Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM

@article{Denniston2022LoopCP,
  title={Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM},
  author={Chris Denniston and Yun Chang and Andrzej Reinke and Kamak Ebadi and Gaurav S. Sukhatme and Luca Carlone and Benjamin Morrell and Ali-akbar Agha-mohammadi},
  journal={IEEE Robotics and Automation Letters},
  year={2022},
  volume={7},
  pages={9651-9658}
}
Multi-robot SLAM systems in GPS-denied environments require loop closures to maintain a drift-free centralized map. With an increasing number of robots and size of the environment, checking and computing the transformation for all the loop closure candidates becomes computationally infeasible. In this work, we describe a loop closure module that is able to prioritize which loop closures to compute based on the underlying pose graph, the proximity to known beacons, and the characteristics of the… 

Figures and Tables from this paper

Decentralized LiDAR-inertial Swarm Odometry

TLDR
A fully decentralized state estimation method for aerial swarm systems, in which each drone performs precise ego-state estimation, exchanges ego- state and mutual observation information by wireless communication, and estimates relative state with respect to (w.r.t.) the rest of UAVs, all in real-time and only based on LiDAR-inertial mea- surements.

D-Lite: Navigation-Oriented Compression of 3D Scene Graphs under Communication Constraints

TLDR
This paper uses graph-theoretic tools, namely graph spanners, to design heuristic strategies that efficiently compress 3D Scene Graphs to enable communication under bandwidth constraints, and designs compression strategies that are navigation-oriented in that they are designed to approximately preserve shortest paths between locations of interest.

Present and Future of SLAM in Extreme Underground Environments

TLDR
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.

LAMP 2.0: A Robust Multi-Robot SLAM System for Operation in Challenging Large-Scale Underground Environments

TLDR
This letter reports on a multi-robot SLAM system developed by team CoSTAR in the context of the DARPA Subterranean Challenge, and extends the previous work, LAMP, by incorporating a single-ro Bot front-end interface that is adaptable to different odometry sources and lidar configurations.

References

SHOWING 1-10 OF 31 REFERENCES

Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection

TLDR
The Black-Rangarajan duality between robust estimation and outlier processes is leveraged, and it is shown thatgraduated non-convexity (<monospace>GNC</monospace>) can be used in conjunction with non-minimal solvers to compute robust solutions, without requiring an initial guess.

Generalized-ICP

In this paper we combine the Iterative Closest Point (’ICP’) and ‘point-to-plane ICP‘ algorithms into a single probabilistic framework. We then use this framework to model locally planar surface

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

TLDR
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.

Fast Loop Closure Selection Method with Spatiotemporal Consistency for Multi-Robot Map Fusion

TLDR
A fast inter-robot loop closure selection method that integrates the consistency and topology relationship of inter- robot measurements, which both conform to the continuity characteristics of similar scenes and spatiotemporal consistency is proposed.

LAMP 2.0: A Robust Multi-Robot SLAM System for Operation in Challenging Large-Scale Underground Environments

TLDR
This letter reports on a multi-robot SLAM system developed by team CoSTAR in the context of the DARPA Subterranean Challenge, and extends the previous work, LAMP, by incorporating a single-ro Bot front-end interface that is adaptable to different odometry sources and lidar configurations.

Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection

TLDR
A general-purpose learning architecture towards submodular maximization at scale, with decentralized communications that leverages a graph neural network (GNN) to capture local interactions of the robots and learns decentralized decision-making for the robots.

Neural Trees for Learning on Graphs

TLDR
It is proved that any continuous G -invariant/equivariant function can be approximated by a nonlinear combination of such probability distribution functions over G, and it is shown that the neural tree architecture can approximate any smooth probability distribution function over an undirected graph.

CHORD: Distributed Data-Sharing via Hybrid ROS 1 and 2 for Multi-Robot Exploration of Large-Scale Complex Environments

TLDR
To the knowledge, this work is the first real-world demonstration of a ROS 2-based multi-robot system in such large-scale extreme environments and encourages wider adoption of ROS 2 in field robotics applications.

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

TLDR
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).