Back to Events

(THESIS DEFENSE) Bridging Model-Based and Learning-Based Methods for Robotic Loco-Manipulation and Control

October 24 2025

2:00P - 3:00P

Location

32-G449
Virtual Event

Speaker: Lujie Yang

Host: Prof. Russ Tedrake

Date: Friday - October 24, 2025

Time: 2:00 - 3:00pm ET

Location: Room 32-G449 (Patil/Kiva)

Zoom Link: https://mit.zoom.us/j/95546717935

 

Abstract: Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control, including autonomous driving, drone racing, locomotion and manipulation. Yet, these policies remain constrained by their dependence on large quantities of high-quality data and their inability to provide the performance guarantees demanded in safety-critical settings. In contrast, model-based optimization methods exploit system structures to provide strong guarantees and enable efficient offline computation, but they often require accurate models and struggle with complex, long-horizon tasks. 

This thesis bridges the gap between these paradigms by leveraging model-based tools to address the limitations of learning-based methods. First, I introduce a scalable framework for physics-driven data generation, combining human demonstrations with trajectory optimization to produce large-scale, dynamically feasible datasets for dexterous manipulation. Behavior cloning policies trained on these datasets achieve robust performance and generalization across different embodiments and physical parameters. I further extend this framework to whole-body loco-manipulation by integrating human-object interaction demonstrations with interaction-preserving optimization to generate kinematically consistent motions across diverse spatial configurations. These synthesized trajectories are then used to guide reinforcement learning to produce dynamically consistent policies with improved robustness and generalization.

Finally, to equip learned policies with formal guarantees, I propose an optimization-inspired approach for synthesizing and verifying NN controllers with Lyapunov stability guarantees, scalable to partially observable systems via GPU-accelerated verification. Together, these contributions integrate model-based structure with learning-based flexibility, advancing data-efficient, generalizable, and verifiable robotic control.

Add to Calendar 2025-10-24 14:00:00 2025-10-24 15:00:00 America/New_York (THESIS DEFENSE) Bridging Model-Based and Learning-Based Methods for Robotic Loco-Manipulation and Control Speaker: Lujie YangHost: Prof. Russ TedrakeDate: Friday - October 24, 2025Time: 2:00 - 3:00pm ETLocation: Room 32-G449 (Patil/Kiva)Zoom Link: https://mit.zoom.us/j/95546717935 Abstract: Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control, including autonomous driving, drone racing, locomotion and manipulation. Yet, these policies remain constrained by their dependence on large quantities of high-quality data and their inability to provide the performance guarantees demanded in safety-critical settings. In contrast, model-based optimization methods exploit system structures to provide strong guarantees and enable efficient offline computation, but they often require accurate models and struggle with complex, long-horizon tasks. This thesis bridges the gap between these paradigms by leveraging model-based tools to address the limitations of learning-based methods. First, I introduce a scalable framework for physics-driven data generation, combining human demonstrations with trajectory optimization to produce large-scale, dynamically feasible datasets for dexterous manipulation. Behavior cloning policies trained on these datasets achieve robust performance and generalization across different embodiments and physical parameters. I further extend this framework to whole-body loco-manipulation by integrating human-object interaction demonstrations with interaction-preserving optimization to generate kinematically consistent motions across diverse spatial configurations. These synthesized trajectories are then used to guide reinforcement learning to produce dynamically consistent policies with improved robustness and generalization.Finally, to equip learned policies with formal guarantees, I propose an optimization-inspired approach for synthesizing and verifying NN controllers with Lyapunov stability guarantees, scalable to partially observable systems via GPU-accelerated verification. Together, these contributions integrate model-based structure with learning-based flexibility, advancing data-efficient, generalizable, and verifiable robotic control. TBD

Part of

Related Events