Learning to predict resistive forces during robotic excavation

Few robot tasks require as forceful an interaction with the world as excavation. In order to effectively plan its actions, a robot excavator requires a method to predict the resistive forces experienced as it scoops soil from the terrain. This paper presents methods for a robot to predict resistive forces and to improve its predictions based on experience, using "learning" methods. A simple analytical model of a flat blade translating through soil is extended to account to for phenomena specific to motions of an excavator. In addition, the paper examines how representation and methodology affect prediction performance.

[1]  Xin Li,et al.  Modeling soil: realtime dynamic models for soil slippage and manipulation , 1993, SIGGRAPH.

[2]  Reid G. Simmons,et al.  Task Planning For Robotic Excavation , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Nelson Earl Craig,et al.  Machines for moving earth , 2022 .

[4]  William H. Press,et al.  Numerical recipes , 1990 .

[5]  Regis Hoffman,et al.  Terrain Mapping For Long-duration Autonomous Walking , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Sanjiv Singh.  Developing Plans for Robotic Excavators , 1994 .

[7]  Edward McKyes,et al.  Soil Cutting and Tillage , 1986 .

[8]  V. I. Balovnev,et al.  Machines for moving the earth. , 1986 .

[9]  William R. Gill,et al.  Soil dynamics in tillage and traction , 1967 .

[10]  D.R.P. Hettiaratchi,et al.  Theoretical soil mechanics and implement design , 1988 .

[11]  K. Terzaghi.  Theoretical Soil Mechanics , 1943 .

[12]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[13]  A. R. Reece.  Paper 2: The Fundamental Equation of Earth-Moving Mechanics , 1964 .

[14]  Christopher G. Atkeson,et al.  Using locally weighted regression for robot learning , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[15]  P Cundall,et al.  A MICROCOMPUTER PROGRAM FOR MODELLING LARGE-STRAIN PLASTICITY PROBLEMS. PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON NUMERICAL METHODS IN GEOMECHANICS, 11-15 APRIL 1988, INNSBRUCK, AUSTRIA. VOLUMES 1 - 3 , 1988 .

[16]  Ralph Alcock,et al.  Soil Cutting and Tillage , 1986 .