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.”
Method
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.”
BackgroundMethodThe 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
“[4] within the Map API framework [27].”
Self-citationCollaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation
Golodetz, S., Cavallari, T., Lord, N. A., Prisacariu, V. A., Murray, D. W., & Torr, P. H. S. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2868533 · Cited by 78
“[11] presented a sophisticated decentralised collaborative mapping back-end based on distributed version control.”
BackgroundRDC-SLAM: A Real-Time Distributed Cooperative SLAM System Based on 3D LiDAR
Xie, Y., Zhang, Y., Chen, L. F., Cheng, H., Tu, W., Cao, D., & Li, Q. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3132375 · Cited by 75
“Motivated by ideas for version control tools, we deploy optimistic concurrency control into the distributed robot system, similarly to [35], [41], [42].”
MethodKeep it brief: Scalable creation of compressed localization maps
Dymczyk, M., Lynen, S., Bosse, M. C., & Siegwart, R. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353722 · Cited by 57
“Particularly for larger datasets the partitioning approach will also allow us to leverage our cloud-backend [30] such that we can distribute the compression over multiple machines.”
BackgroundSelf-citationCollaborative navigation for flying and walking robots
Fankhauser, P., Bloesch, M., Krüsi, P., Diethelm, R., Wermelinger, M., Schneider, T., Dymczyk, M., Hutter, M., & Siegwart, R. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759443 · Cited by 62
“[24]), but reliable wireless communication is still a major issue.”
BackgroundSelf-citationMultirobot Collaborative Monocular SLAM Utilizing Rendezvous
Jang, Y., Oh, C., Lee, Y.-W., & Kim, H. J. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3058502 · Cited by 53
Collaborative Visual SLAM Using Compressed Feature Exchange
Opdenbosch, D. V., & Steinbach, E. G. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2878920 · Cited by 49
“garding the map exchange, approaches for map synchronization have been proposed in [16], [17].”
Appearance-based landmark selection for efficient long-term visual localization
Bürki, M., Gilitschenski, I., Stumm, E. S., Siegwart, R., & Nieto, J. I. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759609 · Cited by 35
“The underlying map is assumed to be stored as a pose-graph in a multi-session SLAM framework, as described in [17], which contains information about landmarks (position estimates and feature descriptors of respective observations).”
BackgroundSelf-citationReal-time visual-inertial localization for aerial and ground robots
Oleynikova, H., Burri, M., Lynen, S., & Siegwart, R. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353802 · Cited by 37
“Besides the data-sharing aspect the Map-API provides a mechanism to run algorithms asynchronously on a particular version of the map, while adding new data to it in the meantime.”
MethodSelf-citationEfficient Map Compression for Collaborative Visual SLAM
Opdenbosch, D. V., Aykut, T., Alt, N., & Steinbach, E. G. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00114 · Cited by 30
“[5] addressed the map exchange itself.”
Cross-Descriptor Visual Localization and Mapping
Dusmanu, M., Mikšík, O., Schönberger, J. L., & Pollefeys, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00600 · Cited by 38
“, robots, drones) has been thoroughly studied [17, 11, 34] in the field of robotics.”
BackgroundLarge-scale cooperative 3D visual-inertial mapping in a Manhattan world
Guo, C. X., Sartipi, K., DuToit, R. C., Georgiou, G. A., Li, R., O'Leary, J., Nerurkar, E. D., Hesch, J. A., & Roumeliotis, S. I. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487238 · Cited by 22
Erasing bad memories: Agent-side summarization for long-term mapping
Dymczyk, M., Schneider, T., Gilitschenski, I., Siegwart, R., & Stumm, E. S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759673 · Cited by 23
“In a typical setting, a mapping agent creates a map of the current session locally [4, 2].”
BackgroundMethodSelf-citationResource-Aware Large-Scale Cooperative Three-Dimensional Mapping Using Multiple Mobile Devices
Guo, C. X., Sartipi, K., DuToit, R. C., Georgiou, G. A., Li, R., O'Leary, J., Nerurkar, E. D., Hesch, J. A., & Roumeliotis, S. I. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2858229 · Cited by 24
“Early work on CM [5], as well as more recent distributed approaches [6], determine the relative pose between users by aligning their individual maps without estimating the resulting combined map.”
BackgroundCheckout my map: Version control for fleetwide visual localisation
Gadd, M., & Newman, P. M. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759843 · Cited by 18
“In contrast to [9], we avoid globally consistent metric maps.”
Internet of Robotic Things: A Review
Khalid, S. J. (2021) · Journal of Applied Science and Technology Trends · doi:10.38094/jastt203104 · Cited by 24
“The cloud framework has also been adopted by the robot community called cloud robotics to offload resource-intensive tasks, through data and information exchange between robots app store models [18] [7] [19] [20].”
MethodHastily formed knowledge networks and distributed situation awareness for collaborative robotics
Doherty, P., Berger, C., Rudol, P., & Wzorek, M. (2021) · Autonomous Intelligent Systems · doi:10.1007/s43684-021-00016-w · Cited by 19
“A decentralized approach was proposed in [22].”
Range-based Cooperative Localization with Nonlinear Observability Analysis
Araki, B., Gilitschenski, I., Ogata, T., Wallar, A., Schwarting, W., Choudhury, Z., Karaman, S., & Rus, D. L. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8916915 · Cited by 12
“Recent work has also investigated scenarios where several agents simultaneously create a joint map [15], [16], [17].”
BackgroundDubois, R., Eudes, A., & Frémont, V. (2020) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi49285.2020.9235257 · Cited by 18
“inference [17] and distributed map storage [18].”
Reshaping our model of the world over time
Fehr, M., Dymczyk, M., Lynen, S., & Siegwart, R. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487397 · Cited by 11
Self-citationSparse Pointcloud Map Fusion of Multi-Robot System
Sun, S., Xu, B., Sun, Y., & Sun, Z. (2018) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2018.8570467 · Cited by 7
“Data correspondence between robots is a key issue in collaborative robotic tasks and collaborative simultaneous localization and mapping (SLAM) [1].”
BackgroundData-Efficient Decentralized Visual SLAM
Cieslewski, T., Choudhary, S., & Scaramuzza, D. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461155 · Cited by 200
Self-citationLive Collaborative Large-Scale Dense 3D Reconstruction Using Consumer-Grade Hardware
Golodetz, S., Cavallari, T., Lord, N. A., Prisacariu, V. A., Murray, D. W., & Torr, P. H. S. (2018) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2018.00122 · Cited by 6
“Finally, our approach is unique in making use of the collaborative, interactive paradigm in a dense, large-scale reconstruction context: whilst numerous multi-agent mapping approaches exist, they mostly focus either on sparse/semi-dense mapping in a decentralised [4–8] or centralised [3, 16, 18] context, or on dense m…”
MethodManaging environment models in multi-robot teams
Koch, P., & Lacroix, S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759842 · Cited by 5
“Approach and outline: The proposed framework implements two basic principles: purposiveness of the environment models, that are defined and built according to the processes that exploit them, and economy of means, be they related to computations, storage and communications.”
BackgroundRobustness to connectivity loss for collaborative mapping
Quraishi, A., Cieslewski, T., Lynen, S., & Siegwart, R. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759674 · Cited by 4
“Further, to make Map API suitable for applications where bandwidth is limited, we would like to explore various approaches, such as simplifying Raft leader election and relaxing the complete consistency requirement on the application side.”
MethodInfluentialSelf-citationSIDE : Self Driving Drones Embrace Uncertainty
Bartolini, N., Coletta, A., & Maselli, G. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3135894 · Cited by 4
“The problem of combining chunks of information from several drones to build a single robust view of the environment, has been previously studied under different scenarios [29], [30], [31], [32], [33], [34], [35].”
BackgroundKootstra, G., Edan, Y., Henten, E. J. V., & Bergerman, M. (2015) · doi:10.18174/392250 · Cited by 3
Indoor Mapping for Human Navigation – A Low-Cost SLAM Solution
Röger, C., & Timpf, S. (2018) · GI_Forum · doi:10.1553/giscience2018_01_s152 · Cited by 2
Visual-Inertial Localization and Map Summarization Based on Prior Map
Fu, B., Jiao, Y., Ding, X., Wang, Y., & Xiong, R. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-32-9050-1_40 · Cited by 1
Dubois, R. (2021) · theses.fr (ABES) · doi:10.70675/7c156bfaze487z4eeczbc6fz5e4cc0a88493 · Cited by 1
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.