Novel Active-Vision-Based Motion Cues for Local Navigation
نویسندگان
چکیده
Observer Clearance v1 v2 v3 v3 v2 v1-v4-v5-v6-v4-v5-v6 t v7 v7 v7 v7 v1>v2>v3>0 v4>v5>v6>0 v7=0 Abstract In the absence of a-priori information about the environment, an autonomous mobile robot relies on sensory information to make local judgments about its surrounding. Generation of a local collision-free path based on sensory data plays an important role in the control of the robot's interaction with the environment. This paper presents a novel approach based on active-vision paradigm, for generating local collision-free paths for mobile robot navigation, in indoor as well as outdoor environments. Two measurable visual motion cues that provide, some measure for a relative change in range as well clearance between a 3D surface and a fixated observer in motion are described. These visual cues are independent of the 3D environment and need no a-priori knowledge about it. For each visual motion cue, there is a visual field surrounding the moving observer. In other words, there are imaginary 3D surfaces attached to the observer that move with it, each of which correspond to a value of the cue. These visual fields can be used to demarcate regions around a moving observer into safe and danger zones of varying degree, which is suitable for making local decisions about the steering as well as speed commands to the mobile robot. We describe a practical method to extract these cues from a sequence of images. This approach needs no feature tracking between images and almost no camera calibration.
منابع مشابه
A novel fuzzy multi-criteria decision-making methodology based upon the spherical fuzzy sets with a real case study
The choice of roll stabilization system is critical for many types of ships. For warships where operational activities are fast and the concept of time is very effective, determining the most appropriate of these systems is of particular importance. Some operations, such as the landing of the helicopter on board, are critical for naval ships. Unwanted rolling motion makes this difficult. In add...
متن کاملComplex interactions between spatial, orientation, and motion cues for biological motion perception across visual space.
Human observers are adept at perceiving complex actions in point-light biological motion displays that represent the human form with a sparse array of moving points. However, the neural computations supporting action perception remain unclear, particularly with regards to central versus peripheral vision. We created novel action stimuli comprised of Gabor patches to examine the contributions of...
متن کاملApplication of Combined Local Object Based Features and Cluster Fusion for the Behaviors Recognition and Detection of Abnormal Behaviors
In this paper, we propose a novel framework for behaviors recognition and detection of certain types of abnormal behaviors, capable of achieving high detection rates on a variety of real-life scenes. The new proposed approach here is a combination of the location based methods and the object based ones. First, a novel approach is formulated to use optical flow and binary motion video as the loc...
متن کاملContribution of configural information in a direction discrimination task: Evidence using a novel masking paradigm
Understanding how structure and motion information contribute to the perception of biological motion is often studied with masking techniques. Current techniques in masking point-light walkers typically rely on adding surrounding masking dots or altering phase relations between joints. Here, we demonstrate the use of novel stimuli that make it possible to determine the noise level at which the ...
متن کاملMotion Segmentation based on On-line Non-parametric Learning using RGB-D Data
Motion segmentation is a fundamental technology in many robotic applications, such as mapping and navigation in dynamic environments. In this study, we propose a novel motion segmentation approach based on on-line non-parametric learning using RGB-D data. The proposed approach requires no prior information, such as hand-labelled initial segmentation. Foreground cues are derived from dense optic...
متن کامل