Smart Industrial Robot Control Trends, Challenges and Opportunities within Manufacturing

Ārents, Jānis; Greitāns, Modris

doi:10.3390/app12020937

Cited by 137 publications

(58 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is a kind of a self-learning competence where the robot attempt to acquire knowledge and skills by continuous observation and imitation of people and other intelligent systems. As with humans, it requires observing events and situations, classifying and organizing them, extracting relevant features and inferring rules and understanding situations and partner's intentions (Arents and Greitans, 2022;Nicolescu and Mataric, 2005).…”

Section: Brief Summary About Ai and Hrimentioning

confidence: 99%

Overview of some Command Modes for Human-Robot Interaction Systems

Zaatri

2022

J INFORM SYSTEMS ENG

View full text Add to dashboard Cite

Interaction and command modes as well as their combination are essential features of modern and futuristic robotic systems interacting with human beings in various dynamical environments. This paper presents a synthetic overview concerning the most command modes used in Human-Robot Interaction Systems (HRIS). It includes the first historical command modes which are namely tele-manipulation, off-line robot programming, and traditional elementary teaching by demonstration. It then introduces the most recent command modes which have been fostered later on by the use of artificial intelligence techniques implemented on more powerful computers. In this context, we will consider specifically the following modes: interactive programming based on the graphical-user-interfaces, voice-based, pointing-on-image-based, gesture-based, and finally brain-based commands.

show abstract

Section: Brief Summary About Ai and Hrimentioning

confidence: 99%

Overview of some Command Modes for Human-Robot Interaction Systems

Zaatri

2022

J INFORM SYSTEMS ENG

View full text Add to dashboard Cite

show abstract

“…These intelligent robots that constantly enter our lives are constantly changing our understanding of future life. At the same time, they also put forward higher requirements for the control technology of intelligent robots [5].…”

Section: Introductionmentioning

confidence: 99%

Research on a New Adaptive Integral Sliding Mode Controller Based on a Small BLDC

Guo

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

A new adaptive saturation Integral Sliding Mode Controller (ADSA-ISMC) is presented to solve the speed fluctuation problem caused by a small brushless DC motor (S-BLDC) under variable load. First, according to the characteristics of S-BLDC and Kalman filter, a Kalman-based S-BLDC load disturbance observer is established, and an adaptive integrated sliding mode controller (AD-ISMC) is constructed based on the motor load obtained by the observer. Then, we introduce the saturation function into the input error link of the traditional integral sliding mode function, to propose a new ADSA-ISMC to improve the windup phenomenon produced by the integral sliding mode controller and prove the stability and convergence of the controller by the Lyapunov method. Finally, the experimental results show that the Kalman load disturbance observer can observe the motor load disturbance well. In addition, when a load of S-BLDC changes, many speed control performance indexes of ADSA-ISMC are significantly better than SMC and AD-ISMC. Theoretical analysis and experimental results show that the ADSA-ISMC proposed in this paper shows excellent control performance in S-BLDC speed control.

show abstract

“…Manipulator arms and other types of robots have become ubiquitous in modern industry and their use has been proliferating for decades, yet even now, the primary method for programming these devices remains the procedural code, hand crafted by specially trained technicians and engineers. This significantly increases the cost and complexity of commissioning process nodes that utilize industrial robots [1]. To this end, various alternative approaches grounded in machine learning have been proposed.…”

Section: Introductionmentioning

confidence: 99%

A Motion Capture and Imitation Learning Based Approach to Robot Control

2022

Self Cite

View full text Add to dashboard Cite

Imitation learning is a discipline of machine learning primarily concerned with replicating observed behavior of agents known to perform well on a given task, collected in demonstration data sets. In this paper, we set out to introduce a pipeline for collecting demonstrations and training models that can produce motion plans for industrial robots. Object throwing is defined as the motivating use case. Multiple input data modalities are surveyed, and motion capture is selected as the most practicable. Two model architectures operating autoregressively are examined—feedforward and recurrent neural networks. Trained models execute throws on a real robot successfully, and a battery of quantitative evaluation metrics is proposed. Recurrent neural networks outperform feedforward ones in most respects, but this advantage is not universal or conclusive. The data collection, pre-processing and model training aspects of our proposed approach show promise, but further work is required in developing Cartesian motion planning tools before it is applicable in production applications.

show abstract

Smart Industrial Robot Control Trends, Challenges and Opportunities within Manufacturing

Cited by 137 publications

References 115 publications

Overview of some Command Modes for Human-Robot Interaction Systems

Overview of some Command Modes for Human-Robot Interaction Systems

Research on a New Adaptive Integral Sliding Mode Controller Based on a Small BLDC

A Motion Capture and Imitation Learning Based Approach to Robot Control

Contact Info

Product

Resources

About