@inproceedings{Ghezzi2023b,

title = {Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximation},

author = {Andrea Ghezzi and Jasper Hoffman and Jonathan Frey and Joschka Boedecker and Moritz Diehl},

doi = {https://doi.org/10.48550/arXiv.2304.01782},

year  = {2023},

date = {2023-08-17},

booktitle = {2023 Conference on Decision and Control (CDC)},

abstract = {This work presents a novel loss function for learning nonlinear Model Predictive Control policies via Imitation Learning. Standard approaches to Imitation Learning neglect information about the expert and generally adopt a loss function based on the distance between expert and learned controls. In this work, we present a loss based on the Q-function directly embedding the performance objectives and constraint satisfaction of the associated Optimal Control Problem (OCP). However, training a Neural Network with the Q-loss requires solving the associated OCP for each new sample. To alleviate the computational burden, we derive a second Q-loss based on the Gauss-Newton approximation of the OCP resulting in a faster training time. We validate our losses against Behavioral Cloning, the standard approach to Imitation Learning, on the control of a nonlinear system with constraints. The final results show that the Q-function-based losses significantly reduce the amount of constraint violations while achieving comparable or better closed-loop costs.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{Reiter2023Hierarchical,

title = {A Hierarchical Approach for Strategic Motion Planning in Autonomous Racing},

author = {Rudolf Reiter and Jasper Hoffman and Joschka Boedecker and Moritz Diehl},

doi = {10.23919/ECC57647.2023.10178143},

isbn = {978-3-907144-08-4},

year  = {2023},

date = {2023-07-17},

urldate = {2023-07-17},

booktitle = {2023 European Control Conference (ECC)},

pages = {1-8},

publisher = {IEEE},

address = {Bucharest, Romania},

abstract = {We present an approach for safe trajectory planning, where a strategic task related to autonomous racing is learned sample efficiently within a simulation environment. A high-level policy, represented as a neural network, outputs a reward specification that is used within the function of a parametric nonlinear model predictive controller. By including constraints and vehicle kinematics in the nonlinear program, we can guarantee safe and feasible trajectories related to the used model. Compared to classical reinforcement learning, our approach restricts the exploration to safe trajectories, starts with an excellent prior performance and yields complete trajectories that can be passed to a tracking lowest-level controller. We do not address the lowest-level controller in this work and assume perfect tracking of feasible trajectories. We show the superior performance of our algorithm on simulated racing tasks that include high-level decision-making. The vehicle learns to efficiently overtake slower vehicles and avoids getting overtaken by blocking faster ones.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}