Behavior Cloning of MPC for 3-DOF Robotic Manipulators

Theo Guegan, Wen Jie Dexter Teo

Keywords: Behavior Cloning, Model Predictive Control, Neural Network Surrogates, Robotic Manipulators, Real-time Control

TL;DR: Our paper investigates the usage of neural surrogates to replace computationally expensive Model Predictive Control.

Abstract: While Model Predictive Control (MPC) provides strong stability and robustness, it imposes a significant computational burden on real-time systems and resource-constrained devices. This paper investigates the application of Behavior Cloning to approximate MPC policies for the real-time control of a 3-degree-of-freedom (3-DOF) robotic manipulator. We present a baseline controller combining Inverse Kinematics with MPC and evaluate a spectrum of neural network architectures, ranging from classical regression algorithms to complex deep learning models including Deep MLPs and RNNs, to derive computationally efficient surrogate policies. We analyze generalization capabilities, stability considerations, and the trade-offs inherent in different architectural choices. Our empirical study employs both online and offline evaluations to assess performance regarding accuracy, computational efficiency, and fidelity to the original MPC policy. Our results demonstrate that Behavior Cloning can effectively reduce the computational burden of MPC policies for 3-DOF robotic manipulators, achieving a 3x reduction in inference latency with a 84.98% success rate under relaxed tolerances. Notably, we find that static architectures outperform temporal variants, confirming the sufficiency of instantaneous state observations for this task. However, we observe a precision gap under strict tolerances, which suggest that while Behavior Cloning captures the global optimal trajectory, further research is needed to minimize terminal steady-state error.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 10