboratory. I obtained my M.S. degrees from University of Southern California and Gwangju Institute of Science and Technology.

I am honored to receive Viterbi Fellowship and AME Department Fellowship from USC. I am fortunate to collaborate with Prof. Nikolay Atanasov (UC San Diego), Dr. Guillaume Bellegarda (EPFL, Switzerland), and Dr. Thai Duong (Rice University).

Email  /  Google Scholar  /  Github

Recent News

• [Jun 2025] I started my job as robotic researcher and software engineer at Ghost Robotics to develop solution for enhancing robustness and agility for legged locomotion.
• [May 2025] I will present 3 papers at ICRA 2025. See you in Atlanta!.
• [Feb 2025] I started my internship at Field AI to build up solution for last-mile package delievery for Amazon using legged robots.
• [Feb 2025] Our paper on Variational Integrator Discretized Trajectory Optimization for Legged Maneuvers is accepted to ICRA 2025.
• [Feb 2025] Our paper on Iterative Learning Control for Dynamic Maneuvers on Legged Robots is accepted to ICRA 2025.
• [Nov 2024] Our paper on Variable-Frequency Model Learning and Predictive Control for Legged Robots is accepted to Robotics And Automation Letter 2024.
• [Oct 2024] Our paper on Deep Reinforcement Learning for Robust Jumping on Legged Robots is accepted to Robotics And Autonomous Systems Journal 2024.
• [Aug 2023] Our paper on Deep Reinforcement Learning for Robust Jumping on Legged Robots is submitted to Robotics And Autonomous Systems Journal.
• [Aug 2023] I TA'ed at AME301: Dynamics.
• [Sep 2022] I gave a presentation on Contact-timing and Trajectory Optimization for 3D Jumping on Quadruped Robots at IROS'22.
• [July 2022] Our paper on Continuous Jumping for Legged Robots has been accepted to CDC 2022 . 🎉🎉🎉🎉🎉
• [Jun 2022] Our paper on Optimize 3D jumping on quadruped robots has been accepted to IROS 2022. 🎉🎉🎉🎉🎉
• [Jan 2021] I TA'ed at AME599: Dynamic Robotics and Control.
• [Sep 2020] I am honored to receive Viterbi Fellowship and AME Department Fellowship from the AME Department.
• [Sep 2020] I started my Ph.D. journey in the AME Department at University of Southern California.

Research Areas

My research spans optimization, control, and learning-based approaches for dynamic robotics, including trajectory optimization, reinforcement learning, supervised learning, and real-time optimization-based control. During my Ph.D. studies, I have focused on enhancing the agility and robustness of legged locomotion. I am also interested in game theory and the control of multi-agent dynamical systems.

Publications and Research Projects

Achieving precise target jumping with legged robots poses a significant challenge due to the long flight phase and the uncertainties inherent in contact dynamics and hardware. Forcefully attempting these agile motions on hardware could result in severe failures and potential damage. Motivated by these challenging problems, we propose an Iterative Learning Control (ILC) approach that aims to learn and refine jumping skills from easy to difficult, instead of directly learning these challenging tasks. We verify that learning from simplicity can enhance safety and target jumping accuracy over trials. Compared to other ILC approaches for legged locomotion, our method can tackle the problem of a long flight phase where control input is not available. In addition, our approach allows the robot to apply what it learns from a simple jumping task to accomplish more challenging tasks within a few trials directly in hardware, instead of learning from scratch.

Performing acrobatic maneuvers involving long aerial phases, such as precise dives or multiple backflips from significant heights, remains an open challenge in legged robot autonomy. Such aggressive motions often require accurate state predictions over long horizons with multiple contacts and extended flight phases. We propose a novel whole-body TO method using variational integration (VI) and full-body nonlinear dynamics for long-flight aggressive maneuvers. Compared to traditional Euler-based TO, our approach using VI preserves energy and momentum properties of the continuous time system and reduces error between predicted and executed trajectories by factors of between 2 − 10 while achieving similar planning time. We successfully demonstrate long-flight triple backflips on a quadruped A1 robot model and backflips on a bipedal HECTOR robot model for various heights and distances, achieving landing angle errors of only a few degrees.

Robust Walking with High Payload on Humanoid Robots

Realizing robust walking on unknown and rough terrain while carrying payloads is highly challenging for humanoid locomotion. Such motions often require both accurate whole-body coordination and real-time feedback control. To tackle this challenge, we utilize a framework combining the advantage of whole-body control (WBC) and model predictive control (MPC). The framework is validated on a humanoid robot with 29 degrees of freedom. We achieve robust walking at a speed of 1.5 m/s on uneven terrain while carrying a payload of 8 kg.

Performing highly agile acrobatic motions with a long flight phase requires perfect timing, high accuracy, and coordination of the full-body motion. To address these challenges, we present a novel approach on timings and trajectory optimization framework for legged robots performing aggressive 3D jumping. In our method, we firstly utilize an effective optimization framework using simplified rigid body dynamics to solve for contact timings and a reference trajectory of the robot body. The solution of this module is then used to formulate a full-body trajectory optimization based on the full nonlinear dynamics of the robot. This combination allows us to effectively optimize for contact timings while ensuring that the jumping trajectory can be effectively realized in the robot hardware. We first validate the efficiency of the proposed framework on the A1 robot model for various 3D jumping tasks such as double-backflips off the high altitude of 2m. Experimental validation was then successfully conducted for various aggressive 3D jumping motions such as diagonal jumps, barrel roll, and double barrel roll from a box of heights 0.4m and 0.9m, respectively.

Performing highly agile dynamic motions, such as jumping or running on uneven stepping stones has remained a challenging problem in legged robot locomotion. This paper presents a framework that combines trajectory optimization and model predictive control to perform robust and consecutive jumping on stepping stones. In our approach, we first utilize trajectory optimization based on full-nonlinear dynamics of the robot to generate periodic jumping trajectories for various jumping distances. A jumping controller based on a model predictive control is then designed for realizing smooth jumping transitions, enabling the robot to achieve continuous jumps on stepping stones. Thanks to the incorporation of MPC as a real-time feedback controller, the proposed framework is also validated to be robust to uneven platforms with unknown height perturbations and model uncertainty on the robot dynamics.

Achieving both target accuracy and robustness in dynamic maneuvers with long flight phases has been a significant challenge for legged robots. We propose a novel learningbased control approach consisting of model learning and model predictive control (MPC) utilizing an adaptive frequency scheme. We learn a model directly from experiments, accounting not only for leg dynamics but also for modeling errors and unknown dynamics mismatch in hardware and during contact. Additionally, learning the model with adaptive frequency allows us to cover the entire flight phase and final jumping target, enhancing the prediction accuracy of the jumping trajectory. Using the learned model, we also design an adaptive-frequency MPC to effectively leverage different jumping phases and track the target accurately.

In this paper, we consider a general task of jumping varying distances and heights for a quadrupedal robot in noisy environments, such as off of uneven terrain and with variable robot dynamics parameters. To accurately jump in such conditions, we propose a framework using deep reinforcement learning that leverages and augments the complex solution of nonlinear trajectory optimization for quadrupedal jumping. While the standalone optimization limits jumping to take-off from flat ground and requires accurate assumptions of robot dynamics, our proposed approach improves the robustness to allow jumping off of significantly uneven terrain with variable robot dynamical parameters and environmental conditions. Compared with walking and running, the realization of aggressive jumping on hardware necessitates accounting for the motors’ torque-speed relationship as well as the robot’s total power limits. By incorporating these constraints into our learning framework, we successfully deploy our policy sim-to-real without further tuning, fully exploiting the available onboard power supply and motors. We demonstrate robustness to environment noise of foot disturbances of up to 6 cm in height, or 33% of the robot’s nominal standing height, while jumping 2x the body length in distance.

This paper presents a number of ideas combining consensus algorithms and differential inclusions to effectively solve exact potential games with continuous strategy space in a multi-agent network. Solving these games or finding their Nash equilibrium (NE) is conducted in a distributed manner via the forms of two interconnected subsystems, the first one estimating necessary information by average consensus algorithm, and another using differential inclusion to seek NE with respect to distributed constraints on players' actions. Firstly, a special form of exact potential games is considered. Secondly, larger potential games are taken into consideration. It is shown that designed dynamical systems are semi-practically globally asymptotically stable (SPA), enabling players' actions to converge to NE non-locally.