This paper presents a 6-DOF Pose Estimation (PE) method for a Robotic Navigation Aid (RNA) for the visually impaired. The RNA uses a single 3D camera for PE and object detection. The proposed method processes the camera’s intensity and range data to estimates the camera’s egomotion that is then used by an Extended Kalman Filter (EKF) as the motion model to track a set of visual features for PE. A RANSAC process is employed in the EKF to identify inliers from the visual feature correspondences between two image frames. Only the inliers are used to update the EKF’s state. The EKF integrates the egomotion into the camera’s pose in the world coordinate system. To retain the EKF’s consistency, the distance between the camera and the floor plane (extracted from the range data) is used by the EKF as the observation of the camera’s z coordinate. Experimental results demonstrate that the proposed method results in accurate pose estimates for positioning the RNA in indoor environments. Based on the PE method, a wayfinding system is developed for localization of the RNA in a home environment. The system uses the estimated pose and the floorplan to locate the RNA user in the home environment and announces the points of interest and navigational commands to the user through a speech interface. Note to Practitioners This work was motivated by the limitations of the existing navigation technology for the visually impaired. Most of the existing methods use a point/line measurement sensor for indoor object detection. Therefore, they lack capability in detecting 3D objects and positioning a blind traveler. Stereovision has been used in recent research. However, it cannot provide reliable depth data for object detection. Also, it tends to produce a lower localization accuracy because its depth measurement error quadratically increases with the true distance. This paper suggests a new approach for navigating a blind traveler. The method uses a single 3D time-of-flight camera for both 6-DOF PE and 3D object detection and thus results in a small-sized but powerful RNA. Due to the camera’s constant depth accuracy, the proposed egomotion estimation method results in a smaller error than that of existing methods. A new EKF method is proposed to integrate the egomotion into the RNA’s 6-DOF pose in the world coordinate system by tracking both visual and geometric features of the operating environment. The proposed method substantially reduces the pose error of a standard EKF method and thus supports a longer range navigation task. One limitation of the method is that it requires a feature-rich environment to work well.

Abstract-Planning under process and measurement uncertainties is a challenging problem. In its most general form it can be modeled as a Partially Observed Markov Decision Process (POMDP) problem. However POMDPs are generally difficult to solve when the underlying spaces are continuous, particularly when beliefs are non-Gaussian, and the difficulty is further exacerbated when there are also non-convex constraints on states. Existing algorithms to address such challenging POMDPs are expensive in terms of computation and memory. In this paper, we provide a feedback policy in non-Gaussian belief space via solving a convex program for common non-linear observation models. The solution involves a Receding Horizon Control strategy using particle filters for the non-Gaussian belief representation. We develop a way of capturing non-convex constraints in the state space and adapt the optimization to incorporate such constraints, as well. A key advantage of this method is that it does not introduce additional variables in the optimization problem and is therefore more scalable than existing constrained problems in belief space. We demonstrate the performance of the method on different scenarios.

In this paper, we present a 6-DOF pose estimation method for a Portable Navigation Aid for the visually impaired. The navigation aid uses a single 3D camera SwissRanger SR4000 for both pose estimation and object/obstacle detection. The SR4000 provides intensity and range data of the scene. These data are simultaneously processed to estimate the camera's egomotion, which is then used as the motion model by an Extended Kalman Filter (EKF) to track the visual features maintained in a local map. In order to create correct feature correspondences between images, a 3-point RANSAC (RANdom SAmple Consensus) process is devised to identify the inliers from the feature correspondences based on the SIFT (Scale Invariant Feature Transform) descriptors. Only the inliers are used to update the EKF's state. Additional inliers caused by the updated state are then located and used to perform another state update. The EKF integrates the egomotion into the camera's pose in the world coordinate with a relatively small error. Since the camera's y coordinate may be measured as the distance between the camera and the floor plane, it is used as an additional observation in this work. Experimental results indicate that the proposed pose estimation method results in accurate pose estimates for positioning the visually impaired in an indoor environment.

No abstract

Abstract-In this paper a new strategy for handling the observation information of a bearing-range sensor throughout the filtering process of EKF-SLAM is proposed. This new strategy is advised based on a thorough consistency analysis and aims to improve the process consistency while reducing the computational cost. At first, three different possible observation models are introduced for the EKF-SLAM solution for a robot equipped with a bearing-range sensor. General form of the covariance matrix and the level of inconsistency in the robot orientation estimate is then calculated for these variants, and based on the numerical comparison of the estimation results, it is proposed to use the bearing and range information of a feature in the initialization step of EKF-SLAM. However, it is recommended to use only the bearing information to perform other iteration steps. The simulation observations verify that the new strategy yields to more consistent estimates both for the robot and the features. Moreover, through the proposed consistency analysis, it is shown that since the source of consistency improvement is independent from the choice of the motion model, it gives us an advantage over other existing methods that assume a specific motion models for consistency improvement.