A Novel Approach to Coupling Terms to Avoid Obstacles in a Manipulator Movement Reproduction

다국어 초록 (Multilingual Abstract)

Many people have attempted to generate specific movements based on the concept that neural networks in the brain and spinal cord create multiple sets of temporal templates. Dynamic movement primitives (DMPs) are inspired by the motion control of biological systems and can be mathematically represented as stable nonlinear dynamic systems in the form of motion primitives. One way to improve the work efficiency of robots in various industries is to leverage the ability of DMPs to generalize learned trajectories to enable them to perform a wider range of tasks. This study discusses obstacle avoidance techniques using DMPs and proposes a novel approach to obstacle avoidance. DMPs have the ability to generalize and have extensions that make them valuable in generalizing in unforeseen situations. Obstacle avoidance in DMPs has been approached in various ways, with previous research utilizing potential field methods as typical obstacle avoidance techniques. We added a formulated coupling term to DMPs to avoid obstacles. This novel approach proposes modeling obstacles as point clouds, objects surrounded by bounding boxes or smooth standard shapes, and adding a new coupling term to smoothly avoid obstacles without disrupting the existing reference movement’s topology while closely following a reference trajectory. This study also discusses the determination of the magnitude and direction of a desired repelling force against obstacles. Overall, this study discusses obstacle avoidance techniques using DMPs and introduces a novel approach that improves obstacle avoidance in DMPs. The goal of this study is to confirm the effectiveness of the proposed approach by implementing previous and newly proposed algorithms for semi-elliptical trajectories and applying them to robot manipulators.

참고문헌 (Reference)

1 M. Aein, "Toward a library of manipulation actions based on semantic object-action relations" 4555-4562, 2013

2 A. Ude, "Taskspecific generalization of discrete and periodic dynamic movement primitives" 26 (26): 800-815, 2010

3 N. Uminy, "Strategic and interactive learning of a hierarchical set of tasks by the poppy humanoid robot" 204-209, 2017

4 F. Abu-Dakka, "Solving peg-in-hole tasks by human demonstration and exception strategies" 41 (41): 575-584, 2014

5 A. Pervez, "Novel learning from demonstration approach for repetitive teleoperation tasks" 60-65, 2017

6 D. H. Park, "Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields" 2008

7 D. H. Park, "Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields" IEEE 91-98, 2008

8 A. D. Dragan, "Movement primitives via optimization" 2339-2346, 2015

9 A. J. Ijspeert, "Movement imitation with nonlinear dynamical systems in humanoid robots" IEEE 2 : 1398-1403, 2002

10 Ude, "LocallyWeighted Regression (LWR)"

11 C. G. Atkeson, "Locally weighted learning" 11 : 11-73, 1997

12 X. Yin, "Learning nonlinear dynamical system for movement primitives" 3761-3766, 2014

13 P. Pastor, "Learning and generalization of motor skills by learning from demonstration" 763-768, 2009

14 P. Pastor, "Learning and generalization of motor skills by learning from demonstration" 763-768, 2009

15 R. Caccavale, "Imitation learning and attentional supervision of dual-arm structured tasks" 66-71, 2018

16 A. J. Ijspeert, "Dynamical movement primitives : Learning attractor models for motor behaviors" 25 (25): 328-373, 2013

17 M. Ginesi, "Dynamic movement primitives: Volumetric obstacle avoidance using dynamic potential functions" 101 : 2021

18 M. Saveriano, "Dynamic movement primitives in robotics : A tutorial survey"

19 M. Ginesi, "Dynamic movement primitives : Volumetric obstacle avoidance" 2019

20 G. Schöner, "Dynamic Thinking: A Primer on Dynamic Field Theory" Oxford University Press 2016

21 S. Schaal, "Dynamic Systems: Brain, Body, and Imitation" Cambridge University Press 177-214, 2006

22 A. Gams, "Coupling movement primitives : Interaction with the environment and bimanual tasks" 30 (30): 816-830, 2014

23 S. Schaal, "Constructive incremental learning from only local information" 10 (10): 2047-2084, 1998

24 S. Schaal, "Constructive incremental learning from only local information" 10 (10): 2047-2084, 1998

25 S. Schaal, "Constructive incremental learning from only local information" 10 (10): 2047-2084, 1998

26 E. Bizzi, "Computations underlying the execution of movement : A biological perspective" 253 (253): 287-291, 1991

27 H. Hoffmann, "Biologically-inspired dynamical systems for movement generation : Automatic real-time goal adaptation and obstacle avoidance" 2587-2592, 2009

28 H. Hoffmann, "Biologically inspired dynamical systems for movement generation : Automatic real-time goal adaptation and obstacle avoidance" 2587-2592, 2009

29 S. Schaal, "Adaptive Motion of Animals and Machines" Springer 261-280, 2006

30 S. Schaal, "Adaptive Motion of Animals and Machines" Springer 261-280, 2006

31 S. Calinon, "A tutorial on task-parameterized movement learning and retrieval" 9 (9): 1-29, 2016