Collaborative Exploration with a Marsupial Ground-Aerial Robot Team through Task-Driven Map Compression
Angelos Zacharia, Mihir Rahul Dharmadhikari, Kostas Alexis
AI summary
Problem
Heterogeneous robot teams struggle to share large-scale spatial data efficiently due to limited bandwidth and communication constraints, hindering collaborative exploration in complex environments.
Approach
The authors propose a decentralized exploration framework that strategically deploys an aerial robot from a ground carrier and shares compressed keyframes using a custom Variational Autoencoder to reconstruct volumetric maps for coordinated path planning.
Key results
- Task-driven point cloud compression achieving up to 300x data reduction while preserving occupancy map structure
- Decentralized collaborative exploration framework with an exploration gain-based aerial deployment strategy
- Keyframe-based map sharing and co-localization enabling real-time volumetric map integration
- Validated improvements in exploration efficiency and bandwidth usage across simulations and real-world experiments
Why it matters
Enables reliable, large-scale collaborative mapping and exploration for ground-aerial robot teams in communication-constrained environments like search-and-rescue or subterranean missions.
Abstract
Efficient exploration of unknown environments is crucial for autonomous robots, especially in confined and large- scale scenarios with limited communication. To address this challenge, we propose a collaborative exploration framework for a marsupial ground-aerial robot team that leverages the complementary capabilities of both platforms. The framework employs a graph-based path planning algorithm to guide explo- ration and deploy the aerial robot in areas where its expected gain significantly exceeds that of the ground robot, such as large open spaces or regions inaccessible to the ground platform, thereby maximizing coverage and efficiency. To facilitate large- scale spatial information sharing, we introduce a bandwidth- efficient, task-driven map compression strategy. This method enables each robot to reconstruct resolution-specific volumetric maps while preserving exploration-critical details, even at high compression rates. By selectively compressing and sharing key data, communication overhead is minimized, ensuring effective map integration for collaborative path planning. Simulation and real-world experiments validate the proposed approach, demon- strating its effectiveness in improving exploration efficiency while significantly reducing data transmission.