Search papers, labs, and topics across Lattice.
This paper presents Marine Multi-Objective Compliance-Integrated Coevolution (MMOCIC), a novel framework that integrates coevolved behaviors with compliance considerations to optimize multi-robot performance in maritime missions. By decoupling the learning process from compliance, the framework effectively balances team progress with adherence to safety and regulatory norms, addressing a critical challenge in robotic coordination. Experimental results demonstrate that MMOCIC achieves high team performance and collision avoidance in both simulated and real-world scenarios involving up to 12 vehicles.
Decoupling compliance from learning enables multi-robot teams to excel in complex maritime missions while adhering to safety norms.
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.
