Publications

2018

1. [M.Sc.]
   Toward Invariant Visual-Inertial State Estimation using Information Sparsification Hsiung, J. Master Thesis 2018 [Abs] [PDF] [Presentation]

   In this work, we address two current challenges in real-time visual-inertial odometry (VIO) systems — efficiency and nonlinearity. To this end, we present a novel approach to tightly couple visual and inertial measurements in a fixed-lag VIO framework using information sparsification. To bound computational complexity, fixed-lag smoothers perform marginalization of variables but consequently deteriorate accuracy and especially efficiency. Current state-of-the-art approaches work around this by selectively discarding measurements and marginalizing additional variables. However, such strategies are sub-optimal from an information-theoretic perspective. In contrast, our approach formulates an optimization based on Kullback-Leibler divergence to preserve most of the information. To validate our approach, we conduct extensive real-time drone tests and perform comparisons to current state-of-the-art fixed-lag VIO methods in the EuRoC visual-inertial dataset. The experimental results show that the proposed method achieves competitive and superior accuracy in almost all trials. In achieving a more efficient and accurate state estimator, the second part of the work presents the on-going progress in formulating an optimization-based VIO system using matrix Lie groups. Inspired by the recently developed Invariant-EKF framework, the proposed framework presents better convergence and addresses the consistency problem commonly seen in EKF-based and fixed-lag frameworks. In particular, we provide detailed derivations of a novel IMU preintegration framework using the group affine properties. Simulation results show our proposed formulation allows the nonlinear optimizer to converge with significantly fewer iterations, as compared to the state-of-the-art IMU preintegration scheme.

2. [IROS]
   Information Sparsification in Visual-Inertial Odometry (Best Conference Paper Finalist) Hsiung, J., Hsiao, M., Westman, E., Valencia, R., Kaess, M. IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS) 2018 [Abs] [PDF]

   In this paper, we present a novel approach to tightly couple visual and inertial measurements in a fixed-lag visual-inertial odometry (VIO) framework using information sparsification. To bound computational complexity, fixed-lag smoothers typically marginalize out variables, but consequently introduce a densely connected linear prior which significantly deteriorates accuracy and efficiency. Current state-of-the-art approaches account for the issue by selectively discarding measurements and marginalizing additional variables. However, such strategies are sub-optimal from an informationtheoretic perspective. Instead, our approach performs a dense marginalization step and preserves the information content of the dense prior. Our method sparsifies the dense prior with a nonlinear factor graph by minimizing the information loss. The resulting factor graph maintains information sparsity, structural similarity, and nonlinearity. To validate our approach, we conduct real-time drone tests and perform comparisons to current state-of-the-art fixed-lag VIO methods in the EuRoC visual-inertial dataset. The experimental results show that the proposed method achieves competitive and superior accuracy in almost all trials. We include a detailed run-time analysis to demonstrate that the proposed algorithm is suitable for realtime applications.

3. [WM]
   Localized Imaging and Mapping for Underwater Fuel Storage Basins Hsiung, J., Tallaksen, A., Papincak, L., Suresh, S., Jones, H., Whittaker, W., Kaess, M. In Proceedings of the Symposium on Waste Management 2018 [Abs] [PDF]

   Current methods for inspection of spent nuclear fuel storage basins involve lowering a single camera for visual inspection of walls and other structures. We present a localized inspection solution where the images are automatically annotated by localization information and a 3D model of the inspected area is generated. The system consists of an underwater sensor pod containing a stereo pair of cameras, light source, inertial measurement unit, and a pressure sensor. The sensors are time synchronized to provide precise measurements. We describe both the sensor pod and the algorithms that keep the pod localized. Preliminary results from in-air testing of a prototype are presented.

2017

1. [JFR]
   A Multi-Autonomous Underwater Vehicle System for Autonomous Tracking of Marine Life Lin, Y., Hsiung, J., Piersall, R., White, C., Lowe, C. G., Clark, C. M. Journal of Field Robotics (JFR) 2017 [Abs] [PDF]

   This paper presents a multi-autonomous underwater vehicle system capable of cooperatively and autonomously tracking and following marine targets (i.e., fish) tagged with an acoustic transmitter. The AUVs have been equipped with stereo-hydrophones that receive signals broadcasted by the acoustic transmitter tags to enable real-time calculation of bearing-to-tag and distance-to-tag measurements. These measurements are shared between AUVs via acoustic modem and fused within each AUV’s particle filter for estimating the target’s position. The AUVs use a leader/follower multi-AUV control system to enable the AUVs to drive toward the estimated target state by following collision-free paths. Once within the local area of the target, the AUVs circumnavigate the target state until it moves to another area. The system builds on previous work by incorporating a new SmartTag package that can be attached to an individual’s dorsal fin. The SmartTag houses a full inertial measurement unit (INU), video logger, acoustic transmitter, and timed release mechanism. After real-time AUV tracking experiments, the SmartTag is recovered. Logged IMU data are fused with logged AUV-obtained acoustic tag measurements within a particle filter to improve state estimation accuracy. This improvement is validated through a series of multi-AUV shark and boat tracking experiments conducted at Santa Catalina Island, California. When compared with previous work that did not use the SmartTag package, results demonstrated a decrease in mean position estimation error of 25–75%, tag orientation estimation errors dropped from 80° to 30° , the sensitivity of mean position error with respect to distance to the tag was less by a factor of 50, and the sensitivity of mean position error with respect to acoustic signal reception frequency to the tag was 25 times less. These statistics demonstrate a large improvement in the system’s robustness when the SmartTag package is used.

2016

1. [IROS]
   Stochastic modeling and control for tracking the periodic movement of marine animals via AUVs Smith, K. D., Hsiung, J., White, C., Lowe, C. G., Clark, C. M. In IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS) 2016 [Abs] [PDF]

   This paper presents a graph-based model of periodic migrations of tagged fish populations and two multi-AUV stochastic controllers developed to track these fish from the model. The model presented in this paper characterizes patterns in the historical movement of tagged fish and is used to develop stochastic tracking by a “model based control” and a “feedback control”. These two controllers permit swarms of AUVs to track the transition probabilities of the tagged population between vertices of the model. To validate these controllers, a periodic model is developed for a simulated population based on three months of geolocation data from a kelp bass (Paralabrax clathratus), and AUV teams utilizing both controllers are simulated in tracking this population. Results show the viability of stochastic controls for multi-AUV tracking of populations whose behavior is well-approximated by the graph-based model. Preliminary trials with physical AUV systems indicate the plausibility of hardware implementation.