Asynchronous Adaptive Conditioning for Visual-Inertial SLAM

Keivan, Nima; Patron-Perez, Alonso; Sibley, Gabe

doi:10.1007/978-3-319-23778-7_21

Cited by 14 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A naive implementation would require adding a new state at every IMU measurement, which quickly becomes impractically slow [37]. Therefore, inertial measurements are typically integrated between frames to form relative motion constraints [24,30,[38][39][40]. For standard IMU integration between two frames, the initial condition is given by the state estimate at the first frame.…”

Section: Full Smoothingmentioning

confidence: 99%

On-Manifold Preintegration for Real-Time Visual--Inertial Odometry

et al. 2017

View full text Add to dashboard Cite

Abstract-Current approaches for visual-inertial odometry (VIO) are able to attain highly accurate state estimation via nonlinear optimization. However, real-time optimization quickly becomes infeasible as the trajectory grows over time; this problem is further emphasized by the fact that inertial measurements come at high rate, hence leading to fast growth of the number of variables in the optimization. In this paper, we address this issue by preintegrating inertial measurements between selected keyframes into single relative motion constraints. Our first contribution is a preintegration theory that properly addresses the manifold structure of the rotation group. We formally discuss the generative measurement model as well as the nature of the rotation noise and derive the expression for the maximum a posteriori state estimator. Our theoretical development enables the computation of all necessary Jacobians for the optimization and a-posteriori bias correction in analytic form. The second contribution is to show that the preintegrated IMU model can be seamlessly integrated into a visual-inertial pipeline under the unifying framework of factor graphs. This enables the application of incremental-smoothing algorithms and the use of a structureless model for visual measurements, which avoids optimizing over the 3D points, further accelerating the computation. We perform an extensive evaluation of our monocular VIO pipeline on real and simulated datasets. The results confirm that our modelling effort leads to accurate state estimation in real-time, outperforming state-of-the-art approaches. SUPPLEMENTARY MATERIAL• Video of the experiments: https://youtu.be/CsJkci5lfco • Source-code for preintegrated IMU and structureless vision factors https://bitbucket.org/gtborg/gtsam.

show abstract

Section: Full Smoothingmentioning

confidence: 99%

On-Manifold Preintegration for Real-Time Visual--Inertial Odometry

et al. 2017

View full text Add to dashboard Cite

show abstract

“…As the combined use of the visual and vestibular system is key to human navigation, recent advances in visual-inertial navigation on mobile robots are enabling unprecedented performance in pose estimation in GPS-denied environments using commodity hardware. The literature on visual-inertial navigation is vast, with many contributions proposed over the last two years, including approaches based on filtering [53], [42], [54], [55], [56], [57], fixed-lag smoothing [58], [59], [60], [61], and full smoothing [62], [63], [64], [65], [66], [67], [68]. We refer the reader to [68] for a comprehensive review.…”

Section: Related Work This Work Intersects Several Lines Of Reseamentioning

confidence: 99%

Attention and Anticipation in Fast Visual-Inertial Navigation

2019

View full text Add to dashboard Cite

We study a Visual-Inertial Navigation (VIN) problem in which a robot needs to estimate its state using an on-board camera and an inertial sensor, without any prior knowledge of the external environment. We consider the case in which the robot can allocate limited resources to VIN, due to tight computational constraints. Therefore, we answer the following question: under limited resources, what are the most relevant visual cues to maximize the performance of visual-inertial navigation? Our approach has four key ingredients. First, it is task-driven, in that the selection of the visual cues is guided by a metric quantifying the VIN performance. Second, it exploits the notion of anticipation, since it uses a simplified model for forwardsimulation of robot dynamics, predicting the utility of a set of visual cues over a future time horizon. Third, it is efficient and easy to implement, since it leads to a greedy algorithm for the selection of the most relevant visual cues. Fourth, it provides formal performance guarantees: we leverage submodularity to prove that the greedy selection cannot be far from the optimal (combinatorial) selection. Simulations and real experiments on agile drones show that our approach ensures state-of-the-art VIN performance while maintaining a lean processing time. In the easy scenarios, our approach outperforms appearance-based feature selection in terms of localization errors. In the most challenging scenarios, it enables accurate visual-inertial navigation while appearance-based feature selection fails to track robot's motion during aggressive maneuvers. This paper is conditionally accepted for publication in the IEEE Transaction on Robotics. Please cite the conference version as: L. Carlone and S. Karaman, "Attention and anticipation in fast visual-inertial navigation" 1 This definition oversimplifies the attention mechanisms in humans. While the role of attention is to optimally allocate resources to maximize performance, it is known that some involuntary attention mechanisms can actually hinder the correct execution of a task [2].

show abstract

“…Since consistency in filtering approaches is achieved by the use of first estimates Jacobians [12], a consistent filter would be further susceptible to nonlinearities in the parameters and prior distribution. Considering the aforementioned points, the Adaptive Asynchronous Conditioning (AAC) [6] method is used to adaptively adjust the optimization window of an asynchronous bundle adjuster based on the error of the conditioning edge to the inactive part of the trajectory.…”

Section: Adaptive Slammentioning

confidence: 99%

“…Note that in section IV, the AAC estimator is used with IMU information in order to maintain scale during an experimental trajectory, and also in order to carry the estimation through the loss of tracking caused by de-focus during the zoom operation (center image in Figure 1). The formulation for the integration of IMU measurement is as per [6]. IMU measurements are solely used for scale-correct pose and map estimation.…”

Section: Adaptive Slammentioning

confidence: 99%

Online SLAM with any-time self-calibration and automatic change detection

Keivan

Sibley

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-A framework for online simultaneous localization, mapping and self-calibration is presented which can detect and handle significant change in the calibration parameters. Estimates are computed in constant-time by factoring the problem and focusing on segments of the trajectory that are most informative for the purposes of calibration. A novel technique is presented to detect the probability that a significant change is present in the calibration parameters. The system is then able to re-calibrate. Maximum likelihood trajectory and map estimates are computed using an asynchronous and adaptive optimization. The system requires no prior information and is able to initialize without any special motions or routines, or in the case where observability over calibration parameters is delayed. The system is experimentally validated to calibrate camera intrinsic parameters for a nonlinear camera model on a monocular dataset featuring a significant zoom event partway through, and achieves high accuracy despite unknown initial calibration parameters. Self-calibration and re-calibration parameters are shown to closely match estimates computed using a calibration target. The accuracy of the system is demonstrated with SLAM results that achieve sub-1% distance-travel error even in the presence of significant re-calibration events.

show abstract

Asynchronous Adaptive Conditioning for Visual-Inertial SLAM

Cited by 14 publications

References 15 publications

On-Manifold Preintegration for Real-Time Visual--Inertial Odometry

On-Manifold Preintegration for Real-Time Visual--Inertial Odometry

Attention and Anticipation in Fast Visual-Inertial Navigation

Online SLAM with any-time self-calibration and automatic change detection

Contact Info

Product

Resources

About