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

arXiv: https://arxiv.org/abs/2212.02224 · HTML: https://mlsanity.com/paper/2212.02224/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 13 of 13)

- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Training Neural Networks Without Gradients: A Scalable ADMM Approach](https://mlsanity.com/paper/1605.02026/) (2016)
- [Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving](https://mlsanity.com/paper/1905.02680/) (2019)
- [STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation](https://mlsanity.com/paper/2104.13542/) (2021)
- [Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning](https://mlsanity.com/paper/1803.10056/) (2018)
- [Policy Search for Model Predictive Control with Application to Agile Drone Flight](https://mlsanity.com/paper/2112.03850/) (2021)
- [Optimal parameter selection for the alternating direction method of multipliers (ADMM): quadratic problems](https://mlsanity.com/paper/1306.2454/) (2013)
- [A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning](https://mlsanity.com/paper/2101.06778/) (2021)
- [Dynamic Input for Deep Reinforcement Learning in Autonomous Driving](https://mlsanity.com/paper/1907.10994/) (2019)
- [Multi-Modal Model Predictive Control through Batch Non-Holonomic Trajectory Optimization: Application to Highway Driving](https://mlsanity.com/paper/2109.10392/) (2021)
- [Fast UAV Trajectory Optimization using Bilevel Optimization with Analytical Gradients](https://mlsanity.com/paper/1811.10753/) (2018)
- [Decision-making for Autonomous Vehicles on Highway: Deep Reinforcement Learning with Continuous Action Horizon](https://mlsanity.com/paper/2008.11852/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Survey of Generative AI for Intelligent Transportation Systems: Road Transportation Perspective](https://mlsanity.com/paper/2312.08248/) (2023)
- [A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research](https://mlsanity.com/paper/2410.07066/) (2024)

## Abstract (arXiv)

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.