Multi-Objective Compliance-Integrated Coevolution For Simulated And Real-World Deployment Of Multi-Robot Marine Autonomy

2026-07-28

AI Summary

This work addresses the challenge in multi-robot oceanic missions where sparse feedback and safety compliance constraints often hinder the simultaneous achievement of high team performance and strict adherence to operational rules. To resolve this trade-off, the paper proposes the MMOCIC framework, which innovatively decouples learning from compliance and integrates high-level team objectives with low-level regulatory constraints through a multi-objective co-evolutionary algorithm. Evaluated in both simulation (up to 12 robots) and real-world experiments (up to 8 robots) on collaborative search-and-rescue tasks, the approach demonstrates exceptional task efficiency while ensuring zero collisions, thereby achieving compliant coordination without sacrificing performance. The framework supports end-to-end deployment in real marine environments, showcasing its practical viability for complex, safety-critical multi-robot operations.

Abstract

Collaborative robots are well-suited to maritime missions that benefit from coordination, such as the exploration of unknown reef structures, inspection of subsea infrastructure, or search-and-rescue operations. These missions typically provide sparse feedback signals for measuring progress and require adherence to safety and regulatory norms, turning a mission into a multi-objective optimization problem. Coevolutionary algorithms can process these sparse feedback signals to generate coordinated behaviors, and in some cases extend behaviors to multiple objectives. However, incorporating high-level team objectives with low-level compliance considerations on the fly to balance norm adherence with team performance remains elusive. This paper introduces a multi-objective framework that blends coevolved behaviors with compliance behaviors to achieve a balance between maximizing team progress and minimizing norm violations. The key insight is to decouple learning from compliance since operational norms are prescribed rather than discovered. We demonstrate that our framework achieves high team performance while avoiding collisions on a collaborative swimmer rescue mission with up to 8 vehicles in a hardware deployment, and 12 vehicles in simulation. The key contribution of this paper is Marine Multi-Objective Compliance-Integrated Coevolution (MMOCIC), a framework that blends team-wide optimization with established norms for real-world deployments of learning-based coordination.

Problem

• multi-objective optimization
• compliance
• coevolution
• multi-robot autonomy
• marine robotics

Innovation

• coevolutionary algorithms
• multi-objective optimization
• compliance integration
• multi-robot marine autonomy
• norm-aware coordination