Machine Learning for Active Gravity Compensation in Robotics: Application to Neurological Rehabilitation Systems

Ugartemendia, Axier; Rosquete, Daniel; Gil, Jorge Juan; Díaz, Iñaki; Borro, Diego

doi:10.1109/mra.2020.2978484

Cited by 10 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the training is performed, the testing set is used to determine the quality of the model [24]. The testing set is unseen by the model until the evaluation and is only used for the forward propagation [25,26]. The errors are then compared to the real values in the set, and the quality of the model is determined based on the amount of error the model achieves on the testing set [27].…”

Section: Results Evaluationmentioning

confidence: 99%

Prediction of Robot Grasp Robustness using Artificial Intelligence Algorithms

et al. 2022

View full text Add to dashboard Cite

Predicting the quality of the robot end-effector grasp quality during an industrial robot manipulator operation can be an extremely complex task. As is often the case with such complex tasks, Artificial Intelligence methods may be applied to attempt the creation of a model -if sufficient data exists. The presented dataset uses a publicly available dataset, consisting of 992632 measurements of position, torque, and velocity -for each of the three joints of three fingers of the simulated end-effector. The dataset is first analyzed and pre-processed to prepare it for model training. The duplicate values are removed from the dataset, as well as the statistical outliers. Then, a multilayer perceptron (MLP) machine learning algorithm is applied to 80% of the data contained in the dataset, using the Grid Search algorithm to determine the best combination of MLP hyperparameters. As the dataset consists of torque, velocity, and speed measurements for separate joints and fingers of the tested end-effector the testing is performed to see if a subset of the inputs may be used to regress the robustness of the given grip. The normalization of the dataset is also applied, and its effect on the regression quality is tested. The results, evaluated with the coefficient of determination, show that while the best model is achieved using all the possible inputs, a satisfactory result can be obtained using only velocity and torque.The results also show that the normalization of the dataset improves the regression quality in all the observed cases.

show abstract

Section: Results Evaluationmentioning

confidence: 99%

Prediction of Robot Grasp Robustness using Artificial Intelligence Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To prove the optimality, the three conditions, obtained from Pontryagin's minimum principle, must be held. Considering Hamiltonian function (9), the first necessary condition for optimality results in:…”

Section: Assumption 2 (Observability Condition Continuous-time Domain)mentioning

confidence: 99%

“…Yun et al researched the compensation mechanism for a dual-arm cooperative manipulator which was subjected to variable weight due to the change of the waist of the robot, or in other words, the CoM of the system [7]. Ugartemendia et al investigated gravity compensation in rehabilitation robotics [9]. It was concluded that it is a mandatory feature in mechatronics systems for rehabilitations to present a neutral motion feeling for the people subjected to treatment.…”

Section: Introductionmentioning

confidence: 99%

Gravity compensation and optimal control of actuated multibody system dynamics

Nekoo

Acosta

Ollero

2021

IET Control Theory & Appl

View full text Add to dashboard Cite

This work investigates the gravity compensation topic, from a control perspective. The gravity could be levelled by a compensating mechanical system or in the control law, such as proportional derivative (PD) plus gravity, sliding mode control, or computed torque method. The gravity compensation term is missing in linear and nonlinear optimal control, in both continuous-and discrete-time domains. The equilibrium point of the control system is usually zero and this makes it impossible to perform regulation when the desired condition is not set at origin or in other cases, where the gravity vector is not zero at the equilibrium point. The system needs a steady-state input signal to compensate for the gravity in those conditions. The stability proof of the gravity compensated control law based on nonlinear optimal control and the corresponding deviation from optimality, with proof, are introduced in this work. The same concept exists in discrete-time control since it uses analog to digital conversion of the system and that includes the gravity vector of the system. The simulation results highlight two important cases, a robotic manipulator and a tilted-rotor hexacopter, as an application to the claimed theoretical statements.

show abstract

“…Although the weight of the mechanism is 8.2 kg, the inertia of the moving parts of the device that is felt by the users is m ≈ 3 kg. This is relatively high when compared to other mechanical interfaces [19], although the device is very easy to handle, because the motors compensate for the gravitational components of the mechanism [13]. HomeRehab has the option of working in two-dimensional (2D) and three-dimensional (3D) workspaces.…”

Section: Rehabilitation Devicementioning

confidence: 99%

“…Rehabilitation games are relevant scenarios in which to incorporate complex haptic effects, because virtual tasks are easier to understand if the haptic feedback is realistic [12]. These effects have several benefits, among them: the possibility to enhance the virtual scene and the ability to facilitate the rehabilitation, such as adding or subtracting the weight of the device by modifying the virtual mass or even making it weightless [13]. These virtual effects add immersiveness and realism to virtual interactions.…”

Section: Introductionmentioning

confidence: 99%

Stability Analysis and User Perception of Haptic Rendering Combining Virtual Elastic, Viscous and Inertial Effects

2020

Self Cite

View full text Add to dashboard Cite

Virtual Reality environments are being used on a mass scale in fields, such as Industry and Medicine. These virtual scenarios serve very different purposes such as prototyping, gaming and exercising. Interaction with the virtual environment is mainly achieved by senses of sight and hearing through devices, such as a mouse or VR glasses. To this end, haptic research started a few decades ago with the aim of improving this interaction through a sense of touch. A key element, hitherto not researched, is the effective combination of virtual elastic, viscous, and inertial effects in haptic feedback restored to the user and the safety implications of these feedback effects. It is of particular importance in neurological rehabilitation exercising, as interaction realism and safety are of great importance in therapy and for the patient. Therefore, this work addresses the stability analysis of the combination of three haptic effects—elastic, viscous, and inertial—and the subjective feeling on the part of users regarding different combinations of these effects. A theoretical analysis is presented with a view to establishing stable control principles, and a user-study was carried out in order to help understand the perception of users to different combinations of haptic effects.

show abstract

Machine Learning for Active Gravity Compensation in Robotics: Application to Neurological Rehabilitation Systems

Cited by 10 publications

References 18 publications

Prediction of Robot Grasp Robustness using Artificial Intelligence Algorithms

Prediction of Robot Grasp Robustness using Artificial Intelligence Algorithms

Gravity compensation and optimal control of actuated multibody system dynamics

Stability Analysis and User Perception of Haptic Rendering Combining Virtual Elastic, Viscous and Inertial Effects

Contact Info

Product

Resources

About