Inter-robot loop closure detection, e.g., for collaborative simultaneous localization and mapping (CSLAM), is a fundamental capability for many multirobot applications in GPS-denied regimes. In real-world scenarios, this process is resource-intensive as it involves exchanging many observations and verifying a large number of potential matches. This poses severe challenges especially for small-size and low-cost robots with various operational and resource constraints that limit, e.g., energy consumption, communication bandwidth, and computation capacity.
This project aims to develop resource-aware algorithms for distributed inter-robot loop closure detection and measurement selection. In particular, we seek to maximize a monotone submodular performance metric without exceeding computation and communication budgets. This problem is in general NP-hard. We have developed efficient approximation algorithms with provable performance guarantees that handle such resource constraints.