This paper presents, for the first time, a method for learning in-contact tasks from a teleoperated demonstration with a hydraulic manipulator. Due to the use of extremely powerful hydraulic manipulator, a force-reflected bilateral teleoperation is the most reasonable method of giving a human demonstration. An advanced subsystem-dynamic-based control design framework, virtual decomposition control (VDC), is used to design a stability-guaranteed controller for the teleoperation system, while taking into account the full nonlinear dynamics of the master and slave manipulators. The use of fragile force/torque sensor at the tip of the hydraulic slave manipulator is avoided by estimating the contact forces from the manipulator actuators' chamber pressures. In the proposed learning method, it is observed that a surface-sliding tool has a friction-dependent range of directions (between the actual direction of motion and the contact force) from which the manipulator can apply force to produce the sliding motion. By this intuition, an intersection of these ranges can be taken over a motion to robustly find a desired direction for the motion from one or more demonstrations. The compliant axes required to reproduce the motion can be found by assuming that all motions outside the desired direction is caused by the environment, signalling the need for compliance. Finally, the learning method is incorporated to a novel VDC-based impedance control method to learn compliant behaviour from teleoperated human demonstrations. Experiments with 2-DOF hydraulic manipulator with a 475kg payload demonstrate the suitability and effectiveness of the proposed method to perform learning from demonstration (LfD) with heavy-duty hydraulic manipulators.

In this paper, a force-sensorless high-performance contact force/motion control approach is proposed for multiple-degree-of-freedom hydraulic manipulators. A rigorous stability proof for an entire hydraulic manipulator performing contact tasks is provided for the first time. The controller design for the manipulator is based on the recently introduced virtual decomposition control approach. As a significant novelty, the end-effector contact force is directly estimated from the manipulator's cylinder pressure data, which provides a practical solution for heavy-duty contact force control without engaging fragile force/torque sensors. In the experiments, the proposed controller achieved a force control accuracy of 4.1% at a desired contact force of 8000 N while in motion. This can be considered a significant result due to the hydraulic actuators' highly nonlinear behaviors, the coupled mechanical linkage dynamics, and the complex interaction dynamics between the manipulator and the environment.

Hydraulic actuators are well-known for their high power-to-weight ratio, rapid responses, compactness and reliable performance. However, one of the drawbacks of fluid power systems have been large energy losses. In this paper, our research objective is to develop both energy-efficient and high performance motion controller for heavy-duty hydraulic manipulators. We apply an unconventional Servo Meter-In Meter-Out (SMIMO) hydraulic valve control setup that is used to decouple hydraulic actuator load pressure level from load force to improve energy efficiency. The developed control system is based on the Virtual Decomposition Control (VDC) approach to guarantee the closed-loop system stability of the multi degree of freedom heavy-duty hydraulic crane driven by the proposed novel SMIMO VDC controller. Capability for approximately 42% lower energy consumption was achieved in the Cartesian motion trajectory experiments with the proposed novel controller compared with a conventional 4-way servo valve setup, without significant control performance deterioration.