header photo

SurfMan: Generating Smooth End-Effector Trajectories on 3D Object Surfaces for Human-Demonstrated Pattern Sequence

[paper at RA-L IEEE, PDF, Video, Source codes, Trial data, Planners comparison, Visual examples, ]

Authors

R.Skoviera(1*), J.K.Behrens(1*), K.Stepanova(1)

(1)Czech Technical University in Prague, Czech Institute of Informatics, Robotics, and Cybernetics, jan.kristof.behrens@cvut.cz,karla.stepanova@cvut.cz, (*) Both authors contributed the same

Abstract

Specifying robot tasks for low-volume manufacturing scenarios is an open problem. The state-of-the-art robotic systems enable the application of smooth 2D paths to a 3D surface but assume that the product engineer provides these paths. We extend this approach with a novel tool-path specification method, which produces smooth paths from noisy demonstrations. The user demonstrates only short patterns and selects a base path relative to an object in front of the robot, along which these patterns should be applied. The representation based on polynomials allows controlling the grade of the smoothness of the resulting tool path. We generate parametrized robot trajectories to meet the use-case-specific constraints and adhere to the robot’s kinodynamic limits. We propose a set of measures to evaluate the quality of the generated curves and corresponding trajectories with respect to executability by a robot. The evaluation in simulation and real-robot experiments showed that the robot could reach up to 15.9% higher constant speed on tool paths generated by our system compared to unprocessed paths.

Attachment video

Video showing the usage of the proposed system.

Here is a link to the video.

Additional resources

Paper at RA-L IEEE: link

Citation:
R. Skoviera, J. K. Behrens and K. Stepanova, "SurfMan: Generating Smooth End-Effector Trajectories on 3D Object Surfaces for Human-Demonstrated Pattern Sequence," in IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 9183-9190, Oct. 2022, doi: 10.1109/LRA.2022.3189178.

@ARTICLE{Surfman2022, author={Skoviera, Radoslav and Behrens, Jan Kristof and Stepanova, Karla},
journal={IEEE Robotics and Automation Letters},
title={SurfMan: Generating Smooth End-Effector Trajectories on 3D Object Surfaces for Human-Demonstrated Pattern Sequence},
year={2022},
volume={7},
number={4},
pages={9183-9190},
doi={10.1109/LRA.2022.3189178}}

Submitted manuscript [PDF]

Source code https://github.com/imitrob/surftask

Trial data Download bag file with trial data from GDrive [502 MB]

Comparison of execution using different planners.

Plot of the trajectory from the Descartes planner (10 repetititons of knots applied to a circle): Descartes trajectory
Plot of the trajectory from the Cartesian planner (10 repetititons of knots applied to a circle): Cartesian planner trajectory

Video showing the trajectory execution by Descartes planner.

Video showing the trajectory execution by Cartesian planner.

Examples of setting parameters for contour detection.

Video showing the contour detection process (video shows well in Chrome, not in Firefox).

Video showing the contour detection process.

Examples of various patterns applied to 3D surfaces.

(the black lines coming from the points depict the tool orientation vector) Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory (the black lines coming from the points depict the tool orientation vector)

Examples of various patterns applied to different curves - simulation.

Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory Cartesian planner trajectory