DocumentCode :
2412577
Title :
Improved non-linear spline fitting for teaching trajectories to mobile robots
Author :
Sprunk, Christoph ; Lau, Boris ; Burgard, Wolfram
Author_Institution :
Comput. Sci. Dept., Univ. of Freiburg, Freiburg, Germany
fYear :
2012
fDate :
14-18 May 2012
Firstpage :
2068
Lastpage :
2073
Abstract :
In this paper, we present improved spline fitting techniques with the application of trajectory teaching for mobile robots. Given a recorded reference trajectory, we apply non-linear least-squares optimization to accurately approximate the trajectory using a parametric spline. The fitting process is carried out without fixed correspondences between data points and points along the spline, which improves the fit especially in sharp curves. By using a specific path model, our approach requires substantially fewer free parameters than standard approaches to achieve similar residual errors. Thus, the generated paths are ideal for subsequent optimization to reduce the time of travel or for the combination with autonomous planning to evade obstacles blocking the path. Our experiments on real-world data demonstrate the advantages of our method in comparison with standard approaches.
Keywords :
collision avoidance; intelligent robots; least squares approximations; mobile robots; optimisation; splines (mathematics); teaching; trajectory control; autonomous planning; data points; free parameters; linear least-squares optimization; mobile robots; nonlinear spline fitting process; parametric spline; path blocking obstacles; path generation; real-world data; reference trajectory; residual errors; sharp curves; specific path model; subsequent optimization; trajectory approximation; trajectory teaching; Computational modeling; Hidden Markov models; Interpolation; Optimization; Splines (mathematics); Trajectory; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2012 IEEE International Conference on
Conference_Location :
Saint Paul, MN
ISSN :
1050-4729
Print_ISBN :
978-1-4673-1403-9
Electronic_ISBN :
1050-4729
Type :
conf
DOI :
10.1109/ICRA.2012.6224920
Filename :
6224920
Link To Document :
بازگشت