What question did this study set out to answer?

To model collaborative robot dynamics during physical human–robot interaction and identify joint parameters using a physics-informed neural network without complex regressor formulation.

July 22, 2023Mechanism and Machine TheoryOpen Access

Collaborative robot dynamics with physical human–robot interaction and parameter identification with PINN

View Full Paper

Ask AI

Bookmark

Authors

XYXingyu YangZhengzhou University ZZZhengxue ZhouUniversity of Liverpool LLLeihui LiAarhus University

Discussion

Member takes

Implication

Experimental study demonstrates physics-informed parameter identification in collaborative robots, indicating enhanced safety and dynamic control during physical human–robot interaction.

Key Points

To model collaborative robot dynamics during physical human–robot interaction and identify joint parameters using a physics-informed neural network without complex regressor formulation.
Formulated a generic dynamic model for the quasi-static contact phase of physical human–robot interaction, integrating robot structural dynamics and contact dynamics.
Developed a hybrid physics-informed neural network (PINN) architecture combining a recurrent neural network (RNN) and the Runge–Kutta numerical method.
Collected dynamic contact data using a UR3e collaborative robot to train the network and validate system behavior.
The hybrid PINN successfully identified robot joint dynamic parameters directly from motion data without requiring prior physical knowledge or manual regressor construction.
Dynamic simulations incorporating the identified parameters showed strong agreement with real-world physical human–robot interaction experiments.

Cite This Study

Yang et al. (2023) studied this question.

synapsesocial.com/papers/6a0051a7e92f4a033c8542b2 https://doi.org/10.1016/j.mechmachtheory.2023.105439

View Full Paper

Ask AI

Bookmark

Implication

Experimental study demonstrates physics-informed parameter identification in collaborative robots, indicating enhanced safety and dynamic control during physical human–robot interaction.

Collaborative robot dynamics with physical human–robot interaction and parameter identification with PINN

Discussion

Member takes

Implication

Key Points

Cite This Study

Collaborative robot dynamics with physical human–robot interaction and parameter identification with PINN

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider