scholarly journals Modeling, learning, perception, and control methods for deformable object manipulation

2021 ◽  
Vol 6 (54) ◽  
pp. eabd8803
Author(s):  
Hang Yin ◽  
Anastasia Varava ◽  
Danica Kragic
Keyword(s):  
Data Driven ◽  
Deformable Objects ◽  
Control Methods ◽  
Open Problems ◽  
Integrate Model ◽  
Planning And Control ◽  
Classical Control ◽  
And Control ◽  
Theoretical Developments ◽  
And Task

Perceiving and handling deformable objects is an integral part of everyday life for humans. Automating tasks such as food handling, garment sorting, or assistive dressing requires open problems of modeling, perceiving, planning, and control to be solved. Recent advances in data-driven approaches, together with classical control and planning, can provide viable solutions to these open challenges. In addition, with the development of better simulation environments, we can generate and study scenarios that allow for benchmarking of various approaches and gain better understanding of what theoretical developments need to be made and how practical systems can be implemented and evaluated to provide flexible, scalable, and robust solutions. To this end, we survey more than 100 relevant studies in this area and use it as the basis to discuss open problems. We adopt a learning perspective to unify the discussion over analytical and data-driven approaches, addressing how to use and integrate model priors and task data in perceiving and manipulating a variety of deformable objects.

Modelling and control of manipulators with flexible links working on land and underwater environments

Robotica ◽  
2010 ◽  
Vol 29 (3) ◽  
pp. 461-470 ◽  
Author(s):  
Levent Gümüşel ◽  
Nurhan Gürsel Özmen
Keyword(s):  
Fuzzy Control ◽  
Control Method ◽  
Robot Manipulator ◽  
Control Methods ◽  
Control Laws ◽  
Linear Ordinary Differential Equations ◽  
Intelligent Technique ◽  
Wide Range ◽  
Classical Control ◽  
And Control

SUMMARYIn this study, modelling and control of a two-link robot manipulator whose first link is rigid and the second one is flexible is considered for both land and underwater conditions. Governing equations of the systems are derived from Hamilton's Principle and differential eigenvalue problem. A computer program is developed to solve non-linear ordinary differential equations defining the system dynamics by using Runge–Kutta algorithm. The response of the system is evaluated and compared by applying classical control methods; proportional control and proportional + derivative (PD) control and an intelligent technique; integral augmented fuzzy control method. Modelling of drag torques applied to the manipulators moving horizontally under the water is presented. The study confirmed the success of the proposed integral augmented fuzzy control laws as well as classical control methods to drive flexible robots in a wide range of working envelope without overshoot compared to the classical controls.

scholarly journals Optimal Control Design for Traffic Flow Maximization Based on Data-Driven Modeling Method

Energies ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 187
Author(s):  
Balázs Németh ◽  
Dániel Fényes ◽  
Zsuzsanna Bede ◽  
Péter Gáspár
Keyword(s):  
Traffic Flow ◽  
Optimization Problem ◽  
Control Design ◽  
Prediction Method ◽  
Data Driven ◽  
Traffic Network ◽  
Control Methods ◽  
Prediction And Control ◽  
Data Driven Modeling ◽  
And Control

This paper proposes enhanced prediction and control design methods for improving traffic flow with human-driven and automated vehicles. To achieve accurate prediction for the entire time horizon, data-driven and model-based prediction methods were integrated. The goal of the integration was to accurately predict the outflow of the traffic network, which was selected as the highway section in this paper. The proposed novel prediction method was used in the optimal design for calculating controlled inflows on highway ramps. The goal of the design was to reach the maximum outflow of the traffic network, even against disturbances on uncontrolled inflows of the network. The control design leads to an optimization problem based on the min–max principle, i.e., the traffic outflow is considered to be maximized by controlled inflows and to be minimized by uncontrolled inflows. The effectiveness of the prediction and the control methods through simulation examples are illustrated, i.e., traffic outflow can be maximized by the control system under various uncontrolled inflow values.

scholarly journals Bayesian Models of Brain and Behaviour

2012 ◽  
Vol 2012 ◽  
pp. 1-19 ◽  
Author(s):  
William Penny
Keyword(s):  
Bayesian Inference ◽  
Visual Processing ◽  
Spatial Scales ◽  
Bayesian Models ◽  
Mathematical Framework ◽  
Basic Principles ◽  
Planning And Control ◽  
Population Codes ◽  
And Control ◽  
Theoretical Developments

This paper presents a review of Bayesian models of brain and behaviour. We first review the basic principles of Bayesian inference. This is followed by descriptions of sampling and variational methods for approximate inference, and forward and backward recursions in time for inference in dynamical models. The review of behavioural models covers work in visual processing, sensory integration, sensorimotor integration, and collective decision making. The review of brain models covers a range of spatial scales from synapses to neurons and population codes, but with an emphasis on models of cortical hierarchies. We describe a simple hierarchical model which provides a mathematical framework relating constructs in Bayesian inference to those in neural computation. We close by reviewing recent theoretical developments in Bayesian inference for planning and control.

scholarly journals Evaluation System for Autonomous Control Methods in Coupled Planning and Control Systems

Procedia CIRP ◽  
2015 ◽  
Vol 33 ◽  
pp. 121-126 ◽  
Author(s):  
S. Grundstein ◽  
S. Schukraft ◽  
B. Scholz-Reiter ◽  
M. Freitag
Keyword(s):  
Control Systems ◽  
Evaluation System ◽  
Autonomous Control ◽  
Control Methods ◽  
Planning And Control ◽  
And Control

Optimizing Control Methods of Airport Pipeline Refueling Process

2015 ◽  
Vol 738-739 ◽  
pp. 1007-1011
Author(s):  
Xiao Zhong Zhang ◽  
Fan Qin Meng ◽  
Jie Hui Wang
Keyword(s):  
Intelligent Control ◽  
Control Methods ◽  
Fuzzy Pid Control ◽  
Pipe Line ◽  
Optimizing Control ◽  
The Stability ◽  
Stability And Accuracy ◽  
Classical Control ◽  
And Control ◽  
Better Than

Due to the non-linearity and long delay of airport pipe line refueling system, it is difficult for classical control methods to ensure stable pumping pressure and refueling flow. To improve the stability of the refueling process, the paper introduces human-simulated intelligent control (HSIC) method to the recognization of refueling status, online self-adjusting and control of refueling parameters. Simulation shows that the stability and accuracy of HSIC control methods were better than that of classical PID and fuzzy PID control.

Sign in / Sign up

Export Citation Format

Share Document