Neural Lyapunov Differentiable Predictive Control

Conference · Wed Dec 07 04:00:00 EST 2022

DOI:https://doi.org/10.1109/CDC51059.2022.9992386· OSTI ID:1924633

Mukherjee, Sayak ^[1]; Drgona, Jan ^[1]; Tuor, Aaron R. ^[1]; Halappanavar, Mahantesh ^[1]; Vrabie, Draguna L. ^[1]

---

1. BATTELLE (PACIFIC NW LAB)

We present a learning-based predictive control methodology using the differentiable programming framework with sufficient Lyapunov-based guarantees. The neural Lyapunov differentiable predictive control (NLDPC) learns the policy by constructing a computational graph encompassing the system dynamics, state, and input constraints, and the necessary Lyapunov certification constraints, and thereafter using the automatic differentiation to update the neural policy parameters. In conjunction, our approach jointly learns a Lyapunov function that certifies the regions of state-space with stable dynamics. We also provide an initial condition sampling-based statistical guarantee for the training of NLDPC. Our offline training approach provides a computationally efficient and scalable alternative to classical model predictive control solutions, which now directly comes with Lyapunov based guarantees as shown in this paper. We substantiate the advantages of the proposed approach with simulations to stabilize the double integrator model and on an example of controlling an aircraft model.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1924633
• Report Number(s): PNNL-SA-171659
• Country of Publication: United States
• Language: English