Socially-Compatible Behavior Design of Autonomous Vehicles with Verification on Real Human Data

TL;DR

This paper introduces an uncertain-aware prediction and planning framework for autonomous vehicles that enhances social compatibility by considering human-like courtesy and confidence, validated on real driving data.

Contribution

It presents a novel integrated prediction and planning method that accounts for uncertainties and social behaviors, improving human-likeness and cultural adaptability of AVs.

Findings

Online inference improves human-likeness of AV behaviors.

Drivers exhibit significant courtesy, even without right-of-way.

Driving preferences vary across cultures.

Abstract

As more and more autonomous vehicles (AVs) are being deployed on public roads, designing socially compatible behaviors for them is becoming increasingly important. In order to generate safe and efficient actions, AVs need to not only predict the future behaviors of other traffic participants, but also be aware of the uncertainties associated with such behavior prediction. In this paper, we propose an uncertain-aware integrated prediction and planning (UAPP) framework. It allows the AVs to infer the characteristics of other road users online and generate behaviors optimizing not only their own rewards, but also their courtesy to others, and their confidence regarding the prediction uncertainties. We first propose the definitions for courtesy and confidence. Based on that, their influences on the behaviors of AVs in interactive driving scenarios are explored. Moreover, we evaluate the proposed algorithm on naturalistic human driving data by comparing the generated behavior against ground truth. Results show that the online inference can significantly improve the human-likeness of the generated behaviors. Furthermore, we find that human drivers show great courtesy to others, even for those without right-of-way. We also find that such driving preferences vary significantly in different cultures.