Autonomous Land Vehicle Research Articles

A high integrity IMU/GPS navigation loop for autonomous land vehicle applications

This paper describes the development and implementation of a high integrity navigation system, based on the combined use of the Global Positioning System (GPS) and an inertial measurement unit (IMU), for autonomous land vehicle applications. The paper focuses on the issue of achieving the integrity required of the navigation loop for use in autonomous systems. The paper highlights the detection of possible faults both before and during the fusion process in order to enhance the integrity of the navigation loop. The implementation of this fault detection methodology considers both low frequency faults in the IMU caused by bias in the sensor readings and the misalignment of the unit, and high frequency faults from the GPS receiver caused by multipath errors. The implementation, based on a low-cost, strapdown IMU, aided by either standard or carrier phase GPS technologies, is described. Results of the fusion process are presented.

Smooth vision-based autonomous land vehicle navigation in indoor environments by person following using sequential pattern recognition

A new approach to autonomous land vehicle ALV navigation by the person follow- ing is proposed. This approach is based on sequential pattern recognition and com- puter vision techniques, and maintenance of smoothness for indoor navigation is the main goal. The ALV is guided automatically to follow a person who walks in front of the vehicle. The vehicle can be used as an autonomous handcart, go-cart, buffet car, golf cart, weeder, etc. in various applications. Sequential pattern recognition is used to design a classifier for making decisions about whether the person in front of the vehicle is walking straight or is too right or too left of the vehicle. Multiple images in a sequence are used as input to the system. Computer vision techniques are used to detect and locate the person in front of the vehicle. By sequential pattern recognition, the relation between the location of the person and that of the vehicle is categorized into three classes. Corresponding adjustments of the direction of the vehicle are computed to achieve smooth navigation. The approach is implemented on a real ALV, and successful and smooth navigation sessions confirm the feasibility of the approach.

Decentralized Architecture for Asynchronous Sensors

This paper presents an efficient method of multi-sensor estimation that can be used with asynchronous and synchronous sensors. A decentralized architecture is used for the fusion of information obtained from several asynchronous measurements. The issue of the synchronization of the information, which is critical in the proposed method, is addressed. The information form of the Kalman filter (information filter) is used as the main algorithm for estimation. The method is demonstrated with the implementation of a navigation system for an autonomous land vehicle. The integrity issue is also addressed with the implementation of multiple independent estimation loops. The proposed method allows for efficient fusion of information obtained from different measurements for covariance reduction, while providing the benefits of decentralized estimation architecture for integrity purposes. The resulting estimates are equivalent to an optimal centralized filter when the loops incorporate all the information available in the system. The information obtained from each measurement is then broadcast to the other loops after being synchronized. This information is used in an assimilation stage to achieve more accurate estimates. The assimilation frequency is also discussed considering the trade off of fault detectability and estimation covariance reduction. The performance of the navigation method is examined by comparing the resulting position estimates to those of independent navigation loops.

Recent trends in control architectures for autonomous underwater vehicles

This article describes therecenttrends in controlarchitectures for autonomous vehicles. The study has been carried out on 22 architectures, most of which relate to the field of underwater robotics. The main aim of this article is to show the relationships between these various architectures and to show how developments in architectures for autonomous land vehicles have been extended for use in autonomous underwater vehicles. A summary of important features of the 22 architectures is presented and a new hybrid architecture is proposed for the underwater vehicle GARBI.

Straight-line motion control for autonomous land vehicles using 2D image processing techniques

In this article, we develop a novel approach to detecting the movement changes of an autonomous land vehicle. Movement changes are of two pan values, namely, the pan angle and the pan distance between the vehicle and the navigation line. Both of these two values have to be taken into account while making movement calibration. The approach is comprised of a learning phase and an operation phase. In the former phase, a navigation map is generated by taking four images based on the preset maximum and minimum tolerant pan angles of the vehicle, while it is located on the preset maximum and minimum tolerant pan distances on the side parallel to the navigation line. In the latter phase, images are taken in regular time intervals while the vehicle follows the navigation line, and the two pan values are calculated through interpolation based on the navigation map. To increase the performance of the proposed system, two refinement approaches are also presented. Experimental results are given to reveal the superiority of the proposed approach. © 1998 John Wiley & Sons, Inc.

An incremental-learning-by-navigation approach to vision-based autonomous land vehicle guidance in indoor environments using vertical line information and multiweighted generalized Hough transform technique

An incremental learning by navigation approach to vision based autonomous land vehicle (ALV) guidance in indoor environments is proposed. The approach consists of three stages: initial learning, navigation, and model updating. In the initial learning stage, the ALV is driven manually, and environment images and other status data are recorded automatically. Then, an offline procedure is performed to build an initial environment model. In the navigation stage, the ALV moves along the learned environment automatically, locates itself by model matching, and records necessary information for model updating. In the model updating stage, an offline procedure is performed to refine the learned model. A more precise model is obtained after each navigation-and-update iteration. Used environment features are vertical straight lines in camera views. A multiweighted generalized Hough transform is proposed for model matching. A real ALV was used as the testbed, and successful navigation experiments show the feasibility of the proposed approach.

Vision-based autonomous land vehicle guidance in outdoor road environments using combined line and road following techniques

An intelligent approach to autonomous land vehicle (ALV) guidance in outdoor road environments using combined line and road following and color information clustering techniques is proposed. Path lines and road boundaries are selected as reference models, called the line-model and the road-model, respectively. They are used to perform line-model matching (LMM) and road-model matching (RMM) to locate the ALV for line and road following, respectively. If there are path lines in the road, the LMM process is used to locate the ALV because it is faster than the RMM process. On the other hand, if no line can be found in the road, the RMM process is used. To detect path lines in a road image, the Hough transform is employed, which does not take much computing time because bright pixels in the road are very few. Various color information on roads is used for extracting path lines and road surfaces. And the ISODATA clustering algorithm based on an initial-center-choosing technique is employed to solve the problem caused by great changes of intensity in navigations. The double model matching procedure combined with the color information clustering process enables the ALV to navigate smoothly in roads even if there are shadows, cars, people, or degraded regions on roadsides. Some intelligent methods to speed up the model matching processes and the Hough transform based on the feedback of the previous image information are also presented. Successful navigations show that the proposed approach is effective for ALV guidance in common roads. ©1997 John Wiley & Sons, Inc.

Vision‐based autonomous land vehicle guidance in outdoor road environments using combined line and road following techniques

Vision‐based autonomous land vehicle guidance in outdoor road environments using combined line and road following techniques

Analysis of terrain using multispectral images

Automated terrain analysis is required for many practical applications, such as outdoor navigation, image exploitation, remote sensing, reconnaissance and surveillance. In this paper, we present a hierarchical approach to analyze multispectral (MS) imagery for autonomous land vehicle navigation. The approach integrates several strategies to label various terrain classes in these images acquired using twelve spectral bands in the visible and near-infrared spectrum. At the low (pixel) level, it combines texture gradient results from specifically selected channels by varying the size of gradient operators and performing multithresholding and relaxation-based edge linking operations to obtain robust closed region boundaries. At the high (symbolic) level, it makes use of the spectral, locational, and relational constraints among regions to achieve accurate terrain image interpretation. Details of the technique with examples from real imagery collected by an autonomous land vehicle (ALV) are presented.

Estimation of vehicle position based on projective function using the sequence of a 2D image

The paper proposes a method to estimate the position of an autonomous land vehicle based on the projective function. Usually, there is the fact that obtaining the yaw angle as the motion parameters of the vehicle leads to estimating the lateral variation obtained from the information of a 2D image. From this, an effective method to estimate the lateral variation is shown. In the estimation processing, a projective function from a 2D image into 1D data is considered, and a cross-correlation function for the 1D data, play important roles to reduce the computational effort and the noise effect on a 2D image. Setting up the method in the test vehicle, the experimental result in the case that the vehicle moves in a real passageway is shown.

Evolution of an artificial neural network based autonomous land vehicle controller

This paper presents an evolutionary method for creating an artificial neural network based autonomous land vehicle controller. The evolved controllers perform better in unseen situations than those trained with an error backpropagation learning algorithm designed for this task. In this paper, an overview of the previous connectionist based approaches to this task is given, and the evolutionary algorithms used in this study are described in detail. Methods for reducing the high computational costs of training artificial neural networks with evolutionary algorithms are explored. Error metrics specific to the task of autonomous vehicle control are introduced; the evolutionary algorithms guided by these error metrics reveal improved performance over those guided by the standard sum-squared error metric. Finally, techniques for integrating evolutionary search and error backpropagation are presented. The evolved networks are designed to control Carnegie Mellon University's NAVLAB vehicles in road following tasks.

Mission Planning for an Autonomous Land Vehicle in an Uncertain Environment

An approach to mission planning for an autonomous land vehicle (ALV) on a road network is presented, taking into account the risk for the existence of road sections with obstacles. A structured topological model of the environment described as a graph is used. An algorithm for expansion of the describing graph is proposed, considering the arbitrary (outside the road network) location of the start and goal positions of the ALV. An algorithm of minimum cost path searching in an uncertain environment and an approach to mission completion with path preplanning are presented.

Range sensor based outdoor vehicle Navigation, collision avoidance and parallel parking

Detecting unexpected obstacles and avoiding collisions is an important task for any autonomous mobile system. This article describes GANESHA (Grid based Approach for Navigation by Evidence Storage and Histogram Analysis), a system using sonar that we implemented for the autonomous land vehicle Navlab. The general hardware configuration of the system is shown, followed by a description of how the system builds a local grid map of its environment. The information collected in the map can then be used for a variety of applications in vehicle navigation like collision avoidance, feature tracking and parking. An algorithm was implemented that can track a static feature such as a rail, wall or an array of parked cars and use this information to drive the vehicle. Methods for filtering the raw data and generating the steering commands are discussed and the implementation for collision avoidance, parallel parking and its integration with other vehicle systems is described.

Book reivew: Qualitative Motion Understanding by Wilhelm Burger and Bit Bhanu (Kluwer Academic Publishers 1992)

This book is a summary of a research project sponsored by the Advanced Research Projects Agency (ARPA) in service of one of its great challenges: creating an autonomous land vehicle (ALV). This book reports on the computer vision problems associated with having an ALV interpret the scene as it moves through its environment. The main problems addressed by this work are to separate the moving objects from the stationary objects in the scene (as the ALV moves) and to detect how the moving objects are moving with respect to the ALV.

CAD-MAP and estimation of ALV positions in mountainous areas

SUMMARYPosition estimation is a key issue for an ALV Autonomous Land Vehicle) in navigating a mountainous area. The unevenness of the terrain makes mechanical velocity sensors inaccurate (due to wheel slippage), and the lack of appropriate landmarks complicates the problem. In this paper, we present a solution method using features of the skyline. The skyline from the vision system is assumed given, and compared with a computer map, called the CAD-MAP. The algorithm is composed of: a) Identification of the peak points in the camera skyline, b) Computing the ALV position for the identified peak points, and c) Searching for the corresponding peak point in the CAD-MAP. Heuristics for computational efficiency and solution accuracy are also included in the algorithm. To test the validity and effectiveness of the algorithm, numerous simulations were performed and analyzed.

Autonomous road vehicle navigation

This paper describes a new modular hardware design for an autonomous land vehicle, together with techniques for navigation and obstacle avoidance. A “bootstrap” algorithm is described which aligns the vehicle from an arbitrary starting point using the road's vanishing point. An algorithm to perform navigation along a structured road is then described. This is achieved by modelling the white lane-boundary marking using six parameters which are updated iteratively from frame to frame using a non-linear least-squares techniques. The obstacle-detection method is based on frame differencing. Using data from the vehicle odometry sensors, a motion-corrected version of the difference between frames is produced, in which objects projecting up from the ground plane are easily identified.

Fuzzy and temporal representation for task-level mission management of IAVs using object orientation

Task-level mission management forms an integral part of the command and control system for truly intelligent autonomous vehicles (IAVs). It is responsible for the overall coordination of robot subsystem activities, directing them to achieve some set of mission goals. The task-level mission management processes for an autonomous land vehicle have been implemented in C++ taking advantage of object-oriented techniques. The representations and structure of the software are described, and the temporal and fuzzy extensions to the implemented classical planning component are discussed.

Application of heuristic control technique to path planning of an autonomous guided vehicle

Abstract Industrial robots, such as autonomous mobile robots (AMR), autonomous guided vehicles (AGV), and autonomous land vehicles (ALV) are essential in unmanned automatic factories, the final objective of factory automation. They are still at an early stage of development and their application fields are also very limited. Previous industrial robots have seldom had autonomous moving functions, but they will play an important role for future factory automation. This paper proposes an autonomous moving system having a heuristic control technique similar to human thought, using the path planning algorithm, and describes a simulation to verify the function.

Autonomous land vehicle guidance for navigation in buildings by computer vision, radio, and photoelectric sensing techniques

Abstract An integrated approach to vision‐based autonomous land vehicle (ALV) guidance for automatic navigation and collision avoidance in building corridors and elevators is proposed. Computer vision techniques are utilized to locate an ALV in building corridors and to control it to enter elevators by the use of multiple corner points on walls. The location principle is based on matching input corner position information with a model using a distance‐weighted correlation function. Furthermore, radio equipment is employed to control the elevator operations of lifting up, lifting down, door closing, and door opening so that the ALV can enter elevators automatically. Finally, a photoelectric sensor‐based obstacle avoidance system for the ALV is developed. A real ALV was constructed as a testbed. Many successful navigation experiments confirm the effectiveness of the proposed approach.

Obstacle Detection Using a Motion-Corrected Plan-View Transformation

This paper describes an obstacle detection method for a vision-based autonomous land vehicle (ALV) based on frame differencing. The simple frame-differencing approach has several drawbacks. and an improved method is presented, in wich the difference is taken of perspective projections of the scene. Since the ALV's motion is measured directly using sensors, a motion-corrected version of this difference can be produced. Parallax due to motion is then used to identify objects which project up from the ground plane. This process can be performed at near frame rate