Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913424394420224 |
|---|---|
| author | Hug, David Alzugaray, Ignacio Chli, Margarita |
| author_facet | Hug, David Alzugaray, Ignacio Chli, Margarita |
| contents | Continuous-Time Simultaneous Localization And Mapping (CTSLAM) has become a promising approach for fusing asynchronous and multi-modal sensor suites. Unlike discrete-time SLAM, which estimates poses discretely, CTSLAM uses continuous-time motion parametrizations, facilitating the integration of a variety of sensors such as rolling-shutter cameras, event cameras and Inertial Measurement Units (IMUs). However, CTSLAM approaches remain computationally demanding and are conventionally posed as centralized Non-Linear Least Squares (NLLS) optimizations. Targeting these limitations, we not only present the fastest SymForce-based [Martiros et al., RSS 2022] B- and Z-Spline implementations achieving speedups between 2.43x and 110.31x over Sommer et al. [CVPR 2020] but also implement a novel continuous-time Gaussian Belief Propagation (GBP) framework, coined Hyperion, which targets decentralized probabilistic inference across agents. We demonstrate the efficacy of our method in motion tracking and localization settings, complemented by empirical ablation studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07074 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM Hug, David Alzugaray, Ignacio Chli, Margarita Robotics Computer Vision and Pattern Recognition Symbolic Computation Continuous-Time Simultaneous Localization And Mapping (CTSLAM) has become a promising approach for fusing asynchronous and multi-modal sensor suites. Unlike discrete-time SLAM, which estimates poses discretely, CTSLAM uses continuous-time motion parametrizations, facilitating the integration of a variety of sensors such as rolling-shutter cameras, event cameras and Inertial Measurement Units (IMUs). However, CTSLAM approaches remain computationally demanding and are conventionally posed as centralized Non-Linear Least Squares (NLLS) optimizations. Targeting these limitations, we not only present the fastest SymForce-based [Martiros et al., RSS 2022] B- and Z-Spline implementations achieving speedups between 2.43x and 110.31x over Sommer et al. [CVPR 2020] but also implement a novel continuous-time Gaussian Belief Propagation (GBP) framework, coined Hyperion, which targets decentralized probabilistic inference across agents. We demonstrate the efficacy of our method in motion tracking and localization settings, complemented by empirical ablation studies. |
| title | Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM |
| topic | Robotics Computer Vision and Pattern Recognition Symbolic Computation |
| url | https://arxiv.org/abs/2407.07074 |