Search results

Imitation learning is a powerful tool for planning the trajectory of robotic end-effectors in Cartesian space. Present methods can adapt the trajectory to the obstacle; however, the solutions may not always satisfy users, whereas it is hard for a nonexpert user to teach the robot to avoid obstacles in time as he/she wishes through demonstrations. This paper aims to address the above problem by proposing an approach that combines human supervision with the kernelized movement primitives (KMP) model.

This approach first extracts the reference database used to train KMP from demonstrations by using Gaussian mixture model and Gaussian mixture regression. Subsequently, KMP is used to modulate the trajectory of robotic end-effectors in real time based on feedback from its interaction with humans to avoid obstacles, which benefits from a novel reference database update strategy. The user can test different obstacle avoidance trajectories in the current task until a satisfactory solution is found.

Experiments performed with the KUKA cobot for obstacle avoidance show that this approach can adapt the trajectories of the robotic end-effector to the user’s wishes in real time, including trajectories that the robot has already passed and has not yet passed. Simulation comparisons also show that it exhibits better performance than KMP with the original reference database update strategy.

An interactive learning approach based on KMP is proposed and verified, which not only enables users to plan the trajectory of robotic end-effectors for obstacle avoidance more conveniently and efficiently but also provides an effective idea for accomplishing interactive learning tasks under constraints.

Running-in is a transient process prior to steady state and of great importance for mechanical performance. To reveal the fractal behavior in the running-in process, the steel-on-steel friction and wear tests were performed.

The friction coefficient, friction temperature, friction noise and vibration were recorded, and the surface profile of lower sample was measured on line. The signals and profiles were characterized by correlation dimension and box-counting dimension, respectively.

The signals have the consistent fractal evolvement law, that is, the correlation dimension increases and tends to a stable value. The box-counting dimension of one surface becomes close to that of the other surface. The running-in process can be interpreted as a process in which the fractal dimension of friction signals increases, and the counter surfaces spontaneously adapt to and modify each other to form a spatial ordered structure.

The results reveal the running-in behavior from a new perspective.

The purpose of this paper is to reveal the dynamic contact characteristics of the slip ring. Dynamic contact resistance models considering wear and self-excited were established based on fractal theory.

The effects of tangential velocity, stiffness and damping coefficient on dynamic contact resistance are studied. The relationships between fractal parameters, wear time and contact parameters are revealed.

The results show that the total contact area decreases with the friction coefficient and fractal roughness under the same load. Self-excited vibration occurs at a low speed (less than 0.6 m/s). It transforms from stick-slip motion at 0.4 m/s to pure sliding at 0.5 m/s. A high stiffness makes contact resistance fluctuate violently, while increasing the damping coefficient can suppress the self-excited vibration and reduce the dynamic contact resistance. The fractal contact resistance model considering wear is established based on the fractal parameters models. The validity of the model is verified by the wear tests.

The results have a great significance to study the electrical contact behavior of conductive slip ring.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-09-2023-0300/