Computer Science editorial
Open AccessOA2026
Multi-Target Maneuver Coordinations: Unlocking Coordination Opportunities in Connected Automated Driving
Extending maneuver coordination beyond single-target selection to increase triggered and successful coordinations without protocol changes
Rafael Molina-Masegosa; Sergei S. Avedisov; Miguel Sepulcre; Takayuki Shimizu; Javier Gozalvez; Onur Altintas· 2026· DOI 10.48550/arXiv.2606.22055
The core problem
Maneuver coordination is a key enabler of connected and automated driving, allowing vehicles to negotiate and execute maneuvers that would otherwise be difficult, inefficient, or unsafe. Existing approaches and use cases typically assume coordination with a single predefined target vehicle, which limits the number of coordination opportunities. This paper introduces a maneuver coordination approach based on multi-target selection, which allows a vehicle to identify and select among multiple potential coordination vehicles for a given maneuver. Multi-target maneuver coordination does not require modifications to the maneuver execution logic or to the underlying coordination protocol. Instead, it extends the decision-making process preceding coordination, enabling vehicles to exploit a broader set of feasible cooperative interactions.
Innovation
Results show that multi-target maneuver coordination significantly increases triggered and successfully executed coordinations while maintaining a low computational cost. The proposed approach achieves these gains without requiring the analysis of a large number of potential target vehicles. These improvements preserve coordination success rates while enabling earlier maneuver initiation. The abstract does not provide specific numerical results, but the qualitative findings indicate substantial improvements in coordination opportunities.
Maneuver coordination is a key enabler of connected and automated driving, allowing vehicles to negotiate and execute maneuvers that would otherwise be difficult, inefficient, or unsafe. Existing approaches and use cases typically assume coordination with a single predefined target vehicle, which limits the number of coordination opportunities. This paper introduces a maneuver coordination approach based on multi-target selection, which allows a vehicle to identify and select among multiple potential coordination vehicles for a given maneuver. Multi-target maneuver coordination does not require modifications to the maneuver execution logic or to the underlying coordination protocol. Instead, it extends the decision-making process preceding coordination, enabling vehicles to exploit a broader set of feasible cooperative interactions.
The proposed approach extends the decision-making process preceding coordination by enabling a vehicle to identify and select among multiple potential coordination vehicles for a given maneuver. It does not require modifications to the maneuver execution logic or to the underlying coordination protocol. The selection process considers multiple potential targets, but the approach achieves gains without requiring the analysis of a large number of potential target vehicles, thus maintaining a low computational cost. The methodology is evaluated through simulations or experiments (details not specified in the abstract). The key innovation is the multi-target selection mechanism that broadens the set of feasible cooperative interactions.
Why it matters
The analysis indicates that multi-target maneuver coordination unlocks additional coordination opportunities by allowing vehicles to select among multiple potential partners. This approach maintains low computational cost because it does not require analyzing a large number of potential target vehicles. The preservation of coordination success rates and the ability to initiate maneuvers earlier suggest that the approach is efficient and practical. The findings imply that extending the decision-making process, rather than modifying the protocol or execution logic, is a viable strategy to enhance maneuver coordination in connected automated driving. Future work may explore integration with existing protocols and real-world deployment.
Who should read this
CS practitioners and researchers
Opening member content…