Dynamic Control of Soft Robots Using Reinforcement Learning

2019 ◽  
Author(s):  
Ben Pawlowski ◽  
Charles W. Anderson ◽  
Jianguo Zhao
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Control ◽  
Soft Materials ◽  
Analytic Solutions ◽  
Effective Control ◽  
Soft Robots ◽  
Modeling And Control ◽  
Infinite Degree ◽  
Computationally Intensive ◽  
And Control

Abstract Soft robots made from soft materials recently attracted tremendous research owing to their unique softness compared with rigid robots, making them suitable for applications such as manipulation and locomotion. However, also due to their softness, the modeling and control of soft robots present a significant challenge because of the infinite degree of freedom. In this case, although analytic solutions can be derived for control, they are too computationally intensive for real-time application. In this paper, we aim to leverage reinforcement learning to approach the control problem. We gradually increase the complexity of the control problems to learn. We also test the effectiveness and efficiency of reinforcement learning techniques to the control of soft robots for different tasks. Simulation results show that the control commands to be computed in milliseconds, allowing effective control of soft manipulators, up to trajectory tracking.

Modeling and Control for Plant Dynamics Based on Reinforcement Learning

2009 ◽  
Vol 129 (4) ◽  
pp. 363-367
Author(s):  
Tomoyuki Maeda ◽  
Makishi Nakayama ◽  
Hiroshi Narazaki ◽  
Akira Kitamura
Keyword(s):  
Reinforcement Learning ◽  
Modeling And Control ◽  
Plant Dynamics ◽  
And Control

Modeling and Control of Wheel Motor Based Articulated Vehicle System

2019 ◽  
Author(s):  
Heeseong Kim ◽  
Taehyun Shim ◽  
Byungjun Sung
Keyword(s):  
Control System ◽  
Dynamic Control ◽  
Modeling And Control ◽  
Yaw Control ◽  
Articulated Vehicle ◽  
Vehicle Systems ◽  
Vehicle Dynamic Control ◽  
And Performance ◽  
Traction System ◽  
And Control

Abstract This paper investigates an effectiveness of vehicle dynamic control (VDC) system based on torque vectoring technique using in-wheel-motors to improve the performance of articulated vehicle systems. A 10 degree-of-freedom (DOF) articulated vehicle model including a tractor and a single axle trailer has been developed and its responses are validated with commercial vehicle software of Trucksim. This model includes a nonlinear tire model (MF tire), a hydraulic damping at the hitch, and a traction system using in-wheel-motors at the trailer axle. In this paper, a yaw control system is developed to track the reference yaw rate with application of yaw moment at the trailer axle using torque distribution of in-wheel-motors. The effectiveness of the proposed control system is validated through simulation of sinusoidal steering maneuver on high mu and slippery road conditions. The simulation results show that in-wheel-motors can improve safety and performance of articulate vehicle systems.

Modeling and control of biologically inspired flying robots

Robotica ◽  
2011 ◽  
Vol 30 (1) ◽  
pp. 107-121 ◽  
Author(s):  
Micael S. Couceiro ◽  
J. Miguel A. Luz ◽  
Carlos M. Figueiredo ◽  
N. M. Fonseca Ferreira
Keyword(s):  
Dynamic Models ◽  
Dynamic Control ◽  
Biologically Inspired ◽  
Modeling And Control ◽  
High Level ◽  
New Generation ◽  
And Control ◽  
Level Calculation ◽  
Potential Use ◽  
Flying Robots

SUMMARYThis paper covers a wide knowledge of physical and dynamical models useful for building flying robots and a new generation of flying platform developed in the similarity of flying animals. The goal of this work is to develop a simulation environment and dynamic control using the high-level calculation tool MatLab and the modeling, simulation, and analysis of dynamic systems tool Simulink. Once created the dynamic models to study, this work involves the study and understanding of the dynamic stability criteria to be adopted and their potential use in the control of flying models.

Time Domain Simulation for a 6 DOF Tanker Model in Presence of Waves

2014 ◽  
Vol 596 ◽  
pp. 590-593
Author(s):  
Qiao Mei Sun ◽  
Jin Guo Chen
Keyword(s):  
Pid Controller ◽  
Dynamic Control ◽  
Control Methods ◽  
Time Domain Simulation ◽  
Simulation Experiments ◽  
Modeling And Control ◽  
Position And Orientation ◽  
And Control ◽  
Marine Vessels ◽  
Motion Behavior

Modeling and control of marine vessels raised huge interests in recent years. Lots of articles provided many different mathematical modeling and dynamic control methods with advanced intelligent algorithms. In this paper we presented a 6 DOF dynamic model for a tanker vessel, investigated on its maneuverability and conducted numerical simulation experiments to show 6 DOF motion behavior of the vessel including position and orientation. And we discussed the turning ability of the vessel in simulation using a PID controller in the present of environmental waves.

scholarly journals Review on generic methods for mechanical modeling, simulation and control of soft robots

PLoS ONE ◽  
2022 ◽  
Vol 17 (1) ◽  
pp. e0251059
Author(s):  
Pierre Schegg ◽  
Christian Duriez
Keyword(s):  
Dynamic Control ◽  
Material Behavior ◽  
Sensor Data ◽  
Control Algorithms ◽  
Mechanical Modeling ◽  
Soft Robots ◽  
Mechanical Compliance ◽  
Mechanical Models ◽  
Simulation And Control ◽  
And Control

In this review paper, we are interested in the models and algorithms that allow generic simulation and control of a soft robot. First, we start with a quick overview of modeling approaches for soft robots and available methods for calculating the mechanical compliance, and in particular numerical methods, like real-time Finite Element Method (FEM). We also show how these models can be updated based on sensor data. Then, we are interested in the problem of inverse kinematics, under constraints, with generic solutions without assumption on the robot shape, the type, the placement or the redundancy of the actuators, the material behavior… We are also interested by the use of these models and algorithms in case of contact with the environment. Moreover, we refer to dynamic control algorithms based on mechanical models, allowing for robust control of the positioning of the robot. For each of these aspects, this paper gives a quick overview of the existing methods and a focus on the use of FEM. Finally, we discuss the implementation and our contribution in the field for an open soft robotics research.

scholarly journals Editorial: Soft Robotic Modeling and Control: Bringing Together Articulated Soft Robots and Soft-Bodied Robots

2021 ◽  
Vol 40 (1) ◽  
pp. 3-6
Author(s):  
Cosimo Della Santina ◽  
Robert K. Katzschmann ◽  
Antonio Bicchi ◽  
Daniela Rus
Keyword(s):  
Soft Robots ◽  
Modeling And Control ◽  
And Control

scholarly journals First-Order Dynamic Modeling and Control of Soft Robots

2020 ◽  
Vol 7 ◽  
Author(s):  
Thomas George Thuruthel ◽  
Federico Renda ◽  
Fumiya Iida
Keyword(s):  
Dynamic Modeling ◽  
Soft Robots ◽  
Modeling And Control ◽  
First Order ◽  
And Control

Spline-Based Modeling and Control of Soft Robots

2020 ◽  
Author(s):  
Shuzhen Luo ◽  
Merrill Edmonds ◽  
Jingang Yi ◽  
Xianlian Zhou ◽  
Yantao Shen
Keyword(s):  
Soft Robots ◽  
Modeling And Control ◽  
And Control

A Review of Fuzzy Logic Based Control of Robotic Manipulators

2011 ◽  
Author(s):  
Jayant B. Khurpade ◽  
Sukhdeep S. Dhami ◽  
Sukhwant S. Banwait
Keyword(s):  
Fuzzy Logic ◽  
Performance Indicators ◽  
Fuzzy Systems ◽  
Robotic Manipulators ◽  
Kinematics And Dynamics ◽  
Modeling And Control ◽  
Quantitative Results ◽  
Non Linear Systems ◽  
Computationally Intensive ◽  
And Control

Robotic manipulators are complex mechanisms due to which their kinematics and dynamics are nonlinear in nature and computationally intensive. Fuzzy logic based approach provides an alternative for modeling and control of non-linear systems and hence has been extensively applied in the field of robotics. This paper presents a review of fuzzy logic based techniques for modeling and control of robotic manipulators. The survey is reported in terms of objectives, types of robotic manipulators, types and structures of fuzzy systems employed. A summary of quantitative results is presented as performance indicators of fuzzy modeling and control of robotic manipulators.

Sign in / Sign up

Export Citation Format

Share Document