Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

Source

arXiv

arxiv.org/abs/2607.21488v1

Read the source

Source

Plain-Language Brief

The paper introduces a new deep reinforcement learning architecture called Master-Agent Proto-plan System (MAPS) for coordinating autonomous vehicles at unsignalized intersections. The MAPS system uses a centralized Master agent to generate a global coordination strategy, and decentralized Worker agents to execute vehicle-specific control based on this strategy. The authors test MAPS across 72 intersection configurations in HighwayEnv and find that it significantly reduces average travel time while achieving collision-free navigation, outperforming state-of-the-art baselines.

What the Document Says

  • MAPS is a hierarchical deep reinforcement learning architecture for coordinating autonomous vehicles at unsignalized intersections.
  • The Master agent generates a compact, continuous embedding (proto-plan) that encodes a global coordination strategy.
  • Decentralized Worker agents integrate the proto-plan with local observations to execute vehicle-specific control.
  • The system was tested across 72 intersection configurations in HighwayEnv.
  • MAPS achieves collision-free navigation and reduces average travel time, outperforming state-of-the-art baselines.
  • The learned proto-plans exhibit robust generalization, with a system trained with three agents achieving a 94% success rate when deployed to five-agent scenarios.

Key Concepts Mentioned

  • autonomous vehicles
  • unsignalized intersections
  • multi-agent reinforcement learning (MARL)
  • deep reinforcement learning (DRL)
  • Master-Agent Proto-plan System (MAPS)
  • proto-plan
  • HighwayEnv

Claims Made by the Document

  • MAPS outperforms state-of-the-art baselines in collision-free navigation and reducing average travel time.
  • The learned proto-plans exhibit robust generalization.

Evidence Used

  • Results from testing MAPS across 72 intersection configurations in HighwayEnv.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs. We propose Master-Agent Proto-plan System (MAPS), a hierarchical deep reinforcement learning (DRL) architecture in which a centralized Master agent generates a compact, continuous embedding, denoted as proto-plan, that encodes a global coordination strategy. Decentralized Worker agents integrate this embedding with local observations to execute vehicle-specific control, decoupling strategic intent from tactical execution and enabling independent optimization of each module. As a proof-of-concept evaluation of this coordination mechanism, we test MAPS across 72 intersection configurations in HighwayEnv. MAPS achieves collision-free navigation while significantly reducing average travel time, outperforming state-of-the-art baselines. The learned proto-plans further exhibit robust generalization: a system trained with three agents achieves a 94% success rate when deployed zero-shot to five-agent scenarios, confirming that proto-plan-based hierarchical learning provides a promising framework for multi-vehicle coordination.