Hybrid Imitation-Learning Motion Planner for Urban Driving

TL;DR

This paper introduces a hybrid motion planner for urban driving that combines learning-based trajectory generation with optimization-based refinement to ensure safety and human-like driving behavior.

Contribution

A novel hybrid approach that integrates neural network predictions with optimization techniques for safer and more realistic urban driving planning.

Findings

Effective in simulation experiments

Successfully deployed in real-world self-driving vehicles

Balances safety with human-likeness in trajectories

Abstract

With the release of open source datasets such as nuPlan and Argoverse, the research around learning-based planners has spread a lot in the last years. Existing systems have shown excellent capabilities in imitating the human driver behaviour, but they struggle to guarantee safe closed-loop driving. Conversely, optimization-based planners offer greater security in short-term planning scenarios. To confront this challenge, in this paper we propose a novel hybrid motion planner that integrates both learning-based and optimization-based techniques. Initially, a multilayer perceptron (MLP) generates a human-like trajectory, which is then refined by an optimization-based component. This component not only minimizes tracking errors but also computes a trajectory that is both kinematically feasible and collision-free with obstacles and road boundaries. Our model effectively balances safety and human-likeness, mitigating the trade-off inherent in these objectives. We validate our approach through simulation experiments and further demonstrate its efficacy by deploying it in real-world self-driving vehicles.