Objective learning from human demonstrations

JFS Lin, P Carreno-Medrano, M Parsapour… - Annual Reviews in …, 2021 - Elsevier
Researchers in biomechanics, neuroscience, human–machine interaction and other fields
are interested in inferring human intentions and objectives from observed actions. The …

Robust nonlinear control of blood glucose in diabetic patients subject to model uncertainties

B Farahmand, M Dehghani, N Vafamand, A Mirzaee… - ISA transactions, 2023 - Elsevier
Recent advances in the artificial pancreas system provide an emerging treatment option for
type 1 diabetes. The performance of the blood glucose regulation directly relies on the …

Inverse learning for data-driven calibration of model-based statistical path planning

M Menner, K Berntorp, MN Zeilinger… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
This paper presents a method for inverse learning of a control objective defined in terms of
requirements and their joint probability distribution from data. The probability distribution …

[HTML][HTML] A learning from demonstration framework for adaptive task and motion planning in varying package-to-order scenarios

R Ma, J Chen, J Oyekan - Robotics and Computer-Integrated Manufacturing, 2023 - Elsevier
Current advances in Task and Motion Planning (TAMP) framework often rely on a specific
and static task structure. A task structure is a sequence of how work pieces should be …

Using human ratings for feedback control: A supervised learning approach with application to rehabilitation robotics

M Menner, L Neuner, L Lünenburger… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
This article presents a method for tailoring a parametric controller based on human ratings.
The method leverages supervised learning concepts in order to train a reward model from …

Fast approximate multioutput gaussian processes

V Joukov, D Kulić - IEEE Intelligent Systems, 2022 - ieeexplore.ieee.org
Gaussian processes regression models are an appealing machine learning method as they
learn expressive nonlinear models from exemplar data with minimal parameter tuning and …

Understanding Feedforward–Feedback Controller Components In Human Movement Through Optimization-Based Approaches

M Parsapour - 2023 - uwspace.uwaterloo.ca
Despite many studies in human motion analysis using optimal control theory to understand
how movement is generated, less attention is focused on the structure of the optimal …

Human motion estimation and controller learning

V Joukov - 2021 - uwspace.uwaterloo.ca
Humans are capable of complex manipulation and locomotion tasks. They are able to
achieve energy-efficient gait, reject disturbances, handle changing loads, and adapt to …

[PDF][PDF] Learning Control Objectives from Human Interactions: Methods and Applications

M Menner - 2020 - research-collection.ethz.ch
This thesis investigates the design of control objectives for the automatic feedback control of
dynamical systems. In particular, it presents methodologies—in addition to their applications …

バイラテラルに基づく模倣学習による予測と制御

境野翔 - 日本ロボット学会誌, 2022 - jstage.jst.go.jp
**年の制御は, 最適化や学習を用いるものがトレンドとなっている. 例えば, リアルタイムで最適化
計算をして制御入力を導出するモデル予測制御 [1] や, 1 試行前の追従誤差を次の試行で補償する …