Distributed Gaussian Process Mapping for Robot Teams with Time-varying Communication

  title={Distributed Gaussian Process Mapping for Robot Teams with Time-varying Communication},
  author={James Di and Ehsan Zobeidi and Alec Koppel and Nikolay A. Atanasov},
  journal={2022 American Control Conference (ACC)},
Multi-agent mapping is a fundamentally important capability for autonomous robot task coordination and execution in complex environments. While successful algorithms have been proposed for mapping using individual platforms, cooperative online mapping for teams of robots remains largely a challenge. A critical question to enabling this capability is how to process and aggregate incrementally observed local information among individual platforms, especially when their ability to communicate is… 

Figures and Tables from this paper


  • Q. ZouMonika Sester
  • Environmental Science
    The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • 2022
Abstract. The quality of environmental perception is of great interest for localization tasks in autonomous systems. Maps, generated from the sensed information, are often used as additional spatial

Dense Incremental Metric-Semantic Mapping for Multiagent Systems via Sparse Gaussian Process Regression

An online probabilistic metric-semantic mapping approach for mobile robot teams relying on streaming RGB-D observations based on online Gaussian process training and inference and avoids the complexity of GP classification by regressing a truncated signed distance function of the regions occupied by different semantic classes.

DDF-SAM: Fully distributed SLAM using Constrained Factor Graphs

DDF-SAM is presented, a novel method for efficiently and robustly distributing map information across a team of robots, to achieve scalability in computational cost and in communication bandwidth and robustness to node failure and to changes in network topology.

CCM‐SLAM: Robust and efficient centralized collaborative monocular simultaneous localization and mapping for robotic teams

CCM‐SLAM is presented, a centralized collaborative SLAM framework for robotic agents, each equipped with a monocular camera, a communication unit, and a small processing board, that ensures their autonomy as individuals while a central server with potentially bigger computational capacity enables their collaboration.

DOOR-SLAM: Distributed, Online, and Outlier Resilient SLAM for Robotic Teams

DOOR-SLAM is a fully distributed SLAM system with an outlier rejection mechanism that can work with less conservative parameters, which produces more inter-robot loop closures, successfully rejects outliers, and results in accurate trajectory estimates, while requiring low communication bandwidth.

Coordination strategies for multi-robot exploration and mapping

Through careful consideration of robot team coordination and exploration strategy, large numbers of mobile robots can be allocated to accomplish the mapping task more quickly and accurately.

Factor Graphs for Robot Perception

The use of factor graphs for the modeling and solving of large-scale inference problems in robotics is reviewed, and the iSAM class of algorithms that can reuse previous computations are discussed, re-interpreting incremental matrix factorization methods as operations on graphical models, introducing the Bayes tree in the process.

Dense Incremental Metric-Semantic Mapping via Sparse Gaussian Process Regression

An online Gaussian Process training and inference approach, which avoids the complexity of GP classification by regressing a truncated signed distance function representation of the regions occupied by different semantic classes.

DDF-SAM 2.0: Consistent distributed smoothing and mapping

This paper presents and compares three summarization techniques, with two exact approaches and an approximation, and evaluates the proposed system in a synthetic example and shows the augmented local system and the associated summarization technique do not double-count information, while keeping performance tractable.

A Saddle Point Algorithm for Networked Online Convex Optimization

An algorithm to learn optimal actions in convex distributed online problems is developed and it is shown that decisions made with this saddle point algorithm lead to regret whose order is not larger than O(√T), where T is the total operating time.

Distributed optimization over time-varying directed graphs

This work develops a broadcast-based algorithm, termed the subgradient-push, which steers every node to an optimal value under a standard assumption of subgradient boundedness, which converges at a rate of O (ln t/√t), where the constant depends on the initial values at the nodes, the sub gradient norms, and, more interestingly, on both the consensus speed and the imbalances of influence among the nodes.