# Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61's Approach to the DARPA Subterranean Challenge

arXiv: https://arxiv.org/abs/2104.09053 · HTML: https://mlsanity.com/paper/2104.09053/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2021.

## Built on by (most cited first, 18 of 18)

- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving](https://mlsanity.com/paper/2402.19341/) (2024)
- [The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement](https://mlsanity.com/paper/2404.10438/) (2024)
- [What's in the Black Box? The False Negative Mechanisms Inside Object Detectors](https://mlsanity.com/paper/2203.07662/) (2022)
- [UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT](https://mlsanity.com/paper/2206.08185/) (2022)
- [QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds](https://mlsanity.com/paper/2406.16578/) (2024)
- [LiDAR-guided object search and detection in Subterranean Environments](https://mlsanity.com/paper/2210.14997/) (2022)
- [STAGE: Scalable and Traversability-Aware Graph based Exploration Planner for Dynamically Varying Environments](https://mlsanity.com/paper/2402.02566/) (2024)
- [Tree Reconstruction using Topology Optimisation](https://mlsanity.com/paper/2205.13192/) (2022)
- [Copiloting Autonomous Multi-Robot Missions: A Game-inspired Supervisory Control Interface](https://mlsanity.com/paper/2204.06647/) (2022)
- [Early Recall, Late Precision: Multi-Robot Semantic Object Mapping under Operational Constraints in Perceptually-Degraded Environments](https://mlsanity.com/paper/2206.10062/) (2022)
- [Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities](https://mlsanity.com/paper/2210.09678/) (2022)
- [Multimodal Dataset from Harsh Sub-Terranean Environment with Aerosol Particles for Frontier Exploration](https://mlsanity.com/paper/2304.14520/) (2023)
- [OHM: GPU Based Occupancy Map Generation](https://mlsanity.com/paper/2206.06079/) (2022)
- [FIT-SLAM -- Fisher Information and Traversability estimation-based Active SLAM for exploration in 3D environments](https://mlsanity.com/paper/2401.09322/) (2024)
- [Scaling 3D Reasoning with LMMs to Large Robot Mission Environments Using Datagraphs](https://mlsanity.com/paper/2407.10743/) (2024)
- [HRI-SA: A Multimodal Dataset for Online Assessment of Human Situational Awareness during Remote Human-Robot Teaming](https://mlsanity.com/paper/2603.18344/) (2026)
- [Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation](https://mlsanity.com/paper/2605.25584/) (2026)

## Abstract (arXiv)

Heterogeneous teams of robots, leveraging a balance between autonomy and human interaction, bring powerful capabilities to the problem of exploring dangerous, unstructured subterranean environments. Here we describe the solution developed by Team CSIRO Data61, consisting of CSIRO, Emesent and Georgia Tech, during the DARPA Subterranean Challenge. These presented systems were fielded in the Tunnel Circuit in August 2019, the Urban Circuit in February 2020, and in our own Cave event, conducted in September 2020. A unique capability of the fielded team is the homogeneous sensing of the platforms utilised, which is leveraged to obtain a decentralised multi-agent SLAM solution on each platform (both ground agents and UAVs) using peer-to-peer communications. This enabled a shift in focus from constructing a pervasive communications network to relying on multi-agent autonomy, motivated by experiences in early circuit events. These experiences also showed the surprising capability of rugged tracked platforms for challenging terrain, which in turn led to the heterogeneous team structure based on a BIA5 OzBot Titan ground robot and an Emesent Hovermap UAV, supplemented by smaller tracked or legged ground robots. The ground agents use a common CatPack perception module, which allowed reuse of the perception and autonomy stack across all ground agents with minimal adaptation.