بحث بعنوان Safe and Smooth – Mobile Agent Trajectory Smoothing by SVM

بحث بعنوان
Safe and Smooth – Mobile Agent Trajectory Smoothing by SVM
Chan-Yun Yang1, Jr-Syu Yang2 and Feng-Li Lian3
1Department of Mechanical Engineering
Technology and Science Institute of Northern Taiwan
No. 2, Xue-Yuan Rd., Beitou, Taipei 11202, Taiwan
[email protected]
2Department of Mechanical and Electro-Mechanical Engineering
Tamkang University
No. 151, Yingzhuan Rd., Tamsui Dist., New Taipei City 25137, Taiwan
[email protected]
3Department of Electrical Engineering
National Taiwan University
No. 1, Sec. 4, Roosevelt Rd., Taipei 10617, Taiwan
[email protected]
Received April 2011; revised October 2011
Abstract. The paper presents a model merging Voronoi tessellation with an underlying support vector machine (SVM) in order to develop path planning for guiding an autonomous vehicle safely and smoothly through a space with obstacles. Being a roadmap
method for path generation, the Voronoi tessellation is employed as a preprocessor to
roughly fit a connection between the initial and goal configurations. Though the Voronoi
path is safe for obstacle avoidance, its disjoint linear edges are unsatisfactory when
smoothness is requested. Hence, an SVM postprocessor is proposed to make the segmented path smoother. By analogue to the Gaussian potential field, a zero-potential
curve in the configuration space is thus obtained by the SVM postprocessor and forms a
safe and smooth path. Due to advantages of the SVM with RBF kernel, the post-processed
path has the merits of both smoothness from the Gaussian kernel basis, and wide clearance from the large-margin decision boundary. This paper adopts point configurations to
represent obstacles in the working space. With additional artificial points for auxiliary
constraints, the two-stage path planner is then developed. Detailed property investigations and simulated applications are also included to characterize the path planner. The
results of a practical demonstration show a promising future for further applications.
Keywords: Path planning, Safe, Smooth, Large margin, Support vector machines
Conclusions
An SVM trajectory smoother has been successfully developed to provide a safe and smooth path for a mobile agent. With the most crucial property of induced
smooth and wide clearance, the path planner is uniquely qualified for this purpose. The
demonstrated two-stage model, merging SVM and Voronoi tessellation, realizes the planner as an admissible model to achieve the goal of this paper. Instead of the Voronoi
preprocessor, it is noteworthy that the proposed SVM smoother may potentially be extended more generally to be combined with a preprocessor, which can provide a similar
rough reference for partitioning and labeling the prototypes.

كلمة سر فك الضغط : books-world.net
The Unzip Password : books-world.net