Collision Detection for Industrial Collaborative Robots: A Deep Learning Approach

Heo, Young Jin; Kim, Dayeon; Lee, Woongyong; Kim, Hyoungkyun; Park, Jonghoon; Chung, Wan Kyun

doi:10.1109/lra.2019.2893400

Cited by 129 publications

(71 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking into account the simple comparison of predicted and actual motor current values, the collision detection time can be limited even to the sampling period (42 ms for CURA6). Absolutely estimating, this time seems quite long compared to the results of other neural networks presented in [ 15 ], where the collision detection task performed with a MOD method takes 30 ms and 18.4 ms—in the case of CollisionNet (with a sampling period of approx. 0.25 ms).…”

Section: Collision Detectionmentioning

confidence: 93%

See 1 more Smart Citation

A Simple Neural Network for Collision Detection of Collaborative Robots

Czubenko

Kowalczuk

2021

Sensors

View full text Add to dashboard Cite

Due to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents the practical aspect of collision detection with the use of a simple neural architecture. A virtual force and torque sensor, implemented as a neural network, may be useful in a team of collaborative robots. Four different approaches are compared in this article: auto-regressive (AR), recurrent neural network (RNN), convolutional long short-term memory (CNN-LSTM) and mixed convolutional LSTM network (MC-LSTM). These architectures are analyzed at different levels of input regression (motor current, position, speed, control velocity). This sensor was tested on the original CURA6 robot prototype (Cooperative Universal Robotic Assistant 6) by Intema. The test results indicate that the MC-LSTM architecture is the most effective with the regression level set at 12 samples (at 24 Hz). The mean absolute prediction error obtained by the MC-LSTM architecture was approximately 22 Nm. The conducted external test (72 different signals with collisions) shows that the presented architecture can be used as a collision detector. The MC-LSTM collision detection f1 score with the optimal threshold was 0.85. A well-developed virtual sensor based on such a network can be used to detect various types of collisions of cobot or other mobile or stationary systems operating on the basis of human-machine interaction.

show abstract

Section: Collision Detectionmentioning

confidence: 93%

“…This article proposes a solution to the problem of robot collision detection using a virtual force sensor based on neural networks. The topic of collision detection by neural networks is discussed in the literature [ 14 , 15 , 16 , 17 ]. However, only in a few cases, deep neural networks are used.…”

Section: Introductionmentioning

confidence: 99%

A Simple Neural Network for Collision Detection of Collaborative Robots

Czubenko

Kowalczuk

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Sharkawy et al [12] used the velocity of the robot and the applied force to feed a multilayer neural network to modify online the virtual damping of the admittance controller. Heo et al [13] used a Convolutional Neural Network to train a collision model for a robot using joint signals such as positions, velocities and estimated torques. In their case, they use the force sensor to label the time periods where a collision has occurred.…”

Section: Related Workmentioning

confidence: 99%

Recurrent Neural Networks for Inferring Intentions in Shared Tasks for Industrial Collaborative Robots

Maceira

Olivares-Alarcos

Alenyà

2020

2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

Industrial robots are evolving to work closely with humans in shared spaces. Hence, robotic tasks are increasingly shared between humans and robots in collaborative settings. To enable a fluent human robot collaboration, robots need to predict and respond in real-time to worker's intentions. We present a method for early decision using force information. Forces are provided naturally by the user through the manipulation of a shared object in a collaborative task. The proposed algorithm uses a recurrent neural network to recognize operator's intentions. The algorithm is evaluated in terms of action recognition on a force dataset. It excels at detecting intentions when partial data is provided, enabling early detection and facilitating a quick robot reaction.

show abstract

“…By contrast with traditional machine learning solutions, deep learning techniques are undergoing rapid development. Applications of deep learning involve information retrieval [4], natural language processing [5], human voice recognition [6], computer vision [7], anomaly detection [8], recommendation systems [9], bioinformatics [10], medicine [11,12], crop science [13], earth science [14], robotics [15][16][17][18], transportation engineering [19], communication technologies [20][21][22], and system simulation [23,24].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning on Computational-Resource-Limited Platforms: A Survey

Chen

Zhang

et al. 2020

Mobile Information Systems

View full text Add to dashboard Cite

Nowadays, Internet of Things (IoT) gives rise to a huge amount of data. IoT nodes equipped with smart sensors can immediately extract meaningful knowledge from the data through machine learning technologies. Deep learning (DL) is constantly contributing significant progress in smart sensing due to its dramatic superiorities over traditional machine learning. The promising prospect of wide-range applications puts forwards demands on the ubiquitous deployment of DL under various contexts. As a result, performing DL on mobile or embedded platforms is becoming a common requirement. Nevertheless, a typical DL application can easily exhaust an embedded or mobile device owing to a large amount of multiply and accumulate (MAC) operations and memory access operations. Consequently, it is a challenging task to bridge the gap between deep learning and resource-limited platforms. We summarize typical applications of resource-limited deep learning and point out that deep learning is an indispensable impetus of pervasive computing. Subsequently, we explore the underlying reasons for the high computational overhead of DL through reviewing the fundamental concepts including capacity, generalization, and backpropagation of a neural network. Guided by these concepts, we investigate on principles of representative research works, as well as three types of solutions: algorithmic design, computational optimization, and hardware revolution. In pursuant to these solutions, we identify challenges to be addressed.

show abstract

Collision Detection for Industrial Collaborative Robots: A Deep Learning Approach

Cited by 129 publications

References 14 publications

A Simple Neural Network for Collision Detection of Collaborative Robots

A Simple Neural Network for Collision Detection of Collaborative Robots

Recurrent Neural Networks for Inferring Intentions in Shared Tasks for Industrial Collaborative Robots

Deep Learning on Computational-Resource-Limited Platforms: A Survey

Contact Info

Product

Resources

About