Map-aided localization in sparse global positioning system environments using vision and particle filtering.

Journal of Field Robotics (Impact Factor: 1.88). 09/2011; 28:619-643. DOI: 10.1002/rob.20395
Source: DBLP

ABSTRACT A map-aided localization approach using vision, inertial sensors when available, and a particle filter is proposed and empirically evaluated. The approach, termed PosteriorPose, uses a Bayesian particle filter to augment global positioning system (GPS) and inertial navigation solutions with vision-based measurements of nearby lanes and stop lines referenced against a known map of environmental features. These map-relative measurements are shown to improve the quality of the navigation solution when GPS is available, and they are shown to keep the navigation solution converged in extended GPS blackouts. Measurements are incorporated with careful hypothesis testing and error modeling to account for non-Gaussian and multimodal errors committed by GPS and vision-based detection algorithms. Using a set of data collected with Cornell's autonomous car, including a measure of truth via a high-precision differential corrections service, an experimental investigation of important design elements of the PosteriorPose estimator is conducted. The algorithm is shown to statistically outperform a tightly coupled GPS/inertial navigation solution both in full GPS coverage and in extended GPS blackouts. Statistical performance is also studied as a function of road type, filter likelihood models, bias models, and filter integrity tests. © 2011 Wiley Periodicals, Inc. © 2011 Wiley Periodicals, Inc.

  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a map generation algorithm for a precise roadway map designed for autonomous cars. The roadway map generation algorithm is composed of three steps, namely, data acquisition, data processing, and road modeling. In the data acquisition step, raw trajectory and motion data for map generation are acquired through exploration using a probe vehicle equipped with GPS and on-board sensors. The data processing step then processes the acquired trajectory and motion data into roadway geometry data. GPS trajectory data are unsuitable for direct roadway map use by autonomous cars due to signal interruptions and multipath; therefore, motion information from the on-board sensors is applied to refine the GPS trajectory data. A fixed-interval optimal smoothing theory is used for a refinement algorithm that can improve the accuracy, continuity, and reliability of road geometry data. Refined road geometry data are represented into the B-spline road model. A gradual correction algorithm is proposed to accurately represent road geometry with a reduced amount of control parameters. The developed map generation algorithm is verified and evaluated through experimental studies under various road geometry conditions. The results show that the generated roadway map is sufficiently accurate and reliable to utilize for autonomous driving.
    IEEE Transactions on Intelligent Transportation Systems 06/2014; 15(3):925-937. · 2.47 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The paper describes the design, implementation, and test of an autonomous vehicle navigation system using vehicle model and particle filter tracking algorithm. Typically, a vehicle navigation system comprises of real-time environment perception, vehicle localization, collision avoidance, path planning, and path following. In order to achieve the features for intelligent autonomous vehicle, a sensor suite of integrated inertial measurement unit (IMU), GNSS receiver, and incremental encoder is developed for vehicle position estimation. A map-aided path planning strategy is employed to generate a reference route. To this end, a UMI (User Machine Interface) is developed to facilitate the observation of a goal-oriented path tracking situation. The system utilizes particle filter algorithm to guide the vehicle following the planned path in terms of vehicle estimation control. The recursive particle filter is able to weight the cells and response the angle as well as estimated position information. All the sensors are integrated into an embedded computer platform and able to assess the autonomous driving capability. The test is conducted on campus by installing the sensor suite and embedded computer platform into an electricintegrated inertial measurement unit vehicle.
    2013 CACS International Automatic Control Conference (CACS); 12/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Future advanced driver assistant systems put high demands on the environmental perception especially in urban environments. Today's on-board sensors and on-board algorithms still do not reach a satisfying level of development from the point of view of robustness and availability. Thus, map data is often used as an additional data input to support the on-board sensor system and algorithms. The usage of map data requires a highly correct pose within the map even in cases of positioning errors by global navigation satellite systems or geometrical errors in the map data. In this paper we propose and compare two approaches for map-relative localization exclusively using a lane-level map. These approaches deliberately avoid the usage of detailed a priori maps containing point-landmarks, grids or road-markings. Additionally, we propose a grid-based on-board fusion of road-marking information and stationary obstacles addressing the problem of missing or incomplete road-markings in urban scenarios.
    Intelligent Vehicles Symposium 2014, Dearborn, Michigan; 06/2014