Optimal Behavior Planning for Implicit Communication using a Probabilistic Vehicle-Pedestrian Interaction Model

2025-04-21

AI Summary

Modeling implicit communication between autonomous vehicles (AVs) and crossing pedestrians—and accurately predicting pedestrian responses—remains challenging. Method: This paper proposes a closed-loop prediction-and-planning framework. It introduces, for the first time, a two-stage coupling mechanism integrating optimal control theory with a probabilistic pedestrian acceptance model, explicitly characterizing how vehicle maneuvers influence pedestrian crossing probability. Continuous-time optimal control is solved via variational methods, and the solution is embedded with real-time pedestrian response probability estimation and closed-loop validation. Results: Experiments under diverse initial conditions demonstrate significant improvements in pedestrian interpretability of vehicle intent and consistency of their responses. The generated plans reliably elicit intended pedestrian behaviors, thereby enhancing both safety and naturalness in human–vehicle cooperative interactions.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

In interactions between automated vehicles (AVs) and crossing pedestrians, modeling implicit vehicle communication is crucial. In this work, we present a combined prediction and planning approach that allows to consider the influence of the planned vehicle behavior on a pedestrian and predict a pedestrian's reaction. We plan the behavior by solving two consecutive optimal control problems (OCPs) analytically, using variational calculus. We perform a validation step that assesses whether the planned vehicle behavior is adequate to trigger a certain pedestrian reaction, which accounts for the closed-loop characteristics of prediction and planning influencing each other. In this step, we model the influence of the planned vehicle behavior on the pedestrian using a probabilistic behavior acceptance model that returns an estimate for the crossing probability. The probabilistic modeling of the pedestrian reaction facilitates considering the pedestrian's costs, thereby improving cooperative behavior planning. We demonstrate the performance of the proposed approach in simulated vehicle-pedestrian interactions with varying initial settings and highlight the decision making capabilities of the planning approach.

Problem

• Model implicit AV-pedestrian communication for safe interactions
• Predict pedestrian reactions to planned vehicle behavior
• Optimize cooperative behavior using probabilistic acceptance modeling

Innovation

• Combined prediction and planning approach
• Analytical optimal control problems solving
• Probabilistic behavior acceptance modeling