Human-Adaptive Impedance Control Using Recurrent Neural Network for Stability Recovery in Human-Robot Cooperation

Hanafusa, Misaki; Ishikawa, Jun

doi:10.1109/amc44022.2020.9244389

Cited by 7 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All retrieved publications that discuss exoskeletons target the upper limbs (Orlando et al 2010, Xiang et al 2012, Ren et al 2019. Similarly, all prostheses applications aim for the control of a prosthetic hand (Shima and Tsuji 2010, Li et al 2017, 2018, George et al 2018, Wan et al 2018, Jafarzadeh et al 2019, Hanafusa and Ishikawa 2020, Tam et al 2020. In the retrieved publications, the number of degrees of freedom that are provided by the device vary among the devices used.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Two publications use EMG for wheelchair control(Stroh and Desai 2019, Zhou et al 2019) and two also for operating a robotic arm(Hu et al 2015, Song et al 2020. Other applications that use EMG include drones(Redrovan and Kim 2018), real-time gesture recognition (Cote-Allard et al 2020, Zanghieri et al 2020), human-robot collaboration(Hanafusa and Ishikawa 2020), smartphone interaction(Cotton 2020) and virtual reality movement(Chiu et al 2019). There is…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

et al. 2022

View full text Add to dashboard Cite

Biosignal control is an interaction modality that allows users to interact with electronic devices by decoding the biological signals emanating from the movements or thoughts of the user. This manner of interaction with devices can enhance the sense of agency for users and enable persons suffering from a paralyzing condition to interact with everyday devices that would otherwise be challenging for them to use. It can also improve control of prosthetic devices and exoskeletons by making the interaction feel more natural and intuitive. However, with the current state of the art, several issues still need to be addressed to reliably decode user intent from biosignals and provide an improved user experience over other interaction modalities. One solution is to leverage advances in Deep Learning (DL) methods to provide more reliable decoding at the expense of added computational complexity. This scoping review introduces the basic concepts of DL and assists readers in deploying DL methods to a real-time control system that should operate under real-world conditions. The scope of this review covers any electronic device, but with an emphasis on robotic devices, as this is the most active area of research in biosignal control. We review the literature pertaining to the implementation and evaluation of control systems that incorporate DL to identify the main gaps and issues in the field, and formulate suggestions on how to mitigate them. Additionally, we formulate guidelines on the best approach to designing, implementing and evaluating research prototypes that use DL in their biosignal control systems.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

mentioning

confidence: 99%

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

et al. 2022

View full text Add to dashboard Cite

show abstract

“…7 After that, many researchers combined impedance control with intelligent control algorithm to ensure good control performance of robotic system in unstructured environment. such as adaptive impedance control, 8,9 fuzzy impedance control, 10,11 neural network impedance control, 12,13 learning impedance control 14,15 and so on.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy variable impedance-based adaptive neural network control in physical human–robot interaction

Liu

Chen

Zhu

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This article focus on the problems of trajectory tracking and motion constraint for physical human–robot interaction, and a compliant adaptive control method is proposed for stable and safe physical human–robot interaction during the interaction. First, a fuzzy variable impedance control strategy is given to make the robot to use suitable impedance parameters in different motion states, which can improve positioning accuracy and reduce the interaction force. Second, by transforming the safety interaction constraint into output constraint, a tan-type barrier Lyapunov function is presented to guarantee the safety of human partner in physical human–robot interaction. Third, an adaptive neural network is employed to design the adaptive controller to handle with the dynamic uncertainties and improve the robustness of the system. Finally, simulation results of a 2-degree-of-freedom manipulator are presented to show the effectiveness of the proposed method.

show abstract

Q-Learning-based model predictive variable impedance control for physical human-robot collaboration

Roveda

Testa

Shahid

et al. 2022

Artificial Intelligence

View full text Add to dashboard Cite

Human-Adaptive Impedance Control Using Recurrent Neural Network for Stability Recovery in Human-Robot Cooperation

Cited by 7 publications

References 25 publications

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

Fuzzy variable impedance-based adaptive neural network control in physical human–robot interaction

Q-Learning-based model predictive variable impedance control for physical human-robot collaboration

Contact Info

Product

Resources

About