Cooperative Lateral Maneuvers Manager for Multi-autonomous Vehicles

Assaad, Mohamad Ali; Talj, Reine; Charara, Ali · 2018 · Crossref

DOI: 10.1109/smc.2018.00453

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the complexity of lateral maneuvers, such as lane changing and overtaking, in autonomous vehicles. While longitudinal control is well-studied, lateral maneuvers require complex decision-making regarding surrounding traffic. The authors propose the Cooperative Lateral Maneuvers Manager (CLMM), a system designed to facilitate cooperation between autonomous vehicles using Vehicle-to-Vehicle (V2V) communications. The CLMM implements the Cooperative Maneuvers Manager for Autonomous Vehicles (CMMAV) framework, which applies Systems of Systems (SoS) principles to enable vehicles to negotiate maneuvers before, during, and after execution. The system is designed to operate in mixed environments, interacting with other CLMM-equipped vehicles, communicating vehicles without CLMM, and non-communicating vehicles, thereby respecting vehicle independence and ensuring stable operation across different stages of technological adoption. The CLMM architecture consists of three primary modules: Environment Assessment, Communication, and Decision-Making. The Environment Assessment module constructs a local map of neighbor vehicles and detects lane status, calculating Time-To-Collision (TTC) to determine if a lane change is safe. The Communication module handles the exchange of Cooperative Awareness Messages (CAM) and Decentralized Environmental Notification Messages (DENM) to share intentions and requests with neighbors. The Decision-Making module evaluates the environment and negotiates with neighbors if a maneuver is blocked; for instance, it may request a neighboring vehicle to slow down to facilitate an overtake. The system intervenes at the decision-making level rather than low-level control, issuing commands to existing vehicle subsystems like Adaptive Cruise Control or lane-changing systems. The system was validated using Anylogic, a multi-agent simulation software, chosen to model the independence of agents within an SoS framework. The simulation environment consisted of a three-lane unidirectional freeway where vehicles were generated randomly with varying speeds. A case study demonstrated the negotiation process: when a subject vehicle intended to overtake but was blocked by a rear neighbor, it sent a request for the neighbor to slow down. If the neighbor complied, the overtake proceeded; otherwise, the subject vehicle followed the lead vehicle until conditions improved. In the broader simulation involving 142 generated vehicles, 32 overtaking maneuvers occurred, including three double overtakes. The results showed that all maneuvers respected security requirements and speed limits, with no collisions observed. The significance of this work lies in providing a robust framework for cooperative lateral maneuvers that enhances safety and traffic flow while preserving vehicle autonomy. By leveraging V2V communication, the CLMM allows vehicles to resolve conflicts through negotiation rather than passive waiting, reducing delays. The paper concludes that the CLMM successfully meets the safety and comfort requirements of the CMMAV framework. Future work includes testing the system with physical autonomous vehicles from the Heudiasyc laboratory to validate performance in fully autonomous and mixed-traffic environments, as well as studying the effects of communication failures.

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.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• lane changing