Deep Neural Network Approach in Robot Tool Dynamics Identification for Bilateral Teleoperation

Su, Hang; Qi, Wen; Yang, Chenguang; Sandoval, Juan; Ferrigno, Giancarlo; Momi, Elena De

doi:10.1109/lra.2020.2974445

Cited by 126 publications

(50 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the accuracy of the developed model can be further improved by extending by involving appropriately adapted inspirations involving, amongst others, a series of technical concepts and or paradigms such as the so-called “Adaptive Recognition” [ 41 ], “Dynamic Identification” [ 42 ], and “Manipulator controls” [ 43 ].…”

Section: Discussionmentioning

confidence: 99%

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

Tavakkoli

Mohsenzadegan

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

The core objective of this paper is to develop and validate a comprehensive visual sensing concept for robustly classifying house types. Previous studies regarding this type of classification show that this type of classification is not simple (i.e., tough) and most classifier models from the related literature have shown a relatively low performance. For finding a suitable model, several similar classification models based on convolutional neural network have been explored. We have found out that adding/involving/extracting better and more complex features result in a significant accuracy related performance improvement. Therefore, a new model taking this finding into consideration has been developed, tested and validated. The model developed is benchmarked with selected state-of-art classification models of relevance for the “house classification” endeavor. The test results obtained in this comprehensive benchmarking clearly demonstrate and validate the effectiveness and the superiority of our here developed deep-learning model. Overall, one notices that our model reaches classification performance figures (accuracy, precision, etc.) which are at least 8% higher (which is extremely significant in the ranges above 90%) than those reached by the previous state-of-the-art methods involved in the conducted comprehensive benchmarking.

show abstract

Section: Discussionmentioning

confidence: 99%

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

Tavakkoli

Mohsenzadegan

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…NN was used in Ref. [114] for dynamics identification of a surgical robot which revealed a fast learning operation and it is robust to noise. A dynamic model of a two-FLM was obtained by acquisition of the data from the experimental work of the robot using NN method [115].…”

Section: System Identification Methodsmentioning

confidence: 99%

A critical review of modelling methods for flexible and rigid link manipulators

Lee

Alandoli

2020

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Mathematical modelling plays an important role for robotic manipulators in order to design their particular controllers. Also, it is hard challenge to obtain an accurate mathematical model or obtain a suitable modelling method in such vast field. Thus, this critical review is advantageous and indispensable for researchers who are interested in the area to gain fruitful knowledge on the mathematical modelling methods. This paper is classified based on the type of robotic manipulators such as flexible link manipulators (FLMs), rigid link manipulators (RLMs) and hybrid manipulators which involves rigid links and flexible links. The used modelling methods for FLMs are the assumed mode method, the finite element method, and the lumped parameter method as approximation techniques which are well explained and reviewed. The Lagrangian method has inclusive explanation and review which is widely participated for obtaining the dynamic equations of FLMs, and it is appropriate and commonly employed for modelling RLMs. The Newtonian method, the forward kinematic, and the inverse kinematic are also well discussed and reviewed which are suitable and commonly employed for modelling RLMs. The critical discussion of 170 articles reported in this paper guides researchers to select the suitable method for modelling. This paper reviews the published articles in the period of 2010-2020 except for few older articles for the need of providing essential theoretical knowledge. The advantages and disadvantages of each method are well summarized at the end of the paper. The intelligent identification methods are briefly discussed due to the lack of publications especially on the period of 2010-2020.

show abstract

“…Thus, Sun et al [37] presented a safe motion planning method for an imprecise flexible robot by minimizing the collision probability. Similarly, EMG-based analytics is being adapted for robotics motion control and related teleoperation procedures, such as tool identification and calibration [38][39][40].…”

Section: Literature Reviewmentioning

confidence: 99%

Motion and Trajectory Constraints Control Modeling for Flexible Surgical Robotic Systems

et al. 2020

View full text Add to dashboard Cite

Success of the da Vinci surgical robot in the last decade has motivated the development of flexible access robots to assist clinical experts during single-port interventions of core intrabody organs. Prototypes of flexible robots have been proposed to enhance surgical tasks, such as suturing, tumor resection, and radiosurgery in human abdominal areas; nonetheless, precise constraint control models are still needed for flexible pathway navigation. In this paper, the design of a flexible snake-like robot is presented, along with the constraints model that was proposed for kinematics and dynamics control, motion trajectory planning, and obstacle avoidance during motion. Simulation of the robot and implementation of the proposed control models were done in Matlab. Several points on different circular paths were used for evaluation, and the results obtained show the model had a mean kinematic error of 0.37 ± 0.36 mm with very fast kinematics and dynamics resolution times. Furthermore, the robot's movement was geometrically and parametrically continuous for three different trajectory cases on a circular pathway. In addition, procedures for dynamic constraint and obstacle collision detection were also proposed and validated. In the latter, a collision-avoidance scheme was kept optimal by keeping a safe distance between the robot's links and obstacles in the workspace. Analyses of the results showed the control system was optimal in determining the necessary joint angles to reach a given target point, and motion profiles with a smooth trajectory was guaranteed, while collision with obstacles were detected a priori and avoided in close to real-time. Furthermore, the complexity and computational effort of the algorithmic models were negligibly small. Thus, the model can be used to enhance the real-time control of flexible robotic systems.

show abstract

Deep Neural Network Approach in Robot Tool Dynamics Identification for Bilateral Teleoperation

Cited by 126 publications

References 40 publications

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

A critical review of modelling methods for flexible and rigid link manipulators

Motion and Trajectory Constraints Control Modeling for Flexible Surgical Robotic Systems

Contact Info

Product

Resources

About