Multiple-vehicle Trajectory Planning Framework Considering Vulnerable Road Users
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of real-time trajectory planning for Connected and Automated Vehicles (CAVs) in mixed traffic environments containing Vulnerable Road Users (VRUs), such as pedestrians and cyclists. The research is motivated by the need to improve traffic safety and efficiency, as current CAV systems often struggle with the unpredictable behavior of VRUs, leading to either unsafe interactions or overly conservative driving that disrupts traffic flow. The authors aim to model the multi-agent decision-making process between CAVs and VRUs, anticipating VRU responses to CAV actions while ensuring computational efficiency for real-time implementation. To solve this problem, the authors developed a framework based on game theory and a discrete-time Markov sequential game. This approach models interactions to maximize utility for both vehicles and pedestrians, accounting for the dynamic nature of VRU behavior. Unlike previous methods relying on deep reinforcement learning, which suffer from high computational burdens and poor generalization, this framework uses efficient heuristic algorithms combining customized dynamic programming and adaptive optimization with finite look-ahead anticipation. The methodology defines agent states using kinematic variables and employs a utility function composed of weighted rewards and penalties, including terms for speed maintenance, collision avoidance between vehicles, collision avoidance between vehicles and pedestrians, and lane deviation. The system operates with a planning horizon of eight steps and a temporal resolution of 0.2 seconds. The proposed framework was validated through numerical simulations in a two-lane traffic scenario with a crosswalk. Two distinct experiments were conducted: one with high vehicle density and another with high VRU density. In the high vehicle density scenario, the simulation demonstrated that vehicles maintained speed when pedestrians showed no intent to cross but decelerated appropriately once pedestrians began crossing, ensuring safety without unnecessary stops. In the high VRU density scenario, vehicles successfully yielded to groups of pedestrians, braking as they approached the crosswalk and accelerating promptly after the path cleared. These results indicate that the algorithm effectively balances safety and efficiency, allowing CAVs to adapt their trajectories dynamically based on VRU behavior and traffic conditions. The significance of this work lies in its potential to enhance the operational safety of CAVs in complex, real-world environments. By integrating VRU responses into the planning framework through a computationally efficient game-theoretic approach, the study offers a robust solution for managing interactions in mixed traffic. The findings suggest that this method can significantly improve traffic flow and reduce conflicts between automated vehicles and vulnerable road users, addressing a critical gap in current autonomous driving technologies. The authors conclude that this adaptive framework provides a viable path toward safer and more efficient transportation networks.
Key finding
The proposed game-theoretic trajectory planning framework successfully balances safety and traffic efficiency by enabling CAVs to dynamically adapt their paths in response to the behaviors of vulnerable road users in simulated mixed-traffic scenarios.
Methodology
modeling
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Theoretical Contribution: computational model