Real-time collision detection based on one class SVM for safe movement of humanoid robot

Narukawa, Kaname; Yoshiike, Takahide; Tanaka, K.; Kuroda, Mitsuhide

doi:10.1109/humanoids.2017.8246962

Cited by 20 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their scheme achieved an accuracy of 99.6%. Narukawa et al [18] proposed a real-time collision detection method. They built their method on the one-class support vector machine (SVM) method for the safe movement of humanoid robots.…”

Section: Related Workmentioning

confidence: 99%

Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot

Mahmoud,

Abdel-Jaber,

Sharkawy

2024

Automation

View full text Add to dashboard Cite

In this paper, the aim is to classify torque signals that are received from a 3-DOF manipulator using a pattern recognition neural network (PR-NN). The output signals of the proposed PR-NN classifier model are classified into four indicators. The first predicts that no collisions occur. The other three indicators predict collisions on the three links of the manipulator. The input data to train the PR-NN model are the values of torque exerted by the joints. The output of the model predicts and identifies the link on which the collision occurs. In our previous work, the position data for a 3-DOF robot were used to estimate the external collision torques exerted by the joints when applying collisions on each link, based on a recurrent neural network (RNN). The estimated external torques were used to design the current PR-NN model. In this work, the PR-NN model, while training, could successfully classify 56,592 samples out of 56,619 samples. Thus, the model achieved overall effectiveness (accuracy) in classifying collisions on the robot of 99.95%, which is almost 100%. The sensitivity of the model in detecting collisions on the links “Link 1, Link 2, and Link 3” was 97.9%, 99.7%, and 99.9%, respectively. The overall effectiveness of the trained model is presented and compared with other previous entries from the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot

Mahmoud,

Abdel-Jaber,

Sharkawy

2024

Automation

View full text Add to dashboard Cite

show abstract

“…In [27], various classifiers are developed and tested using the recorded signal samples. Similar work also includes [28], [29], where neural network is constructed to monitor the grasping slippages and colliding torques, and [30], [31], where SVM classifiers are developed to detect external collisions. Based on the mentioned work, a mature development framework for time series has been well-formed.…”

Section: Related Workmentioning

confidence: 99%

An Online Robot Collision Detection and Identification Scheme by Supervised Learning and Bayesian Decision Theory

Zhang

Qian

Schuller

et al. 2021

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

proposed collision identification scheme in this paper especially focuses on overcoming the following two challenges in practice: firstly, to timely and accurately report a collision within its early stage; secondly, to ensure a high identification accuracy in a complicated environment, where ubiquitous disturbance and noise are unneglectable. The experimental validation at the end of this paper confirms its promising application value in humanrobot collaboration.

show abstract

“…We propose to use an unsupervised technique which requires only data corresponding to the normal operation of the robot -namely one-class support vector machine (OCSVM). The technique was used in [1] for collision detection and collision point localisation in a humanoid which can help the remote operator to stop the robot in case of an emergency. In [2] the authors used an isolation forest-based anomaly detection method to detect the anomalous behaviour in Unmanned Aerial Vehicles (UAVs).…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Anomaly Detection for Safe Robot Operations

Somaiya¹,

Hanheide²,

Cielniak³

2020

UK-RAS Conference for PhD and Early Career Researchers Proceedings

View full text Add to dashboard Cite

Faults in robot operations are risky, particularly when robots are operating in the same environment as humans.Early detection of such faults is necessary to prevent further escalation and endangering human life. However, due to sensor noise and unforeseen faults in robots, creating a model for fault prediction is difficult. Existing supervised data-driven approaches rely on large amounts of labelled data for detecting anomalies, which is impractical in real applications. In this paper, we present an unsupervised machine learning approach for this purpose, which requires only data corresponding to the normal operation of the robot. We demonstrate how to fuse multi-modal information from robot motion sensors and evaluate the proposed framework in multiple scenarios collected from a real mobile robot.

show abstract

Real-time collision detection based on one class SVM for safe movement of humanoid robot

Cited by 20 publications

References 9 publications

Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot

Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot

An Online Robot Collision Detection and Identification Scheme by Supervised Learning and Bayesian Decision Theory

Unsupervised Anomaly Detection for Safe Robot Operations

Contact Info

Product

Resources

About