Optimal robot excitation and identification

By Jan Swevers, C. Ganseman, D. Tükel, J. Schutter, H. Brussel. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Model-based reinforcement learning with parametrized physical models and optimism-driven exploration (2015, background): “citation trajectories for model identification [5], [14], [25], [28], [31], [32].”
Fast planning of well conditioned trajectories for model learning (2014, background): “In [5], the optimal trajectory is parameterized as a finite Fourier series, with the Fourier coefficients optimized numerically.”
Block Contextual MDPs for Continual Learning (2021, background): “Our work is related to four broad areas: (i) System Identification and Adaptive Control, (ii) Continual RL, (iii) Context Modeling and (iv) Meta RL and Multitask RL. System Identification and Adaptive Control (Zadeh, 1956; Åström & Bohlin, 1965; Swevers et al., 1997; Bhat et al., 2002; Gevers et al.”
Adaptive Reactionless Motion and Parameter Identification in Postcapture of Space Debris (2013, background): “The issue of persistent excitation of input trajectories for a robotic manipulator has been tackled extensively in the context of robot dynamics identification [30–32].”
Learning-based identification and iterative learning control of direct-drive robots (2005, methodology): “, least-squares [4], maximum-likelihood [4], [6], and normal adaptive techniques [11].”
Model learning for robot control: a survey (2011, background): “For learning inverse dynamics, for example, rich data can be sampled from trajectories by approximately executing desired random point-to-point and rhythmic movements (Schaal and Sternad 1998; Swevers et al. 1997).”
Robot excitation trajectories for dynamic parameter estimation using optimized B-splines (2012, methodology): “Sensitivity of the Solution and Degree of Estimation To evaluate the estimated parameters, several criteria were proposed in the literature [2],[3],[6] and [12].”
Robust dynamic experimental identification of robots with set membership uncertainty (2005, background): “In [3], for instance, the parameterization of robot excitation trajectory in the frequency domain allows a reliable estimation of noise characteristics and an accurate estimation of robot joints velocities and accelerations: the ML estimator lays then on a (almost) noise-free regressor.”
Physical feasibility of robot base inertial parameter identification: A linear matrix inequality approach (2014, methodology): “The identification trajectory is generated and optimized using the techniques proposed by Swevers et al. (1997). Each kth joint trajectory is defined as a function of time t by”
Fast Model Identification via Physics Engines for Data-Efficient Policy Search (2017, methodology): “Traditional system identiﬁcation builds a dynamics model by minimizing prediction error (e.g., using least squares) [Swevers et al. , 1997].”