# Enabling Large-scale Heterogeneous Collaboration with Opportunistic Communications

**Authors:** Fernando Cladera, Zachary Ravichandran, Ian D. Miller, M. Ani Hsieh, C. J. Taylor, Vijay Kumar  
**arXiv:** [2309.15975](https://arxiv.org/abs/2309.15975)  
**Date:** 2023-09-27  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2309.15975v1/

## Key points

- Authors address challenges of multi-robot collaboration in large-scale environments without external infrastructure
- Importance of robust software framework for complex tasks despite unreliable communication links
- Introduction of MOCHA framework for resilient multi-robot collaboration with opportunistic communication
- MOCHA operates on gossip communication protocol for peer-to-peer information propagation
- Real-world experiments conducted using commercial-off-the-shelf (COTS) communication hardware to demonstrate effectiveness
- Scalability explored through simulation studies as number of robots increased and communication ranges varied
- Integration of MOCHA into planning stack of autonomous robots with a tailored communication-aware planning algorithm
- Open-source solution provided with MOCHA and high-altitude UAV planning system available on GitHub

## Summary

In their work titled "Enabling Large-scale Heterogeneous Collaboration with Opportunistic Communications," authors Fernando Cladera, Zachary Ravichandran, Ian D. Miller, M. Ani Hsieh, C. J. Taylor, and Vijay Kumar address the challenges of multi-robot collaboration in large-scale environments with limited-sized teams and without external infrastructure. They highlight the importance of a robust software framework that can support complex tasks despite unreliable and intermittent communication links. The authors introduce MOCHA (Multi-robot Opportunistic Communication for Heterogeneous Collaboration), a framework designed to facilitate resilient multi-robot collaboration in scenarios where continuous communications are not guaranteed. MOCHA operates on a gossip communication protocol that enables robots to interact opportunistically whenever communication links become available, allowing for the propagation of information on a peer-to-peer basis. To demonstrate the effectiveness of MOCHA, the authors conducted real-world experiments using commercial-off-the-shelf (COTS) communication hardware. Additionally, they explored the scalability of the system through simulation studies that evaluated its performance as the number of robots increased and communication ranges varied. Furthermore, the authors showcase how MOCHA can be seamlessly integrated into the planning stack of autonomous robots. They present a communication-aware planning algorithm tailored for high-altitude aerial robots executing collaborative tasks while maximizing information sharing with ground robots. Overall, this work provides valuable insights into overcoming communication challenges in multi-robot collaboration settings and offers an open-source solution in the form of MOCHA and an associated high-altitude UAV planning system available on GitHub for further exploration and implementation by researchers and practitioners in robotics and autonomous systems.