Rodrigo Munguía

Monocular SLAM for Visual Odometry

The ego-motion online estimation process from a video input is often called visual odometry. Typically optical flow and structure from motion (SFM) techniques have been used for visual odometry. Monocular simultaneous localization and mapping (SLAM) techniques implicitly estimate camera ego-motion while incrementally build a map of the environment. However in monocular SLAM, when the number of features in the system state increases, the computational cost grows rapidly; consequently maintaining frame rate operation becomes impractical. In this paper monocular SLAM is proposed for map-based visual odometry. The number of features is bounded removing features dynamically from the system state, for maintaining a stable processing time. In the other hand if features are removed then previous visited sites can not be recognized, nevertheless in an odometry context this could not be a problem. A method for feature initialization and a simple method for recovery metric scale are proposed. The experimental results using real image sequences show that the scheme presented in this paper is promising.

Closing Loops With a Virtual Sensor Based on Monocular SLAM

Monocular simultaneous localization and mapping (SLAM) techniques implicitly estimate camera ego-motion while incrementally building a map of the environment. In monocular SLAM, when the number of features in the system state increases, maintaining a real-time operation becomes very difficult. However, it is easy to remove old features from the state to maintain a stable computational cost per frame. If features are removed from the map, then previously mapped areas cannot be recognized to minimize the robots drift; alternatively, in the context of a real-time virtual sensor that emulates typical sensors as laser for range measurements and encoders for dead reckoning, this limitation should not be a problem. In this paper, a novel framework is proposed to build in real time a consistent map of the environment using the virtual-sensor estimations. At the same time, the proposed approach allows minimizing the drift of the camera-robot position. Experiments with real data are presented to show the performance of this frame of work.

A practical method for implementing an attitude and heading reference system

This paper describes a practical and reliable algorithm for implementing an Attitude and Heading Reference System (AHRS). This kind of system is essential for real time vehicle navigation, guidance and control applications. When low cost sensors are used, efficient and robust algorithms are required for performance to be acceptable. The proposed method is based on an Extended Kalman Filter (EKF) in a direct configuration. In this case, the filter is explicitly derived from both the kinematic and error models. The selection of this kind of EKF configuration can help in ensuring a tight integration of the method for its use in filter-based localization and mapping systems in autonomous vehicles. Experiments with real data show that the proposed method is able to maintain an accurate and drift-free attitude and heading estimation. An additional result is to show that there is no ostensible reason for preferring that the filter have an indirect configuration over a direct configuration for implementing an AHRS system.

Attitude and Heading System based on EKF total state configuration

This paper describes the design, analysis, and experimental results of an Attitude and Heading System based on total state (direct) Extended Kalman Filtering technique. The presented scheme is suitable for implementation using low cost sensors. Attitude determination systems are essential for real time vehicle navigation, guidance and control applications. When low cost sensors are used, efficient and robust algorithms become necessary for an acceptable performance. For the proposed approach, a low cost Inertial Measurement Unit (IMU), formed by 3-axis gyroscope, 3-axis accelerometer, and 3-axis magnetometer, provides the input measurements. A Kalman Filter, in direct configuration, estimates the state of the system, which is formed by a quaternion, representing the body 3D orientation, and the biases of gyros. Experimental results with real data show that the proposed algorithm is able to maintain an accurate and drift-free attitude and heading estimation.

Monocular SLAM for autonomous robots with enhanced features initialization.

This work presents a variant approach to the monocular SLAM problem focused in exploiting the advantages of a human-robot interaction (HRI) framework. Based upon the delayed inverse-depth feature initialization SLAM (DI-D SLAM), a known monocular technique, several but crucial modifications are introduced taking advantage of data from a secondary monocular sensor, assuming that this second camera is worn by a human. The human explores an unknown environment with the robot, and when their fields of view coincide, the cameras are considered a pseudo-calibrated stereo rig to produce estimations for depth through parallax. These depth estimations are used to solve a related problem with DI-D monocular SLAM, namely, the requirement of a metric scale initialization through known artificial landmarks. The same process is used to improve the performance of the technique when introducing new landmarks into the map. The convenience of the approach taken to the stereo estimation, based on SURF features matching, is discussed. Experimental validation is provided through results from real data with results showing the improvements in terms of more features correctly initialized, with reduced uncertainty, thus reducing scale and orientation drift. Additional discussion in terms of how a real-time implementation could take advantage of this approach is provided.

A Robust Approach for a Filter-Based Monocular Simultaneous Localization and Mapping (SLAM) System

Simultaneous localization and mapping (SLAM) is an important problem to solve in robotics theory in order to build truly autonomous mobile robots. This work presents a novel method for implementing a SLAM system based on a single camera sensor. The SLAM with a single camera, or monocular SLAM, is probably one of the most complex SLAM variants. In this case, a single camera, which is freely moving through its environment, represents the sole sensor input to the system. The sensors have a large impact on the algorithm used for SLAM. Cameras are used more frequently, because they provide a lot of information and are well adapted for embedded systems: they are light, cheap and power-saving. Nevertheless, and unlike range sensors, which provide range and angular information, a camera is a projective sensor providing only angular measurements of image features. Therefore, depth information (range) cannot be obtained in a single step. In this case, special techniques for feature system-initialization are needed in order to enable the use of angular sensors (as cameras) in SLAM systems. The main contribution of this work is to present a novel and robust scheme for incorporating and measuring visual features in filtering-based monocular SLAM systems. The proposed method is based in a two-step technique, which is intended to exploit all the information available in angular measurements. Unlike previous schemes, the values of parameters used by the initialization technique are derived directly from the sensor characteristics, thus simplifying the tuning of the system. The experimental results show that the proposed method surpasses the performance of previous schemes.

Vision-Based SLAM System for Unmanned Aerial Vehicles.

The present paper describes a vision-based simultaneous localization and mapping system to be applied to Unmanned Aerial Vehicles (UAVs). The main contribution of this work is to propose a novel estimator relying on an Extended Kalman Filter. The estimator is designed in order to fuse the measurements obtained from: (i) an orientation sensor (AHRS); (ii) a position sensor (GPS); and (iii) a monocular camera. The estimated state consists of the full state of the vehicle: position and orientation and their first derivatives, as well as the location of the landmarks observed by the camera. The position sensor will be used only during the initialization period in order to recover the metric scale of the world. Afterwards, the estimated map of landmarks will be used to perform a fully vision-based navigation when the position sensor is not available. Experimental results obtained with simulations and real data show the benefits of the inclusion of camera measurements into the system. In this sense the estimation of the trajectory of the vehicle is considerably improved, compared with the estimates obtained using only the measurements from the position sensor, which are commonly low-rated and highly noisy.

Concurrent Initialization for Bearing-Only SLAM

Simultaneous Localization and Mapping (SLAM) is perhaps the most fundamental problem to solve in robotics in order to build truly autonomous mobile robots. The sensors have a large impact on the algorithm used for SLAM. Early SLAM approaches focused on the use of range sensors as sonar rings or lasers. However, cameras have become more and more used, because they yield a lot of information and are well adapted for embedded systems: they are light, cheap and power saving. Unlike range sensors which provide range and angular information, a camera is a projective sensor which measures the bearing of images features. Therefore depth information (range) cannot be obtained in a single step. This fact has propitiated the emergence of a new family of SLAM algorithms: the Bearing-Only SLAM methods, which mainly rely in especial techniques for features system-initialization in order to enable the use of bearing sensors (as cameras) in SLAM systems. In this work a novel and robust method, called Concurrent Initialization, is presented which is inspired by having the complementary advantages of the Undelayed and Delayed methods that represent the most common approaches for addressing the problem. The key is to use concurrently two kinds of feature representations for both undelayed and delayed stages of the estimation. The simulations results show that the proposed method surpasses the performance of previous schemes.

Validation of Data Association for Monocular SLAM

Simultaneous Mapping and Localization (SLAM) is a multidisciplinary problem with ramifications within several fields. One of the key aspects for its popularity and success is the data fusion produced by SLAM techniques, providing strong and robust sensory systems even with simple devices, such as webcams in Monocular SLAM. This work studies a novel batch validation algorithm, the highest order hypothesis compatibility test (HOHCT), against one of the most popular approaches, the JCCB. The HOHCT approach has been developed as a way to improve performance of the delayed inverse-depth initialization monocular SLAM, a previously developed monocular SLAM algorithm based on parallax estimation. Both HOHCT and JCCB are extensively tested and compared within a delayed inverse-depth initialization monocular SLAM framework, showing the strengths and costs of this proposal.

New validation algorithm for data association in SLAM

In this work, a novel data validation algorithm for a single-camera SLAM system is introduced. A 6-degree-of-freedom monocular SLAM method based on the delayed inverse-depth (DI-D) feature initialization is used as a benchmark. This SLAM methodology has been improved with the introduction of the proposed data association batch validation technique, the highest order hypothesis compatibility test, HOHCT. This new algorithm is based on the evaluation of statistically compatible hypotheses, and a search algorithm designed to exploit the characteristics of delayed inverse-depth technique. In order to show the capabilities of the proposed technique, experimental tests have been compared with classical methods. The results of the proposed technique outperformed the results of the classical approaches.