Fotios Dimeas

Admittance neuro-control of a lifting device to reduce human effort

In this paper, two admittance-based control schemes for a power-assisted lifting device are presented. This device can be used to hoist a heavy object interactively for reducing the operator’s burden. The proposed system integrates an admittance controller with an inner control loop that regulates the velocity of the object. The admittance is the outer loop that establishes the desired relation between the applied force to the object and its velocity. For the adaptation to a variety of loads, an online learning controller is implemented based on a neural network (NN) with backpropagation training. The overfitting of the NN is resolved with weight decay to decrease the oscillations around the equilibrium point. Alternatively, a gain scheduling PID controller is designed for the inner loop, which measures the object weight and tunes the gains with predefined rules. The performance of these two adaptation methods is demonstrated on an experimental setup and the results illustrate that better generalization can be achieved with the NN.

Fuzzy learning variable admittance control for human-robot cooperation

This paper presents a method for variable admittance control in human-robot cooperation tasks, that combines a human-like decision making process and an adaptation algorithm. A Fuzzy Inference System is designed that relies on the measured velocity and the force applied by the operator to modify on-line the damping of the robot admittance, based on expert knowledge for intuitive cooperation. A Fuzzy Model Reference Learning Controller is used to adapt the Fuzzy Inference System according to the minimum jerk trajectory model. To evaluate the performance of the proposed controller a point-to-point cooperation task is conducted with multiple subjects using a KUKA LWR robot.

Reinforcement learning of variable admittance control for human-robot co-manipulation

In this paper, a variable admittance controller based on reinforcement learning is proposed for human-robot co-manipulation tasks. Setting as the goal of the reinforcement learning algorithm the minimisation of the jerk throughout a point-to-point movement, the proposed controller can learn the appropriate damping for effective cooperation without any prior knowledge of the target position or other task characteristics. The performance of the proposed variable admittance controller is investigated on a co-manipulation task with a number of subjects using a KUKA LWR robot, demonstrating considerable reduction both in the effort required by the operator and in the completion time of the task.

Human - robot collision detection and identification based on fuzzy and time series modelling

SUMMARY In this paper, two methods are proposed and implemented for collision detection between the robot and a human based on fuzzy identification and time series modelling. Both methods include a collision detection system for each joint of the robot that is trained to approximate the external torque. In addition, the proposed methods are able to detect the occurrence of a collision, the link that collided and to some extent the magnitude of the collision without using the explicit model of the robot. Since the speed of the detection is of critical importance for mitigating the danger, attention is paid to recognise a collision as soon as possible. Experimental results conducted with a KUKA LWR manipulator using two joints in planar motion, verify the validity on both methods.

Variable admittance control in pHRI using EMG-based arm muscles co-activation

In this paper, the co-activation level of the arm muscles is used as an indication of the end-point stiffness for improving human-robot cooperation. A variable admittance controller is proposed to adjust the virtual damping in real time by measuring the operators muscle activation by means of surface EMG. An experimental user study is conducted that simulates both high accuracy and fast transition movements, involving human-robot interaction with a 7-DOF LWR serial manipulator. The proposed method is compared to constant admittance and is evaluated in terms of movement accuracy, execution time, and the operators energy consumption. The results demonstrate that there is a significant reduction of the operators effort and an improvement of the cooperative motion accuracy.

Manipulator performance constraints in Cartesian admittance control for human-robot cooperation

This paper addresses the problem of providing feedback to the operator about the manipulators performance during human-robot physical interaction. A method is proposed that implements virtual constraints in Cartesian admittance control in order to prevent the operator from guiding the manipulator to low-performance configurations. The constraints are forces expressed in the Cartesian frame, which restrict the translation of the end-effector when the operator guides the robot below a certain performance threshold. These forces are calculated online by numerically approximating the gradient of the performance index with respect to the Cartesian frame attached to the end-effector. An experimental evaluation is conducted involving human-robot interaction with a 7-DOF LWR serial manipulator under Cartesian admittance control, using the kinematic manipulability index of the manipulator as the performance measure for singularity avoidance.

Design and fuzzy control of a robotic gripper for efficient strawberry harvesting

Strawberry is a very delicate fruit that requires special treatment during harvesting. A hierarchical control scheme is proposed based on a fuzzy controller for the force regulation of the gripper and proper grasping criteria, that can detect misplaced strawberries on the gripper or uneven distribution of forces. The design of the gripper and the controller are based on conducted experiments to measure the maximum gripping force and the required detachment force under a variety of detachment techniques. It is demonstrated that the hand motion for detaching the fruit from the stem has a significant role in the process because it can reduce the required force. By analysing those results a robotic gripper with pressure profile sensors is developed that demonstrates an efficiency comparable to the human hand for strawberry grasping. The designed gripper and fuzzy controller performance is tested with a considerable number of fresh fruits to demonstrate the effectiveness to the uncertainties of strawberry grasping.

Contact distinction in human-robot cooperation with admittance control

The emerging field of physical human-robot interaction raises the need to distinguish collisions over intended contacts in order to guarantee safe and seamless interaction. In this paper, a novel contact distinction method is proposed that monitors the externally applied forces/torques and is able to distinguish unexpected collisions from intended contacts during cooperative tasks. The method is based on a frequency domain analysis of the externally applied forces using the Fast Fourier Transform. Moreover, a tuning method is proposed to adjust the thresholds for the detection, according to the desired dynamic behavior of the admittance controller. The collision distinction method is evaluated experimentally in a human-robot cooperation task with multiple subjects using a 7DOF LWR manipulator.