Adaptive movement sequences and predictive decisions based on hierarchical dynamical systems

This paper addresses the question of how to create adaptive and smooth sequences of actions and how to decide among skill options in a continuous manner without the necessity of recurrent planning. Motion generation is based on serial and parallel blending of movement primitives (MP). MPs are modeled as dynamical systems on task coordinates with attractor behavior and augmented with additional signals to ease their coordination. Sequences and transitions between skills are realized in a unified way as bifurcating dynamical systems based on continuous-time recurrent neural networks. The neural output is used as activation signal for MPs. Besides continuous feedback from the controlled MPs, the neural dynamics is influenced by a cost term from a future prediction to allow the inhibition of an action flow that is expected to fail. First results are shown in a physical simulation environment on a high-DoF robotic hand-arm system. The system is capable of creating smooth transients of MPs. Robustness to disturbances can be observed as local adaptations of individual low-level MPs, flexible sequencing of MPs, and global error recovery by changing the whole strategy of how to perform a movement skill.

[1]  Dmitry Berenson,et al.  A robot path planning framework that learns from experience , 2012, 2012 IEEE International Conference on Robotics and Automation.

[2]  Michael Gienger,et al.  Movement control in biologically plausible frames of reference , 2010, ISR/ROBOTIK.

[3]  Dana Kulic,et al.  Towards Lifelong Learning and Organization of Whole Body Motion Patterns , 2010, ISRR.

[4]  Werner von Seelen,et al.  Complex behavior by means of dynamical systems for an anthropomorphic robot , 1999, Neural Networks.

[5]  Jun Tani,et al.  Learning to generate articulated behavior through the bottom-up and the top-down interaction processes , 2003, Neural Networks.

[6]  T. Christaller,et al.  Dual dynamics: Designing behavior systems for autonomous robots , 1998, Artificial Life and Robotics.

[7]  G. Schöner,et al.  Dynamic Field Theory of Movement Preparation , 2022 .

[8]  Estela Bicho,et al.  Neuro-cognitive mechanisms of decision making in joint action: a human-robot interaction study. , 2011, Human movement science.

[9]  M. Spong,et al.  Robot Modeling and Control , 2005 .

[10]  M. Graziano.  The organization of behavioral repertoire in motor cortex. , 2006, Annual review of neuroscience.

[11]  S. Monsell.  Task switching , 2003, Trends in Cognitive Sciences.

[12]  Daniel Bullock,et al.  Learning and production of movement sequences: behavioral, neurophysiological, and modeling perspectives. , 2004, Human movement science.

[13]  Gregor Schöner,et al.  Dynamics of behavior: Theory and applications for autonomous robot architectures , 1995, Robotics Auton. Syst..

[14]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[15]  Aude Billard,et al.  Imitation learning of globally stable non-linear point-to-point robot motions using nonlinear programming , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Gregor Schöner,et al.  Serial order in an acting system: A multidimensional dynamic neural fields implementation , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[17]  Tamar Flash,et al.  Motor primitives in vertebrates and invertebrates , 2005, Current Opinion in Neurobiology.

[18]  A. Steinhage,et al.  The dynamic approach to autonomous robot navigation , 1997, ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics.

[19]  Jochen J. Steil,et al.  Reaching movement generation with a recurrent neural network based on learning inverse kinematics for the humanoid robot iCub , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[20]  S. Amari.  Dynamics of pattern formation in lateral-inhibition type neural fields , 1977, Biological Cybernetics.

[21]  Maxim Likhachev,et al.  Planning with adaptive dimensionality for mobile manipulation , 2012, 2012 IEEE International Conference on Robotics and Automation.

[22]  Jochen J. Steil,et al.  Interactive imitation learning of object movement skills , 2011, Autonomous Robots.

[23]  E. Bizzi,et al.  Book Review: Modular Organization of Spinal Motor Systems , 2002, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[24]  S. Schaal.  Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .