Acquiring state from control dynamics to learn grasping policies for robot hands

A prominent emerging theory of sensorimotor development in biological systems proposes that control knowledge is encoded in the dynamics of physical interaction with the world. From this perspective, the musculoskeletal system is coupled through sensor feedback and neurological structure to a non-stationary world. Control is derived by reinforcing and learning to predict constructive patterns of interaction. We have adopted the traditions of dynamic pattern theory in which behavior is an artifact of coupled dynamical systems with a number of controllable degrees of freedom. For grasping and manipulation, we propose a closed-loop control process that is parametric in the number and identity of contact resources. We have shown previously that this controller generates a necessary condition for force closure grasps. In this paper, we will show how control decisions can be made by estimating patterns of membership in a family of prototypical dynamic models. A grasp controller can thus be tuned on-line to optimize performance over a variety of object geometries. This same process can be used to match the dynamics to several previously acquired haptic categories. We will illustrate how a grasping policy can be acquired that is incrementally optimal for several objects using our Salisbury hand with tactile sensor feedback.

[1]  Jeffrey C. Trinkle,et al.  Planning for Dexterous Manipulation with Sliding Contacts , 1990, Int. J. Robotics Res..

[2]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[3]  Roderic A. Grupen,et al.  A Computational Model for Repetitive Motion , 1996 .

[4]  Micha Sharir,et al.  Planning, geometry, and complexity of robot motion , 1986 .

[5]  Mark R. Cutkosky,et al.  Friction, Stability and the Design of Robotic Fingers , 1986 .

[6]  Christos H. Papadimitriou,et al.  The Geometry of Grasping , 1990, Int. J. Robotics Res..

[7]  J. Bruner.  Organization of early skilled action. , 1973, Child development.

[8]  Ronald S. Fearing.  Simplified Grasping and Manipulation with Dextrous Robot Hands , 1984 .

[9]  Justus H. Piater,et al.  Toward learning visual discrimination strategies , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[10]  Daniel E. Koditschek.  The Control of Natural Motion in Mechanical Systems , 1991 .

[11]  John F. Canny,et al.  Planning optimal grasps , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[12]  Daniel E. Koditschek,et al.  Distributed real-time control of a spatial robot juggler , 1992, Computer.

[13]  Roderic A. Grupen,et al.  Learning Control Composition in a Complex Environment , 1996 .

[14]  S. Schaal,et al.  Programmable Pattern Generators , 1998 .

[15]  S. Gruber,et al.  Robot hands and the mechanics of manipulation , 1987, Proceedings of the IEEE.

[16]  D. Lewkowicz,et al.  A dynamic systems approach to the development of cognition and action. , 2007, Journal of cognitive neuroscience.

[17]  Roderic A. Grupen,et al.  Learning to Coordinate Controllers - Reinforcement Learning on a Control Basis , 1997, IJCAI.

[18]  S. Shankar Sastry,et al.  Dynamic regrasping by coordinated control of sliding for a multifingered hand , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[19]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[20]  Roderic A. Grupen,et al.  Learning reactive admittance control , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[21]  Jeffrey C. Trinkle,et al.  Dextrous manipulation by rolling and finger gaiting , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[22]  Roderic A. Grupen,et al.  A control basis for learning multifingered grasps , 1997, J. Field Robotics.

[23]  J. A. Coelho,et al.  A Control Basis for Learning Multifingered Grasps , 1997 .

[24]  Gilson A. Giraldi,et al.  Learning policies for attentional control , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[25]  Jr. J. Kenneth Salisbury,et al.  Kinematic and force analysis of articulated hands , 1982 .

[26]  Daniel E. Koditschek,et al.  The construction of analytic diffeomorphisms for exact robot navigation on star worlds , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[27]  J. A. Coelho,et al.  Online grasp synthesis , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[28]  Tomás Lozano-Pérez,et al.  Planning two-fingered grasps for pick-and-place operations on polyhedra , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[29]  Matthew M. Williamson,et al.  Neural control of rhythmic arm movements , 1998, Neural Networks.

[30]  Jeffrey C. Trinkle,et al.  On the stability and instantaneous velocity of grasped frictionless objects , 1992, IEEE Trans. Robotics Autom..

[31]  Vijay Kumar,et al.  On the stability of grasped objects , 1996, IEEE Trans. Robotics Autom..

[32]  Jean Ponce,et al.  On Computing Two-Finger Force-Closure Grasps of Curved 2D Objects , 1993, Int. J. Robotics Res..

[33]  Roderic A. Grupen,et al.  Distributed Control Representation for Manipulation Tasks , 1995, IEEE Expert.

[34]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[35]  David J. Montana,et al.  The Kinematics of Contact and Grasp , 1988, Int. J. Robotics Res..

[36]  D. Koditschek.  The Application of Total Energy as a Lyapunov Function for Mechanical Control Systems , 1989 .

[37]  Jerry Pratt,et al.  Exploiting Natural Dynamics in the Control of a Planar Bipedal Walking Robot , 1998 .

[38]  Bernard Roth,et al.  Analysis of Multifingered Hands , 1986 .

[39]  Randy C. Brost,et al.  Automatic Grasp Planning in the Presence of Uncertainty , 1988, Int. J. Robotics Res..

[40]  Roderic A. Grupen,et al.  A Basis for Distributed Control of Manipulation Tasks , 1994 .

[41]  Gentaro Taga,et al.  A model of the neuro-musculo-skeletal system for anticipatory adjustment of human locomotion during obstacle avoidance , 1998, Biological Cybernetics.

[42]  Roderic A. Grupen,et al.  A feedback control structure for on-line learning tasks , 1997, Robotics Auton. Syst..

[43]  Kamal Souccar,et al.  On-line Grasp Estimator: a Partitioned State Space Approach 1 , 1992 .

[44]  Marc H. Raibert,et al.  Legged Robots That Balance , 1986, IEEE Expert.

[45]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[46]  Van-Duc Nguyen,et al.  The synthesis of stable grasps in the plane , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[47]  Imin Kao,et al.  Quasistatic Manipulation with Compliance and Sliding , 1992 .

[48]  Rodney A. Brooks,et al.  Learning to Coordinate Behaviors , 1990, AAAI.

[49]  Maja J. Mataric,et al.  Reinforcement Learning in the Multi-Robot Domain , 1997, Auton. Robots.

[50]  Andrew G. Barto,et al.  Improving Elevator Performance Using Reinforcement Learning , 1995, NIPS.

[51]  J Hoff,et al.  An Architecture for Behavior Coordination Learning , 1995 .

[52]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .