Interaction-Aware Trajectory Prediction and Planning in Dense Highway Traffic using Distributed Model Predictive Control

TL;DR

This paper introduces a novel distributed model predictive control framework for autonomous vehicle trajectory planning in dense traffic, coupling prediction and planning to improve local optimality and safety.

Contribution

It presents a new integrated approach combining trajectory prediction and planning in multi-agent environments using distributed MPC, with analysis of performance under prediction errors.

Findings

Improved local optimality over decoupled methods

Framework performs well in dense traffic simulations

Analysis of convergence and robustness to prediction errors

Abstract

In this paper we treat optimal trajectory planning for an autonomous vehicle (AV) operating in dense traffic, where vehicles closely interact with each other. To tackle this problem, we present a novel framework that couples trajectory prediction and planning in multi-agent environments, using distributed model predictive control. A demonstration of our framework is presented in simulation, employing a trajectory planner using non-linear model predictive control. We analyze performance and convergence of our framework, subject to different prediction errors. The results indicate that the obtained locally optimal solutions are improved, compared with decoupled prediction and planning.