Filters








8,501 Hits in 5.4 sec

Toward Effective Soft Robot Control via Reinforcement Learning [chapter]

Haochong Zhang, Rongyun Cao, Shlomo Zilberstein, Feng Wu, Xiaoping Chen
2017 Lecture Notes in Computer Science  
effective control policies.  ...  The reinforcement learning process can be trained quickly by ignoring the specific materials and structural properties of the soft robot.  ...  There are many future work for soft robot control via reinforcement learning.  ... 
doi:10.1007/978-3-319-65289-4_17 fatcat:bgpuwinfknespmumcxy7sxzncm

2021 Index IEEE Robotics and Automation Letters Vol. 6

2021 IEEE Robotics and Automation Letters  
., +, LRA April 2021 707-714 Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks.  ...  ., +, LRA Oct. 2021 6289-6296 Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks.  ... 
doi:10.1109/lra.2021.3119726 fatcat:lsnerdofvveqhlv7xx7gati2xu

Deep Reinforcement Learning for Soft, Flexible Robots: Brief Review with Impending Challenges

Sarthak Bhagat, Hritwick Banerjee, Zion Ho Tse, Hongliang Ren
2019 Robotics  
For soft robotic structures possessing countless degrees of freedom, it is at times not convenient to formulate mathematical models necessary for training a deep reinforcement learning (DRL) agent.  ...  Deploying current imitation learning algorithms on soft robotic systems has provided competent results.  ...  The next big step towards learning control policies for robotic applications is imitation learning.  ... 
doi:10.3390/robotics8010004 fatcat:bxlbnniiwrdbhnf3vghkhiew3q

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

Cosimo Della Santina, Robert K. Katzschmann, Antonio Bicchi, Daniela Rus
2021 The international journal of robotics research  
Machine learning Three of the accepted papers use machine learning techniques to control soft robots.  ...  Model-based control Five of the accepted works make use of analytical models to derive effective controllers for soft continuum and articulated soft robots.  ... 
doi:10.1177/0278364921998088 fatcat:qheexbryg5fitas4qrc2nvzrau

2019 Index IEEE Robotics and Automation Letters Vol. 4

2019 IEEE Robotics and Automation Letters  
., +, LRA July 2019 2547-2552 Deep Reinforcement Learning in Soft Viscoelastic Actuator of Dielectric Elastomer.  ...  Pre-Charged Pneumatic Soft Gripper With Closed-Loop Control. Li, Y., +, Robotic Skins That Learn to Control Passive Structures.  ...  Permanent magnets Adaptive Dynamic Control for Magnetically Actuated Medical Robots.  ... 
doi:10.1109/lra.2019.2955867 fatcat:ckastwefh5chhamsravandtnx4

Table of Contents

2021 IEEE Robotics and Automation Letters  
Chung 2217 Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks . ,E. Babaians, and E.  ...  Au 2658 PRIMAL 2 : Pathfinding Via Reinforcement and Imitation Multi-Agent Learning -Lifelong . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lra.2021.3072707 fatcat:qyphyzqxfrgg7dxdol4qamrdqu

Review of machine learning methods in soft robotics

Daekyum Kim, Sang-Hun Kim, Taekyoung Kim, Brian Byunghyun Kang, Minhyuk Lee, Wookeun Park, Subyeong Ku, DongWook Kim, Junghan Kwon, Hochang Lee, Joonbum Bae, Yong-Lae Park (+2 others)
2021 PLoS ONE  
However, compared to rigid robots, soft robots have issues in modeling, calibration, and control in that the innate characteristics of the soft materials can cause complex behaviors due to non-linearity  ...  followed by a summary of the existing machine learning methods for soft robots.  ...  To accomplish such tasks, some papers have used reinforcement learning algorithms to control the robots.  ... 
doi:10.1371/journal.pone.0246102 pmid:33600496 pmcid:PMC7891779 fatcat:alu4zm72irespj6wydikzjb6ie

Table of Contents

2022 IEEE Robotics and Automation Letters  
Liu Aerobatic Tic-Toc Control of Planar Quadcopters via Reinforcement Learning . . . . . . . ...Z. Wang, R. Groß, and S.  ...  Kober SoMoGym: A Toolkit for Developing and Evaluating Controllers and Reinforcement Learning Algorithms for Soft Robots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lra.2022.3165102 fatcat:enjzebowe5hn7hsfwklc7nieuy

2020 Index IEEE Robotics and Automation Letters Vol. 5

2020 IEEE Robotics and Automation Letters  
., +, LRA April 2020 2380-2386 Control of a Silicone Soft Tripod Robot via Uncertainty Compensation.  ...  ., +, LRA Oct. 2020 5283-5290 Learning to Walk a Tripod Mobile Robot Using Nonlinear Soft Vibration Actuators With Entropy Adaptive Reinforcement Learning.  ... 
doi:10.1109/lra.2020.3032821 fatcat:qrnouccm7jb47ipq6w3erf3cja

Elastica: A compliant mechanics environment for soft robotic control [article]

Noel Naughton, Jiarui Sun, Arman Tekinalp, Girish Chowdhary, Mattia Gazzola
2020 arXiv   pre-print
Soft robots are notoriously hard to control.  ...  We demonstrate how Elastica can be coupled with five state-of-the-art reinforcement learning algorithms to successfully control a soft, compliant robotic arm and complete increasingly challenging tasks  ...  Reinforcement learning for soft robotic control.  ... 
arXiv:2009.08422v1 fatcat:yqdh6f7uu5evfaaghda6zsyv7a

Table of Contents

2021 IEEE Robotics and Automation Letters  
Frazzoli 4978 Towards Multi-Modal Perception-Based Navigation: A Deep Reinforcement Learning Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  M.Van der Loos 5010 Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation . and S.  ... 
doi:10.1109/lra.2021.3095987 fatcat:uyk6vlvv45hifbzj4ruzdi6w54

Table of Contents

2022 IEEE Robotics and Automation Letters  
Wang 382 Control of Rough Terrain Vehicles Using Deep Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Yin 183 Courteous Behavior of Automated Vehicles at Unsignalized Intersections Via Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lra.2021.3135183 fatcat:ia2shhauuvdnlbvqfizwuxrqwi

Keywords

2021 2021 18th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)  
and Path Planning of a Spherical Robot using Stochastic Signals PID controller Tuning, Control and Path Planning of a Spherical Robot using Stochastic Signals Plasma treatment Effect of argon plasma treatment  ...  of a Polycarbonate Polymer Matrix with an ABS Additive Reinforcement Learning Low-Level Control of a Quadrotor using Twin Delayed Deep Deterministic Policy Gradient (TD3) Resampling A Resampling Approach  ... 
doi:10.1109/cce53527.2021.9633101 fatcat:7ffdhuyqevhmpawcjajs2rgniq

Setting up a Reinforcement Learning Task with a Real-World Robot

A. Rupam Mahmood, Dmytro Korenkevych, Brent J. Komer, James Bergstra
2018 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks.  ...  On the other hand, the best hyper-parameter configuration from one task may often result in effective learning on held-out tasks even with different robots, providing a reasonable default.  ...  It is natural to expect that successes in simulations would inspire similar engagement within the reinforcement learning community toward policy learning with physical robots.  ... 
doi:10.1109/iros.2018.8593894 dblp:conf/iros/MahmoodKKB18 fatcat:uvpyhpm36rh7dmlijkti3euw2a

Benchmarking Reinforcement Learning Algorithms on Real-World Robots [article]

A. Rupam Mahmood, Dmytro Korenkevych, Gautham Vasan, William Ma, James Bergstra
2018 arXiv   pre-print
Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks.  ...  On the other hand, the best hyper-parameter configuration from one task may often result in effective learning on held-out tasks even with different robots, providing a reasonable default.  ...  It is natural to expect that successes in simulations would inspire similar engagement within the reinforcement learning community toward policy learning with physical robots.  ... 
arXiv:1809.07731v1 fatcat:ticoo72gvnb5jfbnm3oiu4jdd4
« Previous Showing results 1 — 15 out of 8,501 results