Data-driven physical law learning model for chaotic robot dynamics prediction

Qian, Kui; Tian, Lei

doi:10.1007/s10489-021-02902-5

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep understanding of the dynamic characteristics of a manipulator robot is fundamental for practical robot applications. Many of these applications require, for example, effective trajectory tracking capacities that-to improve their performance-should consider a dynamic model of a manipulator robot [9][10][11]. Knowledge and modeling of a manipulator robot's dynamics are crucial for the optimal performance of its control strategies (based on the robot model), such as inverse dynamic control, calculated torque control, and model predictive control [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Automated Symbolic Processes for Dynamic Modeling of Redundant Manipulator Robots

Urrea,

Saa,

Kern

2024

Processes

View full text Add to dashboard Cite

In this study, groundbreaking software has been developed to automate the generation of equations of motion for manipulator robots with varying configurations and degrees of freedom (DoF). The implementation of three algorithms rooted in the Lagrange–Euler (L-E) formulation is achieved through the utilization of .m files in MATLAB R2020a software.This results in the derivation of a symbolic dynamic model for industrial manipulator robots. To comprehend the unique features and advantages of the developed software, dynamic simulations are conducted for two 6- and 9-DoF redundant manipulator robots as well as for a 3-DoF non-redundant manipulator robot equipped with prismatic and rotational joints, which is used to simplify the dynamic equations of the redundant prototypes. Notably, for the 6-DoF manipulator robot, model predictive control (MPC) is employed using insights gained from the dynamic model. This enables optimal control by predicting the future evolution of state variables: specifically, the values of the robot’s joint variables. The software is executed to model the dynamics of different types of robots, and the CPU time for a MacBook Pro with a 3 GHz Dual-Core Intel Core i7 processor is less than a minute. Ultimately, the theoretical findings are validated through response graphs and performance indicators of the MPC, affirming the accurate functionality of the developed software. The significance of this work lies in the automation of motion equation generation for manipulator robots, paving the way for enhanced control strategies and facilitating advancements in the field of robotics.

show abstract

Section: Introductionmentioning

confidence: 99%

Automated Symbolic Processes for Dynamic Modeling of Redundant Manipulator Robots

Urrea,

Saa,

Kern

2024

Processes

View full text Add to dashboard Cite

show abstract

Trajectory prediction based on conditional Hamiltonian generative network for incomplete observation image sequences

Qian

Tian

Song

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

The combination of Hamiltonian formalism and neural networks is playing an important role in dealing with chaotic systems. Aiming at the problem of motion control under the condition of unknown physical quantity and incomplete observation set, a trajectory prediction model based on conditional Hamiltonian generating network (CHGN) for incomplete observation image sequences is proposed. CHGN is composed of Conditional AutoEncoder (CVAE), Hamiltonian neural network (HNN) and Velocity–Verlet integrator. CVAE encoder converts the short-term continuous observation image sequence into target motion state features represented by generalized coordinates and generalized momentum, and generates the trajectory prediction image at the specified time. HNN is used to learn potential Hamiltonian physical quantities, so as to understand more chaotic system dynamics information to realize state cognition. Velocity–Verlet integrator predicts the motion state at any moment according to the Hamiltonian learned by HNN at the current moment. The motion state and the specified time are used as the input of CVAE decoder to generate the target prediction image from the potential motion space. Experimental results show that CHGN can accurately predict target trajectories over a long period of time based on incomplete short-term image sequences, and has better performance with minimum mean square error(MSE) on three physical system datasets than existing deep learning methods.

show abstract

Data-driven physical law learning model for chaotic robot dynamics prediction

Cited by 2 publications

References 34 publications

Automated Symbolic Processes for Dynamic Modeling of Redundant Manipulator Robots

Automated Symbolic Processes for Dynamic Modeling of Redundant Manipulator Robots

Trajectory prediction based on conditional Hamiltonian generative network for incomplete observation image sequences

Contact Info

Product

Resources

About