Applications of Learning Algorithms to Industrial Robotics

Cipriani, Giulio; Bottin, Matteo; Rosati, Giulio

doi:10.1007/978-3-030-55807-9_30

Cited by 4 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern models have force/torque sensors on each joint that increase the perception of the robots, whereas other models have a camera near the endeffector. To make better use of these sensors, recent studies have been focused on the development of AI (Artificial Intelligence) algorithms (Cipriani et al, 2021) . Thanks to these algorithms cobots can learn from their error (Isbell & Shelton, 2001) .…”

Section: Safetymentioning

confidence: 99%

Human factors in cobot era: a review of modern production systems features

et al. 2022

Self Cite

View full text Add to dashboard Cite

Collaborative robots are increasingly common in modern production systems, since they allow to merge the productivity of automated systems with the flexibility and dexterity of manual ones. The direct interaction between the human and the robot can be the greatest advantage and the greatest limit of collaborative systems at the same time, depending on how it affects human factors like ergonomics and mental stress. This work presents an overview of collaborative robotics considering three main dimensions: robot features, modern production systems characteristics and human factors. A literature review on how such dimensions interact is addressed and a discussion on the current state of the art is presented, showing the topics that have been already widely explored and the research gaps that should be fulfilled in the future.

show abstract

Section: Safetymentioning

confidence: 99%

Human factors in cobot era: a review of modern production systems features

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among deep learning-based solutions for real-time applications, computer vision techniques such as image classification, event detection, object detection, and pose estimation in real-time scenarios have interested many researchers. Moreover, several industries have considered employing computer vision cloud-based solutions, including agriculture, transportation, broadcasting and entertainment, education, healthcare, manufacturing, mining, postal services, and telecommunication [12,13]. In such applications, practitioners seek computer vision end-to-end algorithms using imaging data, including static images or video frames, to classify images or localize objects in real-time scenarios [14].…”

Section: Introductionmentioning

confidence: 99%

Optimal Topology of Vision Transformer for Real-Time Video Action Recognition in an End-To-End Cloud Solution

Sarraf,

Kabia

2023

MAKE

View full text Add to dashboard Cite

This study introduces an optimal topology of vision transformers for real-time video action recognition in a cloud-based solution. Although model performance is a key criterion for real-time video analysis use cases, inference latency plays a more crucial role in adopting such technology in real-world scenarios. Our objective is to reduce the inference latency of the solution while admissibly maintaining the vision transformer’s performance. Thus, we employed the optimal cloud components as the foundation of our machine learning pipeline and optimized the topology of vision transformers. We utilized UCF101, including more than one million action recognition video clips. The modeling pipeline consists of a preprocessing module to extract frames from video clips, training two-dimensional (2D) vision transformer models, and deep learning baselines. The pipeline also includes a postprocessing step to aggregate the frame-level predictions to generate the video-level predictions at inference. The results demonstrate that our optimal vision transformer model with an input dimension of 56 × 56 × 3 with eight attention heads produces an F1 score of 91.497% for the testing set. The optimized vision transformer reduces the inference latency by 40.70%, measured through a batch-processing approach, with a 55.63% faster training time than the baseline. Lastly, we developed an enhanced skip-frame approach to improve the inference latency by finding an optimal ratio of frames for prediction at inference, where we could further reduce the inference latency by 57.15%. This study reveals that the vision transformer model is highly optimizable for inference latency while maintaining the model performance.

show abstract

“…In recent years, a significant research effort has been made in the field of collision avoidance due to the quick development of collaborative [1] and autonomous robots [2] by the industries. The former must move accordingly to operator safety, whereas the latter can act in unforeseeable ways due to wrong predictions.…”

Section: Introductionmentioning

confidence: 99%

Development and Validation of an End-Effector for Mitigation of Collisions

Tommasino

Bottin

Cipriani

et al. 2021

Journal of Mechanical Design

Self Cite

View full text Add to dashboard Cite

In robotics the risk of collisions is present both in industrial applications and in remote handling. If a collision occurs, the impact may damage both the robot and external equipment, which may result in successive imprecise robot tasks or line stops, reducing robot efficiency. As a result, appropriate collision avoidance algorithms should be used or, if it is not possible, the robot must be able to react to impacts reducing the contact forces. For this purpose, this paper focuses on the development of a special end-effector that can withstand impacts. It is able to protect the robot from impulsive forces caused by collisions of the end-effector, but it has no effect on possible collisions between the links and obstacles. The novel end-effector is based on a bi-stable mechanism that decouples the dynamics of the end-effector from the dynamics of the robot. The intrinsically non-linear behavior of the endeffector is investigated with the aid of numerical simulations. The effect of design parameters and operating conditions are analyzed and the interaction between the functioning of the bi-stable mechanism and the control system is studied. In particular, the effect of the mechanism in different scenarios characterized by different robot velocities is shown. Results of numerical simulations assess the validity of the proposed end-effector, which can lead to large reductions in impact forces. Numerical results are validated by means of specific laboratory tests.

show abstract

Applications of Learning Algorithms to Industrial Robotics

Cited by 4 publications

References 34 publications

Human factors in cobot era: a review of modern production systems features

Human factors in cobot era: a review of modern production systems features

Optimal Topology of Vision Transformer for Real-Time Video Action Recognition in an End-To-End Cloud Solution

Development and Validation of an End-Effector for Mitigation of Collisions

Contact Info

Product

Resources

About