2000 character limit reached
RMap: Millimeter-Wave Radar Mapping Through Volumetric Upsampling (2310.13188v1)
Published 19 Oct 2023 in cs.RO
Abstract: Millimeter Wave Radar is being adopted as a viable alternative to lidar and radar in adverse visually degraded conditions, such as the presence of fog and dust. However, this sensor modality suffers from severe sparsity and noise under nominal conditions, which makes it difficult to use in precise applications such as mapping. This work presents a novel solution to generate accurate 3D maps from sparse radar point clouds. RMap uses a custom generative transformer architecture, UpPoinTr, which upsamples, denoises, and fills the incomplete radar maps to resemble lidar maps. We test this method on the ColoRadar dataset to demonstrate its efficacy.
- “Present and future of slam in extreme underground environments” In arXiv preprint arXiv:2208.01787, 2022
- “Are we ready for radar to replace lidar in all-weather mapping and localization?” In IEEE Robotics and Automation Letters 7.4 IEEE, 2022, pp. 10328–10335
- “Radar-inertial state estimation and obstacle detection for micro-aerial vehicles in dense fog” In Experimental Robotics: The 17th International Symposium, 2021, pp. 3–16 Springer
- “See through smoke: robust indoor mapping with low-cost mmwave radar” In Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services, 2020, pp. 14–27
- “OctoMap: An efficient probabilistic 3D mapping framework based on octrees” In Autonomous robots 34 Springer, 2013, pp. 189–206
- “ColoRadar: The direct 3D millimeter wave radar dataset” In The International Journal of Robotics Research 41.4 SAGE Publications Sage UK: London, England, 2022, pp. 351–360
- “The fundamentals of millimeter wave sensors” In Texas Instruments, 2017, pp. 1–8 Texas Instruments, Inc. URL: https://www.ti.com/lit/wp/spyy005a/spyy005a.pdf
- “Principles of Modern Radar: Basic Principles, Volume 1” Institution of EngineeringTechnology, 2010
- “Principles of Modern Radar: Advanced Techniques, Volume 2” Institution of EngineeringTechnology, 2012
- FINN HM “Adaptive detection mode with threshold control as a function of spatially sampled clutter-level estimates” In Rca Rev. 29, 1968, pp. 414–465
- “Probably unknown: Deep inverse sensor modelling radar” In 2019 International Conference on Robotics and Automation (ICRA), 2019, pp. 5446–5452 IEEE
- Yeong Sang Park, Joowan Kim and Ayoung Kim “Radar localization and mapping for indoor disaster environments via multi-modal registration to prior LiDAR map” In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, pp. 1307–1314 IEEE
- “High resolution point clouds from mmwave radar” In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 4135–4142 IEEE
- “Learned depth estimation of 3d imaging radar for indoor mapping” In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 13260–13267 IEEE
- “4D iRIOM: 4D Imaging Radar Inertial Odometry and Mapping” In IEEE Robotics and Automation Letters IEEE, 2023
- “Pointnet: Deep learning on point sets for 3d classification and segmentation” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 652–660
- “Pointnet++: Deep hierarchical feature learning on point sets in a metric space” In Advances in neural information processing systems 30, 2017
- “Pcn: Point completion network” In 2018 international conference on 3D vision (3DV), 2018, pp. 728–737 IEEE
- “Attention is all you need” In Advances in neural information processing systems 30, 2017
- “Pointr: Diverse point cloud completion with geometry-aware transformers” In Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 12498–12507
- “Foldingnet: Point cloud auto-encoder via deep grid deformation” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 206–215
- “AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers” In arXiv preprint arXiv:2301.04545, 2023
- “Seedformer: Patch seeds based point cloud completion with upsample transformer” In European conference on computer vision, 2022, pp. 416–432 Springer
- Haoqiang Fan, Hao Su and Leonidas J Guibas “A point set generation network for 3d object reconstruction from a single image” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 605–613
- “Multi-agent autonomy: Advancements and challenges in subterranean exploration” In arXiv preprint arXiv:2110.04390, 2021
- “Flexible supervised autonomy for exploration in subterranean environments” In arXiv preprint arXiv:2301.00771, 2023
- “Fixing weight decay regularization in adam”, 2018
- “What do single-view 3d reconstruction networks learn?” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3405–3414