Map API - scalable decentralized map building for robots
The DOI matches its Crossref record; 21 of the 22 references it cites were found in a registry or an index.
Abstract
Large scale, long-term, distributed mapping is a core challenge to modern field robotics. Using the sensory output of multiple robots and fusing it in an efficient way enables the creation of globally accurate and consistent metric maps. To combine data from multiple agents into a global map, most existing approaches use a central entity that collects and manages the information from all agents. Often, the raw sensor data of one robot needs to be made available to processing algorithms on other agents due to the lack of computational resources on that robot. Unfortunately, network latency and low bandwidth in the field limit the generality of such an approach and make multi-robot map building a tedious task. In this paper, we present a distributed and decentralized back-end for concurrent and consistent robotic mapping. We propose a set of novel approaches that reduce the bandwidth usage and increase the effectiveness of inter-robot communication for distributed mapping. Instead of locking access to the map during operations, we define a version control system which allows concurrent and consistent access to the map data. Updates to the map are then shared asynchronously with agents which previously registered notifications. A technique for data lookup is provided by state-of-the-art algorithms from distributed computing. We validate our approach on real-world datasets and demonstrate the effectiveness of the proposed algorithms.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Time, clocks, and the ordering of events in a distributed system
Lamport, L. (1978) · Communications of the ACM · doi:10.1145/359545.359563 · Cited by 8,488 · cited 1×
“With those, the user of Map API is free to implement conflict resolution tailored to the given application.”
MethodBundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988 · cited 1×
“Participating in a chunk implies that the peer must replicate the current state of the chunk and provide its data to new peers that are interested in the chunk.”
BackgroundIn search of an understandable consensus algorithm
Ongaro, D., & Ousterhout, J. K. (2014) · USENIX Annual Technical Conference · Cited by 3,398
Distributed Consensus in Multi-vehicle Cooperative Control
Ren, W., & Beard, R. W. (2008) · Communications and Control Engineering · doi:10.1007/978-1-84800-015-5 · Cited by 2,826 · cited 1×
“The simplest, yet limited approach to consensus is to average conflicting values [12, 13].”
BackgroundChord: A scalable peer-to-peer lookup service for internet applications
Stoica, I., Morris, R., Karger, D., Kaashoek, M. F., & Balakrishnan, H. (2001) · ACM SIGCOMM Computer Communication Review · doi:10.1145/964723.383071 · Cited by 1,923
Lamport, L. (2001) · Cited by 1,325
The Chubby lock service for loosely-coupled distributed systems
Burrows, M. (2006) · Operating Systems Design and Implementation · doi:10.5555/1298455.1298487 · Cited by 877
A Probabilistic Approach to Collaborative Multi-Robot Localization
Fox, D., Burgard, W., Kruppa, H., & Thrun, S. (2000) · Autonomous Robots · doi:10.1023/a:1008937911390 · Cited by 692 · cited 1×
“Approaches such as the work of Fox [1], Martinelli [2], Trawny [3] or more recently Carillo-Arce [4] to name a few, demonstrated impressive results on how robots can estimate their position in a common frame of reference using a minimum amount of data exchange.”
BackgroundWaibel, M., Beetz, M., Civera, J., D'Andrea, R., Elfring, J., Gálvez-López, D., Häussermann, K., Janssen, R., Montiel, J. M. M., Perzylo, A., et al. (2011) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2011.941632 · Cited by 429 · cited 2×
“In contrast, RoboEarth [7], Rapyuta [8] and Map API , which we propose in this paper, offer solutions to the question of distributing data and computational work between agents which we see as a foundation for any distributed estimation algorithm.”
BackgroundC2TAM: A Cloud framework for cooperative tracking and mapping
Riazuelo, L., Civera, J., & Montiel, J. M. M. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.11.007 · Cited by 254 · cited 2×
“Despite their decentralized architecture, frameworks such as C2TAM [5] and CVSLAM [6] fall back to a central entity for map assembly.”
MethodCollaborative monocular SLAM with multiple Micro Aerial Vehicles
Forster, C., Lynen, S., Kneip, L., & Scaramuzza, D. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696923 · Cited by 201 · cited 3×
“Commonly, the shared map data is locked for the time of a given operation to guarantee consistency by serializing data-access by multiple peers [6].”
BackgroundMethodSelf-citationDecentralized multi-robot cooperative localization using covariance intersection
Carrillo-Arce, L. C., Nerurkar, E. D., Gordillo, J. L., & Roumeliotis, S. I. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696534 · Cited by 178 · cited 1×
“Approaches such as the work of Fox [1], Martinelli [2], Trawny [3] or more recently Carillo-Arce [4] to name a few, demonstrated impressive results on how robots can estimate their position in a common frame of reference using a minimum amount of data exchange.”
BackgroundDDF-SAM 2.0: Consistent distributed smoothing and mapping
Cunningham, A., Indelman, V., & Dellaert, F. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6631323 · Cited by 171 · cited 1×
“However, there are situations in which a map is best built and maintained decentrally : Cunningham [9] as well as Vidal-Calleja et al [10] follow a decentralized approach in which data is owned by the agents that created it, assuming that these agents are available during the scope of the…”
BackgroundCloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost Robots
Mohanarajah, G., Usenko, V., Singh, M., D’Andrea, R., & Waibel, M. (2015) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2015.2408456 · Cited by 155 · cited 1×
“In contrast, RoboEarth [7], Rapyuta [8] and Map API , which we propose in this paper, offer solutions to the question of distributing data and computational work between agents which we see as a foundation for any distributed estimation algorithm.”
BackgroundThe gist of maps - summarizing experience for lifelong localization
Dymczyk, M., Lynen, S., Cieslewski, T., Bosse, M. C., Siegwart, R., & Furgale, P. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139575 · Cited by 86
Self-citationCooperative multi-robot localization under communication constraints
Trawny, N., Roumeliotis, S. I., & Giannakis, G. B. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152606 · Cited by 81 · cited 1×
“Approaches such as the work of Fox [1], Martinelli [2], Trawny [3] or more recently Carillo-Arce [4] to name a few, demonstrated impressive results on how robots can estimate their position in a common frame of reference using a minimum amount of data exchange.”
BackgroundLynen, S., Bosse, M., Furgale, P., & Siegwart, R. (2014) · 2014 2nd International Conference on 3D Vision · doi:10.1109/3dv.2014.36 · Cited by 73 · cited 1×
“To benchmark centralized serial processing against decentralized parallel processing, we use the operation of registering the data from the aerial robots with the data from the ground robots, for which we use loop closure [23] and bundle adjustment optimization [18].”
MethodSelf-citationLarge scale multiple robot visual mapping with heterogeneous landmarks in semi-structured terrain
Vidal-Calleja, T. A., Berger, C., Solà, J., & Lacroix, S. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.05.008 · Cited by 71 · cited 1×
“However, there are situations in which a map is best built and maintained decentrally : Cunningham [9] as well as Vidal-Calleja et al [10] follow a decentralized approach in which data is owned by the agents that created it, assuming that these agents are available during the scope of the…”
BackgroundMartinelli, A. (2007) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2007.4399043 · Cited by 43
Aspects of a trigger subsystem in an integrated database system
Eswaran, K. P. (1976) · doi:10.5555/800253.807683 · Cited by 27
Distributed multi-camera visual mapping using topological maps of planar regions
Montijano, E., & Sagüés, C. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2010.12.022 · Cited by 15
Research works printed but not linked: 2
- ren, 2007, Distributed Consensus in Multivehicle Cooperative Control Theory and Applications
- 2008, How to improve the reliability of chord?, OTM Workshops on the Move to Meaningful Internet Systems
Cited by
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
“[50] is a first study in this direction.”
Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization
Schneider, T., Dymczyk, M., Fehr, M., Egger, K., Lynen, S., Gilitschenski, I., & Siegwart, R. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2800113 · Cited by 267
“It has also served as a research platform for map summarization [10–13], map quality evaluation [14], multisession 3d reconstruction [15], topological mapping [16], visual localization [17–19], and decentralized mapping [20].”
MethodSelf-citationReal-time visual-inertial mapping, re-localization and planning onboard MAVs in unknown environments
Burri, M., Oleynikova, H., Achtelik, M., & Siegwart, R. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353622 · Cited by 155
“Additionally, we use a framework that allows us to access the map from several threads at once and do transaction-based changes [14].”
MethodSelf-citationA Comprehensive Survey of Recent Trends in Cloud Robotics Architectures and Applications
Saha, O., & Dasgupta, P. (2018) · Robotics · doi:10.3390/robotics7030047 · Cited by 137
“[28] proposed a set of novel techniques that lower the bandwidth usage and improve inter-robot communication for distributed mapping by defining a version control system that allows concurrent and consistent access to the map data.”
BackgroundMethod
Metadata
- Authors
- Cieslewski, T., Lynen, S., Dymczyk, M., Magnenat, S., & Siegwart, R.
- Affiliations
- ETH Zurich (CH)
- Venue
- 2015 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2015-05
- Pages
- 6241-6247
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W4241431727
- Cited by
- 36
- References
- 22
- Citations by year
- 2021: 7 · 2020: 1 · 2019: 2 · 2018: 11 · 2016: 10 · 2015: 5
- FWCI
- 15.03
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Control and Systems Engineering › Robotics and Automated Systems
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Path Planning Algorithms
- Keywords
- multi-robot mapping, distributed mapping, version control, inter-robot communication, bandwidth reduction, data lookup, map consistency, field robotics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.