Learning Task-Specific Dynamics to Improve Whole-Body Control

In task-based inverse dynamics control, reference accelerations used to follow a desired plan can be broken down into feedforward and feedback trajectories. The feedback term accounts for tracking errors that are caused from inaccurate dynamic models or external disturbances. On underactuated, free-floating robots, such as humanoids, good tracking accuracy often necessitates high feedback gains, which leads to undesirable stiff behaviors. The magnitude of these gains is anyways often strongly limited by the control bandwidth. In this paper, we show how to reduce the required contribution of the feedback controller by incorporating learned task-space reference accelerations. Thus, we i) improve the execution of the given specific task, and ii) offer the means to reduce feedback gains, providing for greater compliance of the system. In contrast to learning task-specific joint-torques, which might produce a similar effect but can lead to poor generalization, our approach directly learns the task-space dynamics of the center of mass of a humanoid robot. Simulated and real-world results on the lower part of the Sarcos Hermes humanoid robot demonstrate the applicability of the approach.

[1]  Alexander Herzog,et al.  Trajectory generation for multi-contact momentum control , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[2]  David W. Franklin,et al.  Computational Mechanisms of Sensorimotor Control , 2011, Neuron.

[3]  Peter B. Goldsmith On the equivalence of causal LTI iterative learning control and feedback control , 2002, Autom..

[4]  Christopher G. Atkeson,et al.  Dynamic Balance Force Control for compliant humanoid robots , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Olivier Stasse,et al.  Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Andrej Gams,et al.  Learning Compliant Movement Primitives Through Demonstration and Statistical Generalization , 2016, IEEE/ASME Transactions on Mechatronics.

[7]  Christopher G. Atkeson,et al.  Adapting human motion for the control of a humanoid robot , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[8]  Carl E. Rasmussen,et al.  PILCO: A Model-Based and Data-Efficient Approach to Policy Search , 2011, ICML.

[9]  Christopher G. Atkeson,et al.  Human‐in‐the‐loop Control of a Humanoid Robot for Disaster Response: A Report from the DARPA Robotics Challenge Trials , 2015, J. Field Robotics.

[10]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[11]  A.G. Alleyne,et al.  A survey of iterative learning control , 2006, IEEE Control Systems.

[12]  Alexander Herzog,et al.  Momentum control with hierarchical inverse dynamics on a torque-controlled humanoid , 2014, Autonomous Robots.

[13]  Stefan Schaal,et al.  Towards Associative Skill Memories , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

[14]  Stefan Schaal,et al.  Inertial parameter estimation of floating base humanoid systems using partial force sensing , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[15]  Andrej Gams,et al.  Coupling Movement Primitives: Interaction With the Environment and Bimanual Tasks , 2014, IEEE Transactions on Robotics.

[16]  Alberto Montebelli,et al.  Simultaneous kinesthetic teaching of positional and force requirements for sequential in-contact tasks , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[17]  Jan Peters,et al.  Model learning for robot control: a survey , 2011, Cognitive Processing.

[18]  G. Meinsma,et al.  On the use of noncausal LTI operators in iterative learning control , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[19]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[20]  Scott Kuindersma,et al.  An efficiently solvable quadratic program for stabilizing dynamic locomotion , 2013, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[22]  Jan Peters,et al.  Learning torque control in presence of contacts using tactile sensing from robot skin , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[23]  Andrej Gams,et al.  On-line learning and modulation of periodic movements with nonlinear dynamical systems , 2009, Auton. Robots.

[24]  Jean-Jacques E. Slotine,et al.  Linear Matrix Inequalities for Physically Consistent Inertial Parameter Identification: A Statistical Perspective on the Mass Distribution , 2017, IEEE Robotics and Automation Letters.

[25]  S. Schaal,et al.  Robot juggling: implementation of memory-based learning , 1994, IEEE Control Systems.

[26]  Sergey Levine,et al.  Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics , 2014, NIPS.

[27]  Andrej Gams,et al.  Bio-inspired learning and database expansion of Compliant Movement Primitives , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[28]  Mikael Norrlöf,et al.  Iterative Learning Control : Analysis, Design, and Experiments , 2000 .

[29]  Pierre-Brice Wieber,et al.  Hierarchical quadratic programming: Fast online humanoid-robot motion generation , 2014, Int. J. Robotics Res..