Industrial robot trajectory optimization- a review

Ratiu, Mariana; Prichici, Mariana Adriana

doi:10.1051/matecconf/201712602005

Cited by 37 publications

(15 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Task-specific trajectory planning from traditional control methods have proven to be more efficient for designated tasks [29,30] though may lack the flexibility to repurpose a robot to cope with the changes of dynamic environments. On the other hand, optimization techniques from various trajectory planning methods [31], have effectively been adopted for reinforcement learning agents [32,33] that allow for better convergence and learning of the autonomous decision-making process. The introduction of curriculum to RL training process (CRL) helps learning by improving sample efficiency and generalization capabilities of the agent.…”

Section: Curriculum Learningmentioning

confidence: 99%

Curriculum-Based Deep Reinforcement Learning for Adaptive Robotics: A Mini-Review

Gupta¹,

Najjaran²

2021

Int J Robot Eng

View full text Add to dashboard Cite

To facilitate the current and future automation needs, the research community constantly seeks to develop dynamic and efficient autonomous decision-making agents. These agents must not only be robust to modeling uncertainties, internal and external changes, but can adapt to a range of tasks also. Recent progress in deep reinforcement learning has corroborated to its potential to train such autonomous and robust agents. At the same time, the introduction of curriculum learning has made the reinforcement learning process significantly more efficient and allowed for training on much broader tasks. This combination, Curriculum-based Deep Reinforcement Learning (CDRL), presents a powerful solution to meet the increasing complexity of today's automation industry that demands highly intelligent machines. With this work we present a concise review of CDRL methods within the context of their application to the field of adaptive robotics.

show abstract

Section: Curriculum Learningmentioning

confidence: 99%

Curriculum-Based Deep Reinforcement Learning for Adaptive Robotics: A Mini-Review

Gupta¹,

Najjaran²

2021

Int J Robot Eng

View full text Add to dashboard Cite

show abstract

“…Remark 1: The preprogrammed speed in (8) is calculated using Hwang's method [25], but other motion planning methods are possible [26]. Indeed, (9) is a simple method to estimate the pose using the method in another study [18].…”

Section: A Speed Alteration Strategymentioning

confidence: 99%

Collision-Free Speed Alteration Strategy for Human Safety in Human-Robot Coexistence Environments

Chan

Tsai

2020

IEEE Access

View full text Add to dashboard Cite

This paper presents a novel real-time collision-free speed alteration strategy using a danger index and an elite real-coded genetic algorithm (ERGA) for environments in which humans and robots coexist or cooperate, in order to guarantee the safety of an operator who works with a collaborative robot. A danger index based on ellipsoid modeling of the operator and robot describes the degree of safety during human-robot interactions. The ERGA and a penalty function are used to solve the constrained nonlinear optimization problem to change the handling speed of the robot. Comparative simulation results show the superiority of the proposed method by comparing to two existing methods. The applicability of the proposed method is verified using two experiments involving a 6-DoF industrial manipulator with an EtherCAT network protocol, an RGB-D sensor and a real-time operation system. INDEX TERMS Collaborative robot, danger index, ellipsoid modeling, elite real-coded genetic algorithm (ERGA), human-robot coexistence, human-robot cooperation, RGB-D sensor, speed alteration.

show abstract

“…A colaboração entre humanos e robôs tem um papel importante em smart working, em função de sua contribuição para maior produtividade e aumento de eficiência [4]. As aplicações de indústria 4.0 buscam ampliar o uso da robótica, através de conectividade entre máquinas (M2M) e utilização de robôs colaborativos, que permitem homens e equipamentos dividirem o mesmo espaço de trabalho de maneira segura [18].…”

Section: Robóticaunclassified

Towards Smart Working: Integration of Computer Simulation, Robotics and Measurement in Process in the Design of a Manufacturing Cell

Bonatto

Cecconello²

2020

SCI

View full text Add to dashboard Cite

show abstract

Industrial robot trajectory optimization- a review

Cited by 37 publications

References 60 publications

Curriculum-Based Deep Reinforcement Learning for Adaptive Robotics: A Mini-Review

Curriculum-Based Deep Reinforcement Learning for Adaptive Robotics: A Mini-Review

Collision-Free Speed Alteration Strategy for Human Safety in Human-Robot Coexistence Environments

Towards Smart Working: Integration of Computer Simulation, Robotics and Measurement in Process in the Design of a Manufacturing Cell

Contact Info

Product

Resources

About