Journal Article10.1109/TSMCB.2012.2226026
Unbounded Motion Optimization by Developmental Learning
Alan L. Jennings,Raul Ordonez +1 more
5
TL;DR: An algorithm is presented for autonomous motion development with unbounded waveform resolution that predicts the expected outcome for a motion and provides gradient information for optimizing the motion and is compared against bootstrapping a direct optimization on a mathematical problem.
read more
Abstract: An algorithm is presented for autonomous motion development with unbounded waveform resolution. Rather than a single optimization in a very large space, memory is built to support incremental improvements; therefore, complexity is balanced by experience. Analogously, human development manages complexity by limiting it during initial learning stages. Motions are represented by cubic spline interpolation; therefore, the development technique applies broadly to function optimization. Adding a node to the splines allows all previous memory samples to transfer to the higher dimension space exactly. The memory-based model, which is a locally weighted regression (LWR), predicts the expected outcome for a motion and provides gradient information for optimizing the motion. Results are compared against bootstrapping a direct optimization (DO) on a mathematical problem. Additionally, the method has been implemented to learn voltage profiles with the lowest peak current for starting a motor. This method shows practical accuracy and scalability.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
G2-Type SRMPC Scheme for Synchronous Manipulation of Two Redundant Robot Arms
Long Jin,Yunong Zhang +1 more
TL;DR: Computer-simulation results validate the efficacy and accuracy of the SRMPC scheme and the corresponding PLPENN solver for synchronous manipulation of two redundant robot arms.
149
Enhanced Robotic Hand–Eye Coordination Inspired From Human-Like Behavioral Patterns
TL;DR: A reverse channel is introduced that transfers stimulus signals from robotic hand space to visual space to give the robot an enhanced reaching ability and successfully drives the visual system to notice the unseen object when the robotic hand touches an unseen object.
Video measurements of instantaneous forces of flapping wing vehicles
TL;DR: In this article, in-flight measurements of an ornithopter through the use of image processing were performed to measure the instantaneous forces of the upstroke and downstroke of the wing and found that the oscillation about the flight path is significant, being about 20% of the mean velocity and up to 10 g
12
Evaluation and Transformation of Unrealizable Tasks for Robot Systems in Representation Space
TL;DR: The proposed framework for a robot system to actively evaluate its realizability for a specific task based on its representation space is applied to the typical task of path planning for a robots manipulator and parking task of a mobile robot to show its effectiveness as well as its performance.
Robotic Task Realizability in Representation Space
Jianbo Su
- 01 Oct 2015
TL;DR: The representation space (R-Space) is proposed and constructed for a robot system to evaluate its feasibility to a prescribed task and reachesable area in the R-space formalizes the criteria for task realizability.
2
References
Electroactive Polymer Actuators in Dynamic Applications
William Kaal,Sven Herold +1 more
TL;DR: The nonlinearities in a dielectric elastomer (DE) actuator and their consequences for dynamic applications are analyzed on a theoretical level first and then shown to be practically relevant in an experimental setup.
85
Walking Motion Generation, Synthesis, and Control for Biped Robot by Using PGRL, LPI, and Fuzzy Logic
Tzuu-Hseng S. Li,Yu-Te Su,Shao-Wei Lai,Jhen-Jia Hu +3 more
- 01 Jun 2011
TL;DR: The results show that the robot not only has more stable walking but also increases its walking speed after learning and the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme.
77
Force adaptation transfers to untrained workspace regions in children
TL;DR: Examining the adaptive behavior of children found that learning to compensate an external damping force transferred to the opposite hemifield, which indicates that a model of the limb dynamics rather than an association of visited space and experienced force was acquired.
76
Radial Basis Function Neural Network With Incremental Learning for Face Recognition
Yee Wan Wong,Kah Phooi Seng,Li-Minn Ang +2 more
- 01 Aug 2011
TL;DR: A radial basis function (RBF) neural network with a new incremental learning method based on the regularized orthogonal least square (ROLS) algorithm is proposed for face recognition designed to accommodate new information without retraining the initial network.
65
Relaxed LMI-based stability analysis of fuzzy model-based control systems using approximated polynomial membership functions
Mohammand Narimani,Hak-Keung Lam,R. Dilmaghani,Charles D.A. Wolfe +3 more
- 18 Nov 2010
TL;DR: Relaxed linear-matrix-inequality-based stability conditions for fuzzy-model-based control systems with imperfect premise matching are proposed and it is shown that the well-known stability conditions can be special cases of the proposed stability conditions.
56