Interaction-Aware Behavior Planning for Autonomous Vehicles Validated with Real Traffic Data

TL;DR

This paper presents a behavior planning approach for autonomous vehicles that models interactions with other traffic participants as a POMDP, using real traffic data to improve safety and efficiency in lane change scenarios.

Contribution

It introduces a novel POMDP-based behavior planning framework that accounts for unobservable human cooperativeness levels, learned from real traffic data, and validated with real-world traffic scenarios.

Findings

Successfully completed lane changes without collisions

Effective modeling of human behavior from real traffic data

Validated approach in both simulation and real traffic environments

Abstract

Autonomous vehicles (AVs) need to interact with other traffic participants who can be either cooperative or aggressive, attentive or inattentive. Such different characteristics can lead to quite different interactive behaviors. Hence, to achieve safe and efficient autonomous driving, AVs need to be aware of such uncertainties when they plan their own behaviors. In this paper, we formulate such a behavior planning problem as a partially observable Markov Decision Process (POMDP) where the cooperativeness of other traffic participants is treated as an unobservable state. Under different cooperativeness levels, we learn the human behavior models from real traffic data via the principle of maximum likelihood. Based on that, the POMDP problem is solved by Monte-Carlo Tree Search. We verify the proposed algorithm in both simulations and real traffic data on a lane change scenario, and the results show that the proposed algorithm can successfully finish the lane changes without collisions.