2000 character limit reached
Resource-Aware Collaborative Monte Carlo Localization with Distribution Compression
Published 2 Apr 2024 in cs.RO | (2404.02010v1)
Abstract: Global localization is essential in enabling robot autonomy, and collaborative localization is key for multi-robot systems. In this paper, we address the task of collaborative global localization under computational and communication constraints. We propose a method which reduces the amount of information exchanged and the computational cost. We also analyze, implement and open-source seminal approaches, which we believe to be a valuable contribution to the community. We exploit techniques for distribution compression in near-linear time, with error guarantees. We evaluate our approach and the implemented baselines on multiple challenging scenarios, simulated and real-world. Our approach can run online on an onboard computer. We release an open-source C++/ROS2 implementation of our approach, as well as the baselines
- Localization from semantic observations via the matrix permanent. Intl. Journal of Robotics Research (IJRR), 35(1-3):73–99, 2016.
- Collaborative multi-robot Monte Carlo localization in assistant robots. International Transactions on Systems Science and Applications, 3(3):227–237, 2007.
- J.L. Bentley. Multidimensional binary search trees used for associative searching. Communications of the ACM, 18(9):509–517, 1975.
- YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint, 2004.10934, 2020.
- Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age. IEEE Trans. on Robotics (TRO), 32:1309–1332, 2016.
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation. In Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2020.
- Monte-Carlo Localization in Underground Parking Lots Using Parking Slot Numbers. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2021.
- Monte carlo localization for mobile robots. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 1999.
- R. Dwivedi and L. Mackey. Kernel Thinning. arXiv preprint arXiv:2105.05842, 2021.
- R. Dwivedi and L. Mackey. Generalized Kernel Thinning. In International Conference on Learning Representations, 2022.
- A Probabilistic Approach to Collaborative Multi-robot Localization. Autonomous Robots, 8:325–344, 2000.
- Markov localization for mobile robots in dynamic environments. Journal of Artificial Intelligence Research (JAIR), 11:391–427, 1999.
- A kernel two-sample test. The Journal of Machine Learning Research, 13(1):723–773, 2012.
- A k-means clustering algorithm. JSTOR: Applied Statistics, 28(1):100–108, 1979.
- Mask R-CNN. In Proc. of the IEEE Intl. Conf. on Computer Vision (ICCV), 2017.
- Connecting Semantic Building Information Models and Robotics: An application to 2D LiDAR-based localization. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2021.
- Localization for mobile robot teams using maximum likelihood estimation. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2002.
- W-RGB-D: Floor-Plan-Based Indoor Global Localization Using a Depth Camera and WiFi. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2014.
- Modeling RFID signal strength and tag detection for localization and mapping. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2009.
- Multi-robot Localization using Relative Observations. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2005.
- H.P. Moravec. Sensor Fusion in Certainty Grids for Mobile Robots. In Sensor Devices and Systems for Robotics (SDSR), 1989.
- Asynchronous multi-centralized cooperative localization. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2010.
- Distributed maximum a posteriori estimation for multi-robot cooperative localization. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2009.
- S. Omohundro. Bumptrees for efficient function, constraint and classification learning. In Proc. of the Advances in Neural Information Processing Systems (NIPS), 1990.
- A collaborative multi-robot localization method without robot identification. In RoboCup 2008: Robot Soccer World Cup XII 12, 2009.
- Low-cost collaborative localization for large-scale multi-robot systems. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2012.
- A. Prorok and A. Martinoli. A reciprocal sampling algorithm for lightweight distributed multi-robot localization. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2011.
- P. Ram and A.G. Gray. Density estimation trees. In Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, 2011.
- V-rep: A versatile and scalable robot simulation framework. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2013.
- Distributed multi-robot localization. IEEE Trans. on Robotics (TRO), pages 179–188, 2000.
- Distribution Compression in Near-linear Time. In Proc. of the Int. Conf. on Learning Representations (ICLR), 2022.
- Robust double-encoder network for rgb-d panoptic segmentation. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2023.
- Probabilistic Robotics. MIT Press, 2005.
- D. Wu and H. Su. An improved probabilistic approach for collaborative multi-robot localization. In 2008 IEEE International Conference on Robotics and Biomimetics, 2009.
- Long-Term Localization Using Semantic Cues in Floor Plan Maps. IEEE Robotics and Automation Letters (RA-L), 8(1):176–183, 2023.
- Constructing Metric-Semantic Maps Using Floor Plan Priors for Long-Term Indoor Localization. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2023.
- Robust Onboard Localization in Changing Environments Exploiting Text Spotting. Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.