Interaction-Aware Trajectory Planning for Autonomous Vehicles with Analytic Integration of Neural Networks into Model Predictive Control

Abstract

Autonomous vehicles (AVs) must share the driving space with other drivers and often employ conservative motion planning strategies to ensure safety. These conservative strategies can negatively impact AV's performance and significantly slow traffic throughput. Therefore, to avoid conservatism, we design an interaction-aware motion planner for the ego vehicle (AV) that interacts with surrounding vehicles to perform complex maneuvers in a locally optimal manner. Our planner uses a neural network-based interactive trajectory predictor and analytically integrates it with model predictive control (MPC). We solve the MPC optimization using the alternating direction method of multipliers (ADMM) and prove the algorithm's convergence. We provide an empirical study and compare our method with a baseline heuristic method.

References in corpus (9)

• Gaussian Error Linear Units (GELUs)
• Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving
• Driving in Dense Traffic with Model-Free Reinforcement Learning
• Linear tracking MPC for nonlinear systems Part I: The model-based case
• Lane-Change in Dense Traffic with Model Predictive Control and Neural Networks
• Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios
• Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks)
• A Cooperation-Aware Lane Change Method for Autonomous Vehicles
• NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning

Cited by in corpus (2)

• Stochastic Time-Optimal Trajectory Planning for Connected and Automated Vehicles in Mixed-Traffic Merging Scenarios
• Analysis of Functional Insufficiencies and Triggering Conditions to Improve the SOTIF of an MPC-based Trajectory Planner