PlanNetX: Learning an Efficient Neural Network Planner from MPC for Longitudinal Control

TL;DR

PlanNetX introduces a neural network architecture that learns entire MPC trajectories for longitudinal control, enabling efficient, high-accuracy planning suitable for embedded autonomous driving systems.

Contribution

We propose PlanNetX, a novel neural network that learns MPC trajectories directly, improving efficiency and performance over existing imitation learning methods.

Findings

High accuracy in learning MPC trajectories

Improved closed-loop control performance

Effective in autonomous driving scenarios

Abstract

Model predictive control (MPC) is a powerful, optimization-based approach for controlling dynamical systems. However, the computational complexity of online optimization can be problematic on embedded devices. Especially, when we need to guarantee fixed control frequencies. Thus, previous work proposed to reduce the computational burden using imitation learning (IL) approximating the MPC policy by a neural network. In this work, we instead learn the whole planned trajectory of the MPC. We introduce a combination of a novel neural network architecture PlanNetX and a simple loss function based on the state trajectory that leverages the parameterized optimal control structure of the MPC. We validate our approach in the context of autonomous driving by learning a longitudinal planner and benchmarking it extensively in the CommonRoad simulator using synthetic scenarios and scenarios derived from real data. Our experimental results show that we can learn the open-loop MPC trajectory with high accuracy while improving the closed-loop performance of the learned control policy over other baselines like behavior cloning.