当前位置: X-MOL 学术Ind. Rob. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Robot hand-eye cooperation based on improved inverse reinforcement learning
Industrial Robot ( IF 1.8 ) Pub Date : 2021-11-30 , DOI: 10.1108/ir-09-2021-0208
Ning Yu 1 , Lin Nan 2 , Tao Ku 2
Affiliation  

Purpose

How to make accurate action decisions based on visual information is one of the important research directions of industrial robots. The purpose of this paper is to design a highly optimized hand-eye coordination model of the robot to improve the robots’ on-site decision-making ability.

Design/methodology/approach

The combination of inverse reinforcement learning (IRL) algorithm and generative adversarial network can effectively reduce the dependence on expert samples and robots can obtain the decision-making performance that the degree of optimization is not lower than or even higher than that of expert samples.

Findings

The performance of the proposed model is verified in the simulation environment and real scene. By monitoring the reward distribution of the reward function and the trajectory of the robot, the proposed model is compared with other existing methods. The experimental results show that the proposed model has better decision-making performance in the case of less expert data.

Originality/value

A robot hand-eye cooperation model based on improved IRL is proposed and verified. Empirical investigations on real experiments reveal that overall, the proposed approach tends to improve the real efficiency by more than 10% when compared to alternative hand-eye cooperation methods.



中文翻译:

基于改进逆强化学习的机器人手眼协作

目的

如何基于视觉信息做出准确的动作决策是工业机器人的重要研究方向之一。本文的目的是设计一个高度优化的机器人手眼协调模型,以提高机器人的现场决策能力。

设计/方法/方法

逆强化学习(IRL)算法与生成对抗网络相结合,可以有效降低对专家样本的依赖,机器人可以获得优化程度不低于甚至高于专家样本的决策性能。

发现

在仿真环境和真实场景中验证了所提模型的性能。通过监测奖励函数的奖励分布和机器人的轨迹,将所提出的模型与其他现有方法进行比较。实验结果表明,该模型在专家数据较少的情况下具有较好的决策性能。

原创性/价值

提出并验证了一种基于改进IRL的机器人手眼协作模型。对真实实验的实证研究表明,总体而言,与其他手眼协作方法相比,所提出的方法倾向于将实际效率提高 10% 以上。

更新日期:2021-11-30
down
wechat
bug