Bi-Level Optimization Augmented with Conditional Variational Autoencoder for Autonomous Driving in Dense Traffic

TL;DR

This paper introduces a real-time bi-level optimization method for autonomous driving in dense traffic, combining a novel GPU-accelerated optimizer with a CVAE warm-start to improve safety and efficiency.

Contribution

It proposes a new bi-level optimization framework with a CVAE-based warm-start, outperforming existing methods in safety metrics for autonomous driving.

Findings

Outperforms state-of-the-art in collision rate

Runs in real-time with GPU acceleration

Maintains competitive driving efficiency

Abstract

Autonomous driving has a natural bi-level structure. The goal of the upper behavioural layer is to provide appropriate lane change, speeding up, and braking decisions to optimize a given driving task. However, this layer can only indirectly influence the driving efficiency through the lower-level trajectory planner, which takes in the behavioural inputs to produce motion commands. Existing sampling-based approaches do not fully exploit the strong coupling between the behavioural and planning layer. On the other hand, end-to-end Reinforcement Learning (RL) can learn a behavioural layer while incorporating feedback from the lower-level planner. However, purely data-driven approaches often fail in safety metrics in unseen environments. This paper presents a novel alternative; a parameterized bi-level optimization that jointly computes the optimal behavioural decisions and the resulting downstream trajectory. Our approach runs in real-time using a custom GPU-accelerated batch optimizer, and a Conditional Variational Autoencoder learnt warm-start strategy. Extensive simulations show that our approach outperforms state-of-the-art model predictive control and RL approaches in terms of collision rate while being competitive in driving efficiency.