Quick Setup of Force-Controlled Industrial Gluing Tasks Using Learning From Demonstration

This paper presents a framework for programming in-contact tasks using learning by demonstration. The framework is demonstrated on an industrial gluing task, showing that a high quality robot behavior can be programmed using a single demonstration. A unified controller structure is proposed for the demonstration and execution of in-contact tasks that eases the transition from admittance controller for demonstration to parallel force/position control for the execution. The proposed controller is adapted according to the geometry of the task constraints, which is estimated online during the demonstration. In addition, the controller gains are adapted to the human behavior during demonstration to improve the quality of the demonstration. The considered gluing task requires the robot to alternate between free motion and in-contact motion; hence, an approach for minimizing contact forces during the switching between the two situations is presented. We evaluate our proposed system in a series of experiments, where we show that we are able to estimate the geometry of a curved surface, that our adaptive controller for demonstration allows users to achieve higher accuracy in a shorter demonstration duration when compared to an off-the-shelf controller for teaching implemented on a collaborative robot, and that our execution controller is able to reduce impact forces and apply a constant process force while adapting to the surface geometry.

Quality of surface geostatistical parameter reproduction for laser profilometers

The description of the surface topography of building structures is important for contact tasks, bond strength and rheological processes monitoring. The determination of surface parameters is carried out using increasingly sophisticated methods and techniques, such as laser profilometer, laser scanner, confocal microscope or short range photogrammetry. The research is aimed at evaluating the mobile surface test device for quality control and failure prevention, also the authors have addressed the possibility of using inexpensive profile measuring laser equipment to obtain a geostatistical description of the surface parametrics. It is the support of creation of new measurement apparatus that is the impetus for this work for the selection of optimal laser device. It is possible to deduce from the paper how the density of measurements taken and the accuracy of height estimation in the profile affect the parameters of the semivariogram model. With the proper choice of device it is easier correctly estimate the strength parameters of the joint of concrete or soil-concrete structures. The relevance of the correctly performed measurement is proved by the link between the strength parameters of the contact surfaces and its geostatistical description. In order to assess the quality of the mapping, a spherical theoretical model with a corresponding generated surface was used as a reference. The measuring laser devices with various mapping accuracy and depth measurement precision were tested, also for description fractal dimension of results. The measurement accuracy of the depth parameter has the greatest influence for determination of the remaining parameters of the surface roughness.

Design of a Planar Cable-Driven Parallel Robot for Non-Contact Tasks

Cable-driven parallel robots offer significant advantages in terms of workspace dimensions and payload capability. Their mechanical structure and transmission system consist of light and extendable cables that can withstand high tensile loads. Cables are wound and unwound by a set of motorized winches, so that the robot workspace dimensions mainly depend on the amount of cable that each drum can store. For this reason, these manipulators are attractive for many industrial tasks to be performed on a large scale, such as handling, pick-and-place, and manufacturing, without a substantial increase in costs and mechanical complexity with respect to a small-scale application. This paper presents the design of a planar overconstrained cable-driven parallel robot for quasi-static non-contact operations on planar vertical surfaces, such as laser engraving, inspection and thermal treatment. The overall mechanical structure of the robot is shown, by focusing on the actuation and guidance systems. A novel concept of the cable guidance system is outlined, which allows for a simple kinematic model to control the manipulator. As an application example, a laser diode is mounted onto the end-effector of a prototype to perform laser engraving on a paper sheet. Observations on the experiments are reported and discussed.

Imitation learning-based framework for learning 6-D linear compliant motions

We present a novel method for learning from demonstration 6-D tasks that can be modeled as a sequence of linear motions and compliances. The focus of this paper is the learning of a single linear primitive, many of which can be sequenced to perform more complex tasks. The presented method learns from demonstrations how to take advantage of mechanical gradients in in-contact tasks, such as assembly, both for translations and rotations, without any prior information. The method assumes there exists a desired linear direction in 6-D which, if followed by the manipulator, leads the robot’s end-effector to the goal area shown in the demonstration, either in free space or by leveraging contact through compliance. First, demonstrations are gathered where the teacher explicitly shows the robot how the mechanical gradients can be used as guidance towards the goal. From the demonstrations, a set of directions is computed which would result in the observed motion at each timestep during a demonstration of a single primitive. By observing which direction is included in all these sets, we find a single desired direction which can reproduce the demonstrated motion. Finding the number of compliant axes and their directions in both rotation and translation is based on the assumption that in the presence of a desired direction of motion, all other observed motion is caused by the contact force of the environment, signalling the need for compliance. We evaluate the method on a KUKA LWR4+ robot with test setups imitating typical tasks where a human would use compliance to cope with positional uncertainty. Results show that the method can successfully learn and reproduce compliant motions by taking advantage of the geometry of the task, therefore reducing the need for localization accuracy.

Development and Application of a Tandem Force Sensor

In robot teaching for contact tasks, it is necessary to not only accurately perceive the traction force exerted by hands, but also to perceive the contact force at the robot end. This paper develops a tandem force sensor to detect traction and contact forces. As a component of the tandem force sensor, a cylindrical traction force sensor is developed to detect the traction force applied by hands. Its structure is designed to be suitable for humans to operate, and the mechanical model of its cylinder-shaped elastic structural body has been analyzed. After calibration, the cylindrical traction force sensor is proven to be able to detect forces/moments with small errors. Then, a tandem force sensor is developed based on the developed cylindrical traction force sensor and a wrist force sensor. The robot teaching experiment of drawer switches were made and the results confirm that the developed traction force sensor is simple to operate and the tandem force sensor can achieve the perception of the traction and contact forces.