Multi-Agent Autonomy: Advancements and Challenges in Subterranean Exploration

  title={Multi-Agent Autonomy: Advancements and Challenges in Subterranean Exploration},
  author={Michael T. Ohradzansky and Eugene R. Rush and Danny G. Riley and Andrew B Mills and Shakeeb Ahmad and Steve McGuire and Harel Biggie and Kyle Harlow and Michael J. Miles and Eric W. Frew and C. Heckman and James Sean Humbert},
Artificial intelligence has undergone immense growth and maturation in recent years, though autonomous systems have traditionally struggled when fielded in diverse and previously unknown environments. DARPA is seeking to change that with the Subterranean Challenge, by providing roboticists the opportunity to support civilian and military first responders in complex and high-risk underground scenarios. The subterranean domain presents a handful of challenges, such as limited communication… 

NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge

The paper introduces NeBula (Networked Belief-aware Perceptual Autonomy), an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states).

Copiloting Autonomous Multi-Robot Missions: A Game-inspired Supervisory Control Interface

This work leads to improved human-supervisory control for a multi-agent system reducing overhead from application switching, task planning, execution, and verification while increasing available exploration time with this human-autonomy teaming platform.

UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT

A novel approach for autonomous cooperating UAVs in search and rescue operations in subterranean domains with complex topology that enables fully autonomous and decentralized deployment of a UAV team with seamless simulation-to-world transfer, and proves its advantage over less mobile UGV teams in the flyable space of diverse environments.

Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned

This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021 and demonstrated efficient exploration, reliable detection of objects of interest, and accurate mapping.

RACER: Rapid Collaborative Exploration with a Decentralized Multi-UAV System

RACER, a RApid Collaborative ExploRation approach using a pairwise interaction based on an online hgrid space decomposition, achieves fully decentralized collaborative exploration with multiple UAVs in real world for the first time.

Earthshaker: A Mobile Rescue Robot for Emergencies and Disasters through Teleoperation and Autonomous Navigation

To deal with emergencies and disasters without rescue workers being exposed to dangerous environments, this paper presents a mobile rescue robot, Earthshaker. As a combination of a tracked chassis

Present and Future of SLAM in Extreme Underground Environments

The state of the art in underground SLAM is reported on by discussing different SLAM strategies and results across six teams that participated in the three-year-long SubT competition, with particular emphasis on LIDAR-centric SLAM solutions.

ACHORD: Communication-Aware Multi-Robot Coordination with Intermittent Connectivity

ACHORD provides bandwidth prioritization and timely and reliable data transfer despite intermittent connectivity, and exposes low-layer networking metrics to the application layer to enable robots to autonomously monitor, map, and extend the network via droppable radios, as well as restore connectivity to improve collaborative exploration.

Petri Net Toolbox for Multi-Robot Planning under Uncertainty

A software toolbox that encapsulates, in one single package, modeling, planning, and execution algorithms that implements a state-of-the-art approach to representing multi-robot systems: generalized Petri nets with rewards (GSPNRs).

Early Recall, Late Precision: Multi-Robot Semantic Object Mapping under Operational Constraints in Perceptually-Degraded Environments

The Early Recall, Late Precision (EaRLaP) semantic object mapping pipeline was used by Team CoSTAR in DARPA Subterranean Challenge, where it successfully detected all the artifacts encountered by the team of robots.



Supervised Autonomy for Communication-degraded Subterranean Exploration by a Robot Team

Team CoSTAR's results in the first phase of the DARPA Subterranean Challenge are described, focusing on supervised autonomy of a multi-robot team under severe communication constraints, and the design and initial results obtained from field test campaigns conducted in various tunnel-like environments, leading to the competition.

Explore Locally, Plan Globally: A Path Planning Framework for Autonomous Robotic Exploration in Subterranean Environments

The proposed method employs a bifurcated local- and global-planning design to enable exploration efficiency and path planning solution resourcefulness in subterranean environments.

Graph‐based subterranean exploration path planning using aerial and legged robots

A novel graph‐based subterranean exploration path planning method that is attuned to key topological properties of subterranean settings, such as large‐scale tunnel‐like networks and complex multibranched topologies is proposed.

Autonomous Spot: Long-Range Autonomous Exploration of Extreme Environments with Legged Locomotion

This paper discusses the behaviors and capabilities which emerge from the integration of the autonomy architecture NeBula (Networked Belief-aware Perceptual Autonomy) with next-generation mobility systems and demonstrates the performance of the proposed solutions on physical systems in real-world scenarios.

Progress toward multi‐robot reconnaissance and the MAGIC 2010 competition

A variety of autonomous systems that require minimal human effort to control a large number of autonomously exploring robots are described, including a decoupled centralized planning architecture that allowed individual robots to execute tasks myopically, but whose behavior was coordinated centrally.

Duckiefloat: a Collision-Tolerant Resource-Constrained Blimp for Long-Term Autonomy in Subterranean Environments

An autonomous blimp robot, which has the advantages of low power consumption and collision-tolerance compared to other aerial vehicles like drones, and a failure-aware algorithm with minimal communication to human supervisor to have situational awareness and send control signals to the blimp when needed.

DARPA Subterranean Challenge: Multi-robotic Exploration of Underground Environments

A description of the multi-robot heterogeneous exploration system of the CTU-CRAS team, which scored third place in the Tunnel Circuit round, surpassing the performance of all other non-DARPA-funded competitors.

Mine Tunnel Exploration Using Multiple Quadrupedal Robots

A fully autonomous system for multi-robot mine exploration and mapping using legged quadrupeds, as well as a distributed database mesh networking system for reporting data are described.

LAMP: Large-Scale Autonomous Mapping and Positioning for Exploration of Perceptually-Degraded Subterranean Environments

This paper presents a system architecture to enhance subterranean operation, including an accurate lidar-based front-end, and a flexible and robust back-end that automatically rejects outlying loop closures, and discusses potential improvements, limitations of the state of the art, and future research directions.

Reactive Control and Metric-Topological Planning for Exploration

In this paper, a simple yet reliable method for exploring unknown environments is presented based on bio-inspired reactive control and metric-topological planning that is robust, reliable, and computationally efficient.