Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








8,933 Hits in 7.6 sec

Time-Optimal Path Tracking for Industrial Robots: A Dynamic Model-Free Reinforcement Learning Approach [article]

Jiadong Xiao, Lin Li, Tie Zhang, Yanbiao Zou
2019 arXiv   pre-print
In pursuit of the time-optimal path tracking (TOPT) trajectory of a robot manipulator along a preset path, a beforehand identified robot dynamic model is usually used to obtain the required optimal trajectory  ...  for perfect tracking.  ...  Although model-based reinforcement learning algorithm does exist, most of the above-mentioned reinforcement learning algorithms for robots are model-free.  ... 
arXiv:1907.01348v3 fatcat:hahgs6biwbg57fk7jmtjgncili

Special Feature on Advanced Mobile Robotics

DaeEun Kim
2019 Applied Sciences  
Mobile robots and their applications are involved with many research fields including electrical engineering, mechanical engineering, computer science, artificial intelligence and cognitive science [..  ...  [40] proposed a grip planning method for biped robots to produce optimal collision-free grip sequences under kinematic constraints.  ...  It uses a system model with radial-basis function neural network. The control system provides high tracking accuracy as well as fast response time. Kelemen et al.  ... 
doi:10.3390/app9214686 fatcat:25p6a4yjxzd25anrryk5cdghii

Sensors for Robots

Xin Zhao, Mingzhu Sun, Qili Zhao
2024 Sensors  
Currently, robots are playing significant roles in industry [...]  ...  In Contribution 1, the authors proposed a multi-path scattering model for virtual vegetation.  ...  To achieve this target, this study specified the problem as a Markov decision process (MDP) and deployed a deep reinforcement learning (RL) temporal difference model-free algorithm known as the deep Q-network  ... 
doi:10.3390/s24061854 pmid:38544116 pmcid:PMC10975082 fatcat:h7rwfz745bgffpw7abvdhhfdly

Mobile Robot Navigation and Obstacle Avoidance Techniques: A Review

Anish Pandey
2017 International Robotics & Automation Journal  
Several techniques have been applied by the various researchers for mobile robot navigation and obstacle avoidance.  ...  The applications of the autonomous mobile robot in many fields such as industry, space, defence and transportation, and other social sectors are growing day by day.  ...  Real-time collision-free path planning becomes more difficult when the robot is moving in a dynamic and unstructured environment.  ... 
doi:10.15406/iratj.2017.02.00023 fatcat:m6viumq36zf5zbfeexua475gjy

Aerial Field Robotics [chapter]

Mihir Kulkarni, Brady Moon, Kostas Alexis, Sebastian Scherer
2022 Encyclopedia of Robotics  
We conclude with notable contributions and discuss considerations for future research that are essential for resilience in aerial robotics.  ...  Aerial field robotics research represents the domain of study that aims to equip unmanned aerial vehicles - and as it pertains to this chapter, specifically Micro Aerial Vehicles (MAVs)- with the ability  ...  Provided a map, the planning architecture employs a policy for searching admissible paths that optimizes specified objectives for the robot.  ... 
doi:10.1007/978-3-642-41610-1_221-1 fatcat:mpvrn2v4lvhlbnjmds7vxy2ali

On the Development of Learning Control for Robotic Manipulators

Dan Zhang, Bin Wei
2017 Robotics  
This review is able to give a general guideline for future research in learning control for robotic manipulators.  ...  Learning control in robotic manipulators is mainly used to address the issue that the friction at the joints of robotic mechanisms and other uncertainties may exist in the dynamic models, which are very  ...  In [28] , the authors employed the model-free feedback-assisted iterative learning control scheme for the purpose of the path tracking of a 6-DOF mechanism.  ... 
doi:10.3390/robotics6040023 fatcat:k2zex76mz5fk3p6jiuy5mlde54

Table of Contents

2021 2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM)  
.................281 Design of an Optimized Fuzzy Controller for a 3R Non-planar Robotic Manipulator ......................287 On the effectiveness of Stable Model Predictive vs.  ...  .........................................230 Multirate Adaptive Inverse Dynamics Control of 5 DOF Industrial Gryphon Robot ........................255 Design of a Reinforcement Learning based PID Controller  ... 
doi:10.1109/icrom54204.2021.9663492 fatcat:nchpnhiwjbhazeuq3iw4sp2mxu

A Survey for Machine Learning-Based Control of Continuum Robots

Xiaomei Wang, Yingqi Li, Ka-Wai Kwok
2021 Frontiers in Robotics and AI  
However, the trade-off between flexibility and controllability of soft manipulators may not be readily optimized but would be demanded for specific kinds of modeling approaches.  ...  In its application of minimally invasive surgery, such a continuum concept shares the same view of robotization for conventional endoscopy/laparoscopy.  ...  In the following sections, for the sake of clear expression, methods with kinematics/dynamics model denote model-based reinforcement learning; while those without such model represent model-free approaches  ... 
doi:10.3389/frobt.2021.730330 pmid:34692777 pmcid:PMC8527450 fatcat:p4yeo5jqajfhphzsdbiu746swa

A Review of Path-Planning Approaches for Multiple Mobile Robots

Shiwei Lin, Ang Liu, Jianguo Wang, Xiaoying Kong
2022 Machines  
Finally, the new challenge in multi-robot path planning is proposed as fault tolerance, which is important for real-time operations.  ...  This paper reviews multi-robot path-planning approaches and decision-making strategies and presents the path-planning algorithms for various types of robots, including aerial, ground, and underwater robots  ...  A multi-robot path-planning algorithm for industrial robots is presented based on the first low polynomial-time algorithm on grids [122] .  ... 
doi:10.3390/machines10090773 fatcat:bojo6szg7jcqzkipleoxj4e3qi

Learning Robotic Assembly from CAD [article]

Garrett Thomas, Melissa Chien, Aviv Tamar, Juan Aparicio Ojea, Pieter Abbeel
2018 arXiv   pre-print
Reinforcement learning (RL) is a promising approach for autonomously acquiring robot skills that involve contact-rich dynamics.  ...  We show that our approach effectively improves over traditional control approaches for tracking the motion plan, and can solve assembly tasks that require high precision, even without accurate state estimation  ...  The authors would like to thank Menglong Guo for 3D-printing the objects used in our experiments.  ... 
arXiv:1803.07635v2 fatcat:spdof2arh5c6xocarbyrpjvipy

Reinforcement learning based compensation methods for robot manipulators

Yudha P. Pane, Subramanya P. Nageshrao, Jens Kober, Robert Babuška
2019 Engineering applications of artificial intelligence  
The proposed learning algorithms are evaluated on a 6-DoF industrial robotic manipulator arm to follow different kinds of reference paths, such as square or a circular path, or to track a trajectory on  ...  Smart robotics will be a core feature while migrating from Industry 3.0 (i.e., mass manufacturing) to Industry 4.0 (i.e., customized or social manufacturing).  ...  PD is used as a baseline for model-free, non adaptive control method, while MPC is used as a reference for model-based control framework and finally ILC is chosen as a baseline for model-free and adaptive  ... 
doi:10.1016/j.engappai.2018.11.006 fatcat:wdkftm23hnffvn534fmhtpt2jy

2020 Index IEEE Transactions on Robotics Vol. 36

2020 IEEE Transactions on robotics  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Costanzo, M., +, TRO Feb. 2020 157-173 Industrial robots PPCPP: A Predator-Prey-Based Approach to Adaptive Coverage Path Plan-ning.  ...  De Stefano, M., +, TRO Feb. 2020 189-203 An Iterative Approach for Accurate Dynamic Model Identification of Industrial Robots.  ... 
doi:10.1109/tro.2021.3050417 fatcat:gzwbyhjzhbdnrdp6prpokofstu

Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model

Alireza Rastegarpanah, Jamie Hathaway, Rustam Stolkin
2021 Frontiers in Robotics and AI  
We formulate a combination of model predictive control with image-based path planning and real-time visual feedback, based on a learned state-space dynamic model.  ...  The control of the interaction between the robot and environment, following a predefined geometric surface path with high accuracy, is a fundamental problem for contact-rich tasks such as machining, polishing  ...  Under the MPC approach, the path-following task can be reformulated as a discrete-time optimal control problem (OCP) for the current time t: with the objective of minimizing a cost function J over a given  ... 
doi:10.3389/frobt.2021.688275 fatcat:jajsm4q3kfgkxfm4qwteoiniuq

Vision-Based Mobile Robot Controllers: A Scientific Review

Adnan Mohsin Abdulazeez, Fayez Saeed Faizi
2021 Turkish Journal of Computer and Mathematics Education  
Others are for military usages such as drones and the pets robots just for entertainment.  ...  Today, there are different types of self-controlled robots. Some of them had critical effects on our lives like industrial and medical robots.  ...  The proposed model utilizes a supervised approach for the feature extraction and reinforcement method to process and predict the output.  ... 
doi:10.17762/turcomat.v12i6.2695 fatcat:hxdsdt2kl5hs3eswac4ckeuv6i

2021 Index IEEE Robotics and Automation Letters Vol. 6

2021 IEEE Robotics and Automation Letters  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, LRA July 2021 5324-5331 Dual-Objective Collision-Free Path Optimization of Arc Welding Robot.  ...  ., +, LRA Oct. 2021 7145-7152 Arc welding Dual-Objective Collision-Free Path Optimization of Arc Welding Robot.  ... 
doi:10.1109/lra.2021.3119726 fatcat:lsnerdofvveqhlv7xx7gati2xu
« Previous Showing results 1 — 15 out of 8,933 results