The Extended Kalman Filter (EKF) has become a standard technique used in a number of nonlinear estimation and machine learning applications. These include estimating the state of a nonlinear dynamic system, estimating parameters for nonlinear system identification (e.g., learning the weights of
Nonlinear Kalman Filtering for Force-Controlled Robot Tasks
โ Scribed by Tine Lefebvre, Herman Bruyninckx, Joris De Schutter (auth.)
- Publisher
- Springer-Verlag Berlin Heidelberg
- Year
- 2005
- Tongue
- English
- Leaves
- 268
- Series
- Springer Tracts in Advanced Robotics 19
- Edition
- 1
- Category
- Library
No coin nor oath required. For personal study only.
โฆ Synopsis
This monograph focuses on how to achieve more robot autonomy by means of reliable processing skills. "Nonlinear Kalman Filtering for Force-Controlled Robot Tasks " discusses the latest developments in the areas of contact modeling, nonlinear parameter estimation and task plan optimization for improved estimation accuracy. Kalman filtering techniques are applied to identify the contact state based on force sensing between a grasped object and the environment. The potential of this work is to be found not only for industrial robot operation in space, sub-sea or nuclear scenarios, but also for service robots operating in unstructured environments co-habited by humans where autonomous compliant tasks require active sensing.
โฆ Table of Contents
1 Introduction....Pages 1-10
2 Literature Survey: Autonomous Compliant Motion....Pages 11-23
3 Literature Survey: Bayesian Probability Theory....Pages 25-49
4 Kalman Filters for Nonlinear Systems....Pages 51-76
5 The Non-Minimal State Kalman Filter....Pages 77-94
6 Contact Modelling....Pages 95-119
7 Geometrical Parameter Estimation and CF Recognition....Pages 121-137
8 Experiment: A Cube-In-Corner Assembly....Pages 139-164
9 Task Planning with Active Sensing....Pages 165-197
10 General Conclusions....Pages 199-204
A The Linear Regression Kalman Filter....Pages 205-210
B The Non-Minimal State Kalman Filter....Pages 211-217
C Frame Transformations....Pages 219-221
D Kalman Filtering for Non-Minimal Measurement Models....Pages 223-226
E Partial Observation with the Kalman Filter....Pages 227-229
F A NMSKF Linearizing State for the Geometrical Parameter Estimation....Pages 231-234
G CF-Observable Parameter Space for Twist and Pose Measurements....Pages 235-239
โฆ Subjects
Automation and Robotics; Control Engineering; Artificial Intelligence (incl. Robotics); Systems Theory, Control
๐ SIMILAR VOLUMES
The Extended Kalman Filter (EKF) has become a standard technique used in a number of nonlinear estimation and machine learning applications. These include estimating the state of a nonlinear dynamic system, estimating parameters for nonlinear system identification (e.g., learning the weights of
"The book covers control and filtering problems for several classes of stochastic networked systems including stability, robustness, reliability, consensus performance, and/or disturbance attenuation levels within a unified theoretical framework. It derives sufficient conditions for systems to achie
<p>Though there have been significant advances in the theory and applications of linear time-invariant systems, developments regarding repetitive control have been sporadic. At the same time, there is a dearth of literature on repetitive control (RC) for nonlinear systems.<p>Addressing that gap, thi