Interaction-Aware Model Predictive Decision-Making for Socially-Compliant Autonomous Driving in Mixed Urban Traffic Scenarios

TL;DR

This work addresses safe and efficient autonomous driving in urban environments with pedestrians by proposing an interaction-aware model predictive decision-making framework (IAMPDM). It combines an explicit pedestrian motion model based on time-to-collision ($TTC$) with intention modeling, embedding adaptation into the MPC cost via $I_\mathrm{ped}(t)$ and a discounting term to avoid deadlocks. The authors validate the approach in a real-time simulator with a human-in-the-loop design, comparing IAMPDM to non-interactive and rule-based baselines, and analyzing objective metrics such as $TTC_\mathrm{avg}$, $DST_\mathrm{avg}$, and $T_\mathrm{end}$ as well as subjective impressions from 25 participants. The results indicate intention-aware decision-making improves negotiation speed and traffic smoothness, while highlighting the role of human factors and the need for extension to more complex scenarios.

Abstract

This paper presents the experimental validation of an interaction-aware model predictive decision-making (IAMPDM) approach in the course of a simulator study. The proposed IAMPDM uses a model of the pedestrian, which simultaneously predicts their future trajectories and characterizes the interaction between the pedestrian and the automated vehicle. The main benefit of the proposed concept and the experiment is that the interaction between the pedestrian and the socially compliant autonomous vehicle leads to smoother traffic. Furthermore, the experiment features a novel human-in-the-decision-loop aspect, meaning that the test subjects have no expected behavior or defined sequence of their actions, better imitating real traffic scenarios. Results show that intention-aware decision-making algorithms are more effective in realistic conditions and contribute to smoother traffic flow than state-of-the-art solutions. Furthermore, the findings emphasize the crucial impact of intention-aware decision-making on autonomous vehicle performance in urban areas and the need for further research.

Figures (6)

• Figure 1: The pedestrian crosses the street at an unsignalised intersection interacting with an autonomous vehicle. With the courtesy of version1 GmbH.
• Figure 2: Bird's eye view of the scenario with the relevant distances for decision-making
• Figure 3: The simulator setup. Note that the light was turned off during the experiments, and the room was completely dark.
• Figure 6: Results of the subjective assessment
• Figure : Results in case of Delayed Crossing