Many robotic and computer-vision applications, such as robot navigation, demand accurate, reliabl... more Many robotic and computer-vision applications, such as robot navigation, demand accurate, reliable, and real-time stereo matching algorithm. However, stereo images captured from real sceneries usually have much noises, bad contrast, photometric distortions, and lack of textures, heavily affecting the stereo algorithms' performance. This work proposes a new dissimilarity measure in HSL color space in order to substitute the established intensity-based ones. The proposed measure can be adopted by almost any of the existing stereo algorithms, enhancing it with its robust features. The performance of the dissimilarity measure is validated through experimentation with an edge map guided stereo matching algorithm, which is suitable for low texture stereo images. Experimental results for a variety of lighting conditions are gathered and compared to one of intensity-based algorithms. The proposed method outperforms the examined algorithm, exhibiting tolerance to illumination differentiations and lack of textures.
This paper presents a virtual-physics based control framework for swarm robotic chemical plume tr... more This paper presents a virtual-physics based control framework for swarm robotic chemical plume tracing and source localization problem. The control force includes three kinds of effort, which are lattice formation force, plume tracing force, and obstacle avoidant force. The plume tracing and source identify strategy are based on the chemical mass flux passing through the robot colony. Simulation results show that the proposed control framework and tracing strategy can effectively navigate the multi-robot system to the chemical source emitter region. The virtual-physics based framework is highly flexible, endows the robot formation the properties of self-organization and self-repair. The mass flux driven plume tracing can inhibit the robots from adhering to plume "trap" and guide the robots forward to the real source region.
A multiple odor sources search strategy based on a modified ant algorithm is proposed to enable t... more A multiple odor sources search strategy based on a modified ant algorithm is proposed to enable the multi-robot system to search for the odor sources that exist in the indoor environment by imitating the forage behavior of ant colony. The search strategy includes two parts, which are odor tracking strategy and odor sources localization strategy. The tracking strategy consists of a modified ant colony algorithm. The localization strategy is an odor source verification procedure introduced into the tracking process to localize multiple odor sources. Simulation results show that the proposed strategy can effectively enable the robot system to search and determine the odor sources quickly and accurately.
A multi-robot cooperation strategy based on a modified ant colony algorithm (ACA) is proposed. It... more A multi-robot cooperation strategy based on a modified ant colony algorithm (ACA) is proposed. It enables the multi-robot system to search for the odor sources, which exist in the indoor environment, by imitating the forage behavior of the ant society. The modification of ACA includes new definitions of pheromone and heuristic function. And two extra search modes, local traversal search and global random search are added to improve the search performance of the robot system. A verification procedure is introduced into the iteration process to localize multiple odor sources. Simulation results have showed that the modified algorithm can effectively enable the robots to approach and determine the odor sources quickly and accurately.
Uploads
Papers by Yuhua Zou