Assistive Decision-Making for Right of Way Navigation at Uncontrolled Intersections

2025-09-22

AI Summary

To address the high accident risk at unsignalized intersections—stemming from ambiguous right-of-way, occluded visibility, and unpredictable driver behavior—this paper proposes the first POMDP-based decision-support framework for human-driven vehicles. Methodologically, we develop a high-fidelity simulation platform incorporating stochastic traffic flow, pedestrian dynamics, visual occlusions, and adversarial scenarios, and systematically evaluate three probabilistic planners—QMDP, POMCP, and DESPOT—against a deterministic finite-state machine baseline. Our key contribution is the novel application of POMDPs to right-of-way assistance for human drivers, revealing the critical role of explicit uncertainty modeling in safety-critical decision-making. Experimental results demonstrate that probabilistic planners achieve up to 97.5% collision-free intersection traversal; among them, POMCP attains the highest safety performance, while DESPOT achieves the best trade-off between computational efficiency and real-time feasibility.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Uncontrolled intersections account for a significant fraction of roadway crashes due to ambiguous right-of-way rules, occlusions, and unpredictable driver behavior. While autonomous vehicle research has explored uncertainty-aware decision making, few systems exist to retrofit human-operated vehicles with assistive navigation support. We present a driver-assist framework for right-of-way reasoning at uncontrolled intersections, formulated as a Partially Observable Markov Decision Process (POMDP). Using a custom simulation testbed with stochastic traffic agents, pedestrians, occlusions, and adversarial scenarios, we evaluate four decision-making approaches: a deterministic finite state machine (FSM), and three probabilistic planners: QMDP, POMCP, and DESPOT. Results show that probabilistic planners outperform the rule-based baseline, achieving up to 97.5 percent collision-free navigation under partial observability, with POMCP prioritizing safety and DESPOT balancing efficiency and runtime feasibility. Our findings highlight the importance of uncertainty-aware planning for driver assistance and motivate future integration of sensor fusion and environment perception modules for real-time deployment in realistic traffic environments.

Problem

• Addressing ambiguous right-of-way rules at uncontrolled intersections
• Developing assistive navigation for human-driven vehicles under uncertainty
• Evaluating probabilistic planning methods for collision-free intersection navigation

Innovation

• POMDP formulation for right-of-way reasoning
• Probabilistic planners outperforming rule-based baseline
• Simulation testbed with stochastic agents and occlusions