Open Dynamics Engine を用いたスノーボードロボットシミュレータの開発

We present a three-level cognitive system in a learning by demonstration context. The system allows for learning and transfer on the sensorimotor level as well as the planning level. The fundamentally different data structures associated with these two levels are connected by an efficient mid-level representation based on so-called “semantic event chains.” We describe details of the representations and quantify the effect of the associated learning procedures for each level under different amounts of noise. Moreover, we demonstrate the performance of the overall system by three demonstrations that have been performed at a project review. The described system has a technical readiness level (TRL) of 4, which in an ongoing follow-up project will be raised to TRL 6.

/pdf/teaching-a-robot-the-semantics-of-assembly-tasks-lvasv5rjk2.pdf

Teaching a Robot the Semantics of Assembly Tasks

An institution of engineers

Programming robotic assembly for industrial small-batch production is challenging; hence, it is vital to increase robustness and reduce development effort in order to achieve flexible robotic automation. A human who has made an assembly error will often simply undo the process until the error is undone and then restart the assembly. Conceptually, robots could do the same. This paper introduces a programming model that enables robot assembly programs to be executed in reverse. We investigate the challenges in running robot programs backwards and present a classification of reversibility characteristics. We demonstrate how temporarily switching the direction of program execution can be an efficient error recovery mechanism. Moreover, we demonstrate additional benefits arising from supporting reversibility in an assembly language, such as increased code reuse and automatically derived disassembly sequences. As a default approach to reversibility, we use program inversion and statement-level inversion of commands, but with a novel override option providing alternative sequences for asymmetric reverse actions. To efficiently program for this model, this paper introduces a new domain-specific language, SCP-RASQ (Simple C++ Reversible Assembly SeQuences). In initial experiments, where 200 consecutive assemblies of two industrial cases were performed, 18 of 22 errors were corrected automatically using only the trial-and-error capabilities that come from reverse execution.

/pdf/modelling-reversible-execution-of-robotic-assembly-4obqu6zfu9.pdf

Modelling reversible execution of robotic assembly

Motion analysis of a linear vibratory feeder: Dynamic modeling and experimental verification

Vibratory bowl feeders (VBFs) are a widely used option for industrial part feeding, but their design is still largely manual. A subtask of VBF design is determining an optimal parameter set for the passive devices, called traps, which the VBF uses to ensure correct part orientation. This paper proposes a fast and robust strategy for optimising traps, which makes use of dynamic simulation to efficiently evaluate the performance of parameter sets. The optimisation strategy is based on Bayesian Optimisation and selects new parameter sets to evaluate, using a modified Upper Confidence Bound with regression by Kernel Density Estimation as function estimator. The optimisation is run for four different traps with an industrial part and the best parameter sets are tested for robustness in simulation. The traps are then combined to create two sequences performing orientation of the parts and the designs are prototyped and tested on a real VBF.

Optimisation of Trap Design for Vibratory Bowl Feeders

Simulation of robotic tasks allows for cheap evaluation and process optimization, which can then be transferred to the physical system. To avoid discrepancies between physical execution and simulation, real-world process data can be fed back to the simulation environment, a concept referred to as a "Digital Twin". This requires the development of a software architecture, that supports Digital Twins for robot tasks.In this work, we propose a system where an operator can take apart a complex assembly, thus creating digitized assembly instructions. These instructions are then used to visually program the robot setup by blocks, which contain functionality ranging from point-to-point motions to high-level skills. These "Skillblocks" allow for a seamless transition between execution in the simulation environment and on the physical robot through interchangeable execution layers in the software architecture. The system also allows for feedback from a physical execution to be monitored in real-time and fed back to the simulation environment for processing.The aim of the system is to close the gap between digital and physical workcells when integrating robot solutions. This increases intuitiveness and allows for process monitoring and optimization through direct feedback to the digital model.

/pdf/towards-digital-twins-for-industrial-assembly-improving-4pn0hmx6e8.pdf

Towards Digital Twins for Industrial Assembly - Improving Robot Solutions by Intuitive User Guidance and Robot Programming

To support shifting to high mix/low volume production, manufacturers in high wage countries aim for robotizing their production operations – with a special focus on the late production phases, wher...

Towards robot cell matrices for agile production–SDU Robotics' assembly cell at the WRC 2018

Vibratory bowl feeders (VBF) are widely used in industry, but their design process is time consuming. This paper outlines an approach for the automatic design of such feeders, and utilizes rigid body simulation for evaluating design configurations. To ensure the applicability of the simulation, the paper makes an extensive evaluation in simulation and compares it to real world experiments. The experiments show similar overall characteristics, but also reveal differences which need to be considered when using simulation as a tool for design. Finally the paper illustrates the design process by optimizing the parameters of two devices used for the orienting of parts (often referred to as traps), and tests their configurations in the real world.

Configuration and validation of dynamic simulation for design of vibratory bowl feeders

Vibratory parts feeders with mechanical orienting devices are used extensively in the assembly automation industry. Even so, the design process is based on trial-and-error approaches and is largely manual. In this paper, a methodology is presented for automatic design of this type of feeder. The approach uses dynamic simulation for generating the necessary data for configuring a feeder with a sequence of mechanical orienting devices called traps, with the goal of reorienting all parts from a random to fixed orientation. Then, a fast algorithm for facilitating this configuration task automatically is developed from domain specific knowledge. Finally, the algorithm is validated on three industrial cases and its drawbacks and strengths are discussed in detail.

Simon Mathiesen

Papers

Optimisation of Trap Design for Vibratory Bowl Feeders

Towards Digital Twins for Industrial Assembly - Improving Robot Solutions by Intuitive User Guidance and Robot Programming

Towards robot cell matrices for agile production–SDU Robotics' assembly cell at the WRC 2018

Configuration and validation of dynamic simulation for design of vibratory bowl feeders

Automation Selection and Sequencing of Traps for Vibratory Feeders