Long-Horizon Active SLAM system for multi-agent coordinated exploration

Ossenkopf, Marie; Castro, Gaston; Pessacg, Facundo; Geihs, Kurt; Cristóforis, Pablo De

doi:10.1109/ecmr.2019.8870952

Cited by 9 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schlotfeldt et al [224] introduce an anytime search-based planning formulation that progressively reduces the suboptimality of the multi-agent plans while respecting real-time constraints. Instead of using search-based planning, Ossenkopf et al [225] generate candidate robot actions using RRT*. The sampling is biased to prioritize exploration, map improvement, or localization improvement.…”

Section: Multi-robot Active Slammentioning

confidence: 99%

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Placed

Strader

Carrillo³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

Active Simultaneous Localization and Mapping (SLAM) is the problem of planning and controlling the motion of a robot to build the most accurate and complete model of the surrounding environment. Since the first foundational work in active perception appeared, more than three decades ago, this field has received increasing attention across different scientific communities. This has brought about many different approaches and formulations, and makes a review of the current trends necessary and extremely valuable for both new and experienced researchers. In this work, we survey the state-ofthe-art in active SLAM and take an in-depth look at the open challenges that still require attention to meet the needs of modern applications. After providing a historical perspective, we present a unified problem formulation and review the well-established modular solution scheme, which decouples the problem into three stages that identify, select, and execute potential navigation actions. We then analyze alternative approaches, including beliefspace planning and deep reinforcement learning techniques, and review related work on multi-robot coordination. The manuscript concludes with a discussion of new research directions, addressing reproducible research, active spatial perception, and practical applications, among other topics.

show abstract

Section: Multi-robot Active Slammentioning

confidence: 99%

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Placed

Strader

Carrillo³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…These parameters are entropy, KLD, localization info, visual features, and frontier points. In addition to these parameters, AC-SLAM parameters may include (a) the parameters presented by the authors of [86,87], incorporating the multirobot constraints induced by adding the future robot paths while minimizing the optimal control function (which takes into account the future steps and observations) and minimizing the robot state and map uncertainty and adding them into the belief space (assumed to be Gaussian); (b) parameters relating to exploration and relocalization (to gather at a predefined meeting position) phase of robots as described by [88]; (c) 3D mapping info (OctoMap) used by the authors of [89]; and (d) path and map entropy info, as used in [90], and relative entropy, as mentioned in [91]. Relative observation between agents [88] N Localization utility, information gain, cost of navigation [93] N Visual features, map points [94] Weak edges in pose graphs of target agents [95] Frontier points and map information [96] N Localization utility, information gain, cost of navigation [89] N Visual features, optimized paths [90] N Pose and map entropy, Kullback-Leibler divergence [91] Relative pose entropy [97] Visual features, chained localization [87] Multirobot belief evolution by incorporating mutual observations and future measurements [98] N Frontier points and frontier-to-robot distances [99] N Frontiers and relative-position estimates [100] N, Entropy and future measurements [101] N, Information vector and information matrix 1 Centralized.…”

Section: Active Collaborative Slam (Ac-slam)mentioning

confidence: 99%

Active SLAM: A Review on Last Decade

Ahmed,

Masood,

Fremont

et al. 2023

Sensors

View full text Add to dashboard Cite

This article presents a comprehensive review of the Active Simultaneous Localization and Mapping (A-SLAM) research conducted over the past decade. It explores the formulation, applications, and methodologies employed in A-SLAM, particularly in trajectory generation and control-action selection, drawing on concepts from Information Theory (IT) and the Theory of Optimal Experimental Design (TOED). This review includes both qualitative and quantitative analyses of various approaches, deployment scenarios, configurations, path-planning methods, and utility functions within A-SLAM research. Furthermore, this article introduces a novel analysis of Active Collaborative SLAM (AC-SLAM), focusing on collaborative aspects within SLAM systems. It includes a thorough examination of collaborative parameters and approaches, supported by both qualitative and statistical assessments. This study also identifies limitations in the existing literature and suggests potential avenues for future research. This survey serves as a valuable resource for researchers seeking insights into A-SLAM methods and techniques, offering a current overview of A-SLAM formulation.

show abstract

“…Schlotfeldt et al [214] introduce an anytime search-based planning formulation that progressively reduces the suboptimality of the multi-agent plans while respecting real-time constraints. Instead of using search-based planning, Ossenkopf et al [215] generate candidate robot actions using RRT*. The sampling is biased to prioritize exploration, map improvement, or localization improvement.…”

Section: Multi-robot Active Slammentioning

confidence: 99%

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Placed¹,

Strader²,

Carrillo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Active Simultaneous Localization and Mapping (SLAM) is the problem of planning and controlling the motion of a robot to build the most accurate and complete model of the surrounding environment. Since the first foundational work in active perception appeared, more than three decades ago, this field has received increasing attention across different scientific communities. This has brought about many different approaches and formulations, and makes a review of the current trends necessary and extremely valuable for both new and experienced researchers. In this work, we survey the state-of-the-art in active SLAM and take an in-depth look at the open challenges that still require attention to meet the needs of modern applications. After providing a historical perspective, we present a unified problem formulation and review the classical solution scheme, which decouples the problem into three stages that identify, select, and execute potential navigation actions. We then analyze alternative approaches, including belief-space planning and modern techniques based on deep reinforcement learning, and review related work on multi-robot coordination. The manuscript concludes with a discussion of new research directions, addressing reproducible research, active spatial perception, and practical applications, among other topics.

show abstract

Long-Horizon Active SLAM system for multi-agent coordinated exploration

Cited by 9 publications

References 16 publications

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Active SLAM: A Review on Last Decade

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Contact Info

Product

Resources

About