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

Abstract

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.

Programming Fine Manufacturing Tasks on Collaborative Robots: A Case Study on Industrial Gluing

“…In Iturrate et al (2021), a LfD-based framework is proposed for programming and executing industrial gluing tasks, e.g. applying glue to PCBs.…”

“…applying glue to PCBs. In contrast to Nemec et al (2018), this approach uses only a single demonstration of a given task and instead of incremental refinement of the trajectory during execution, Iturrate et al (2021) support the operator during kinesthetic teaching with an admittance controller with time-varying damping. To assist the operator in demonstrating a task, the authors estimate the surface normal of the workpiece to adjust the damping during kinesthetic teaching such as to maintain a higher damping in the direction constrained by the workpiece and lower damping in the non-constrained directions.…”

No-code robotic programming for agile production: A new markerless-approach for multimodal natural interaction in a human-robot collaboration context

“…In recent years, hand-guiding controls have been implemented in many industrial applications, e.g. robotic gluing ( Iturrate et al (2021) ), assembly ( Liu et al (2021) ), polishing ( Kana et al (2021) ), welding ( Zhang et al (2019) ), surface cleaning ( Elliott et al (2017) ), Pick-and-Place or manipulation ( Peng et al (2018) ). Despite the ease of hand-guiding teaching methods, these hand-guiding demands medium to high physical workload to move the robot joints.…”

Learning from Demonstrations in Human–Robot Collaborative Scenarios: A Survey

“…Simultaneous control of force and position for teaching and execution is physically impossible. To tackle this problem, Iturrate et al [60] proposed an adaptive controller architecture that can learn continuous kinematic and dynamic task constraint from a single demonstration. The task kinematics were encoded as DMPs, while the dynamics of the task were preserved by encoding the output of the normal estimator during demonstration as Radial Basis Functions (RBFs) synchronized with the DMPs.…”

“…Similar achievements are presented in [67,85] for pushing-like skills such as sweeping and peg-in-hole assemblies, the robot execution was proven to be better compared to only following the motion trajectory. Another example can be found in [60], where the force modeling consideration not only produces better execution, but also helps during the demonstration phase to provide a better user experience during Kineasthetic teaching. Skill/task interaction force modeling is far more important in collaborative interactions between human and robots.…”