Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain
arXiv:1904.02215 · doi:10.1109/IROS40897.2019
Abstract
A plethora of state estimation techniques have appeared in the last decade using visual data, and more recently with added inertial data. Datasets typically used for evaluation include indoor and urban environments, where supporting videos have shown impressive performance. However, such techniques have not been fully evaluated in challenging conditions, such as the marine domain. In this paper, we compare ten recent open-source packages to provide insights on their performance and guidelines on addressing current challenges. Specifically, we selected direct methods and tightly-coupled optimization techniques that fuse camera and Inertial Measurement Unit (IMU) data together. Experiments are conducted by testing all packages on datasets collected over the years with underwater robots in our laboratory. All the datasets are made available online.
References in corpus (3)
Cited by in corpus (46)
- A Survey of Robot Manipulation in Contact
- From the Desks of ROS Maintainers: A Survey of Modern & Capable Mobile Robotics Algorithms in the Robot Operating System 2
- Semantic-Aware Scene Recognition
- Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations
- A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challenges
- Multi-UAV trajectory planning for 3D visual inspection of complex structures
- Autonomous Aerial Delivery Vehicles, a Survey of Techniques on how Aerial Package Delivery is Achieved
- HEAP -- The autonomous walking excavator
- Active Learning in Robotics: A Review of Control Principles
- Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
- Advances in UAV Avionics Systems Architecture, Classification and Integration: A Comprehensive Review and Future Perspectives
- Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
- Time-dependent inertia of self-propelled particles: the Langevin rocket
- MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation
- Simulation study on the fleet performance of shared autonomous bicycles
- A Survey on Physics Informed Reinforcement Learning: Review and Open Problems
- LiDAR-Based Place Recognition For Autonomous Driving: A Survey
- MKConv: Multidimensional Feature Representation for Point Cloud Analysis
- Immersive Human-Machine Teleoperation Framework for Precision Agriculture: Integrating UAV-based Digital Mapping and Virtual Reality Control
- Constructing Parsimonious Analytic Models for Dynamic Systems via Symbolic Regression
- Verified Synthesis of Optimal Safety Controllers for Human-Robot Collaboration
- Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts
- A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots
- Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot
- Search-Based Task and Motion Planning for Hybrid Systems: Agile Autonomous Vehicles
- A Q-learning approach to the continuous control problem of robot inverted pendulum balancing
- Geometric Impedance Control on SE(3) for Robotic Manipulators
- Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey
- Safe Learning-based Gradient-free Model Predictive Control Based on Cross-entropy Method
- UAV-based path planning for efficient localization of non-uniformly distributed weeds using prior knowledge: A reinforcement-learning approach
- Safe-visor Architecture for Sandboxing (AI-based) Unverified Controllers in Stochastic Cyber-Physical Systems
- Joint Scene and Object Tracking for Cost-Effective Augmented Reality Assisted Patient Positioning in Radiation Therapy
- On-Demand Scenario Generation for Testing Automated Driving Systems
- rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks
- Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications
- 3DRM:Pair-wise relation module for 3D object detection
- Solgenia -- A Test Vessel Toward Energy-Efficient Autonomous Water Taxi Applications
- Adaptive Control of Euler-Lagrange Systems under Time-varying State Constraints without a Priori Bounded Uncertainty
- Neural Policy Style Transfer
- Lightweight Decentralized Neural Network-Based Strategies for Multi-Robot Patrolling
- Towards Developing Socially Compliant Automated Vehicles: Advances, Expert Insights, and A Conceptual Framework
- CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning
- Addressing the challenges of loop detection in agricultural environments
- An Active Learning Framework for Efficient Robust Policy Search
- Stackelberg Meta-Learning Based Control for Guided Cooperative LQG Systems
- Variational interacting particle systems and Vlasov equations