A Hierarchical Approach for Strategic Motion Planning in Autonomous Racing

TL;DR

This paper introduces a hierarchical, learning-based trajectory planning method for autonomous racing that ensures safety and feasibility by integrating a neural network policy with a model predictive controller, demonstrating superior performance in simulation.

Contribution

A novel hierarchical approach combining neural network-based reward specification with NMPC for safe, sample-efficient strategic motion planning in autonomous racing.

Findings

Successfully learned overtaking strategies in simulation

Ensured safe trajectories through integrated constraints

Outperformed classical RL in racing scenarios

Abstract

We present an approach for safe trajectory planning, where a strategic task related to autonomous racing is learned sample-efficient within a simulation environment. A high-level policy, represented as a neural network, outputs a reward specification that is used within the cost function of a parametric nonlinear model predictive controller (NMPC). By including constraints and vehicle kinematics in the NLP, we are able to guarantee safe and feasible trajectories related to the used model. Compared to classical reinforcement learning (RL), our approach restricts the exploration to safe trajectories, starts with a good prior performance and yields full 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 to avoid getting overtaken by blocking faster vehicles.