# Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic

arXiv: https://arxiv.org/abs/2310.02918 · HTML: https://mlsanity.com/paper/2310.02918/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Wayformer: Motion Forecasting via Simple & Efficient Attention Networks](https://mlsanity.com/paper/2207.05844/) (2022)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [A predictive safety filter for learning-based control of constrained nonlinear dynamical systems](https://mlsanity.com/paper/1812.05506/) (2018)
- [Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles](https://mlsanity.com/paper/2001.11231/) (2020)
- [Data-driven Economic NMPC using Reinforcement Learning](https://mlsanity.com/paper/1904.04152/) (2019)
- [Optimization-Based Autonomous Racing of 1:43 Scale RC Cars](https://mlsanity.com/paper/1711.07300/) (2017)
- [Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians](https://mlsanity.com/paper/2102.13073/) (2021)
- [Data-Driven Model Predictive Control with Stability and Robustness Guarantees](https://mlsanity.com/paper/1906.04679/) (2019)
- [Model Predictive Contouring Control for Collision Avoidance in Unstructured Dynamic Environments](https://mlsanity.com/paper/2010.10190/) (2020)
- [A predictive safety filter for learning-based racing control](https://mlsanity.com/paper/2102.11907/) (2021)
- [Policy Search for Model Predictive Control with Application to Agile Drone Flight](https://mlsanity.com/paper/2112.03850/) (2021)
- [Learning from the Hindsight Plan -- Episodic MPC Improvement](https://mlsanity.com/paper/1609.09001/) (2016)
- [Memory of Motion for Warm-starting Trajectory Optimization](https://mlsanity.com/paper/1907.01474/) (2019)
- [Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios](https://mlsanity.com/paper/2107.04538/) (2021)
- [Guaranteeing Consistency in a Motion Planning and Control Architecture Using a Kinematic Bicycle Model](https://mlsanity.com/paper/1804.08290/) (2018)
- [NMPC trajectory planner for urban autonomous driving](https://mlsanity.com/paper/2105.04034/) (2021)
- [Globally Guided Trajectory Planning in Dynamic Environments](https://mlsanity.com/paper/2303.07751/) (2023)

## Built on by (most cited first, 4 of 4)

- [Learning Multiple Initial Solutions to Optimization Problems](https://mlsanity.com/paper/2411.02158/) (2024)
- [Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification](https://mlsanity.com/paper/2504.13111/) (2025)
- [Generative AI for Autonomous Driving: A Review](https://mlsanity.com/paper/2505.15863/) (2025)
- [RL-Guided PAC-NMPC for Probabilistically-Safe Perception-Based Navigation in Unknown Environments](https://mlsanity.com/paper/2609.39854/) (2026)

## Abstract (arXiv)

Model Predictive Control lacks the ability to escape local minima in nonconvex problems. Furthermore, in fast-changing, uncertain environments, the conventional warmstart, using the optimal trajectory from the last timestep, often falls short of providing an adequately close initial guess for the current optimal trajectory. This can potentially result in convergence failures and safety issues. Therefore, this paper proposes a framework for learning-aided warmstarts of Model Predictive Control algorithms. Our method leverages a neural network based multimodal predictor to generate multiple trajectory proposals for the autonomous vehicle, which are further refined by a sampling-based technique. This combined approach enables us to identify multiple distinct local minima and provide an improved initial guess. We validate our approach with Monte Carlo simulations of traffic scenarios.