Online Learning Control of Hydraulic Excavators Based on Echo-State Networks

Park, Jaemann; Lee, Bong Ju; Kang, Seonhyeok; Kim, Pan Young; Kim, H. Jin

doi:10.1109/tase.2016.2582213

Cited by 55 publications

(31 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inequality constraint to avoid exceeding the maximum flow is AE(q)u d ≤ Q max (12) with E(q) being the joint position dependent transformation from joint velocities to piston velocities.…”

Section: A Hierarchical Optimization Inverse Kinematic Arm Controllermentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Free-Form Trenching Using a Walking Excavator

Jud

Leemann

Kerscher

et al. 2019

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

This article shows accurate and autonomous creation of free-form trenches using a walking excavator. We present hardware extensions and modifications for full automation, a mapping approach specifically tailored to excavation, environment collision-free trajectory planning on these maps, an arm controller aware of various limits and an improved state machine that enables the execution on real hardware. Furthermore, previous work about excavation planning and the design of a single soil-independent dig cycle is extended and transferred from simulation to hardware. The entire system is tested on a foursegment, piecewise-planar trench and a free-form curved trench. Both shapes were successfully excavated with unprecedented accuracy.

show abstract

Section: A Hierarchical Optimization Inverse Kinematic Arm Controllermentioning

confidence: 99%

“…Regarding control, Maeda et al [11] used iterative learning control to predict the disturbance in the next dig cycle. No dynamic model in the conventional sense is used by Park et al [12]. Instead, the dynamics are learned online with an echo state network and used to track a position trajectory.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Free-Form Trenching Using a Walking Excavator

Jud

Leemann

Kerscher

et al. 2019

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Fluid power, a technical field involving hydraulics and pneumatics technologies, is widely used in various applications, such as heavy industrial equipment in factories , robotics , construction machines , and lifting and handling machine . Both technologies use fluid, hydraulic oil or pressured gas, for transmitting power from one place with high‐pressure or higher energy levels to other locations and for carrying out specific actions in actuators.…”

Section: Introductionmentioning

confidence: 99%

Super‐Twisting Observer‐Based Integral Sliding Mode Control for Tracking the Rapid Acceleration of a Piston in a Hybrid Electro‐Hydraulic and Pneumatic System

Hoang

Lee

Dugarjav

2018

Asian Journal of Control

View full text Add to dashboard Cite

A new hybrid electro-hydraulic and pneumatic actuator system and its dynamic model for high-performance control are presented. This work focuses on tracking control of rapidly changing acceleration that is an advanced area with various practical applications in industries. The impact motion control of the actuator is one of challenging task due to the system instability during the transition state. Since composite disturbances derived from the inaccurate and unmodeled dynamics considerably reduce the control performance. A novel structure of variable integral sliding mode controls integrated with a sliding mode disturbance observer is proposed based on the super-twisting algorithm. With the control strategy, not only does the controller overcome the extreme sensitivity of the system during rapid movements, but it also eliminates the internal parameter uncertainties and external load disturbance while tracking rapid gain-scheduled acceleration. The results of the numerical simulation and field experiment are presented to assess the effectiveness of the proposed control scheme.

show abstract

“…However, for an excavator, it is difficult to obtain a useful nominal model for controller design due to the following reasons: 1,2,[12][13][14][15] (1) accurate characteristic parameters for proportional directional valves are hard to obtain due to the nonlinear flow gain, hysteresis, dead zone, saturation, and the complex dynamic flow coupling; (2) change in work temperature, aging of hydraulic components, and wear of the mechanical part will result in variations in system parameters; and (3) there is a complex interaction between the excavator and the environment, and even worse, the unknown interaction force often varies in a broad range. Therefore, all aforementioned nominal-model-based methods [4][5][6][7][8][9][10][11][12] are not suitable for hydraulic excavators.…”

Section: Introductionmentioning

confidence: 99%

“…Based on adaptive inverse control theory, adaptive neural inverse control methods have been developed and applied to hydraulic systems. [15][16][17] The input and output signals of the plant were used to learn an inverse model with an online-updated neural network, which meant no explicit knowledge of the plant dynamics was required. To improve control performance, neural-network-based proportional-integral-derivative (PID) control approaches were also developed for hydraulic systems.…”

Section: Introductionmentioning

confidence: 99%

Adaptive neural finite-time trajectory tracking control of hydraulic excavators

Wang

2018

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This article is focused on the high-performance trajectory tracking control of single actuator of a hydraulic excavator. A novel adaptive neural finite-time controller without tedious offline parameter identification and the complex backstepping scheme is put forward. By employing a coordinate transform, the original system can be represented in a canonical form. Consequently, the control objective is retained by controlling the transformed system, which allows a simple controller design without using backstepping. To estimate the immeasurable states of the transformed system, a high-order sliding mode observer is employed, of which observation error is guaranteed to be bounded in finite time. To guarantee finite-time trajectory tracking performance, an adaptive neural finite-time controller based on neural network approximation and terminal sliding mode theory is synthesized. During its synthesis, an echo state network is used to approximate the lumped uncertain system functions, and it guarantees an improved approximation with online-updated output weights. Besides, to handle the lumped uncertain nonlinearities resulting from observation error and neural approximation error, a robust term is employed. The influences of the uncertain nonlinearities are restrained with a novel parameter adaption law, which estimates and updates the upper bound of the lumped uncertain nonlinearities online. With this novel controller, the finite-time trajectory tracking error convergence is proved theoretically. The superior performance and the practical applicability of the proposed method are verified by comparative simulations and experiments.

show abstract

Online Learning Control of Hydraulic Excavators Based on Echo-State Networks

Cited by 55 publications

References 34 publications

Autonomous Free-Form Trenching Using a Walking Excavator

Autonomous Free-Form Trenching Using a Walking Excavator

Super‐Twisting Observer‐Based Integral Sliding Mode Control for Tracking the Rapid Acceleration of a Piston in a Hybrid Electro‐Hydraulic and Pneumatic System

Adaptive neural finite-time trajectory tracking control of hydraulic excavators

Contact Info

Product

Resources

About