Sebastian Wrede

Jannick Stranghöner, Philipp Hartmann, Marco Braun et al.

High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.

Sebastian Baunsgaard, Sebastian B. Wrede, Pınar Tozun

Automatic Speech Recognition (ASR) has increased in popularity in recent years. The evolution of processor and storage technologies has enabled more advanced ASR mechanisms, fueling the development of virtual assistants such as Amazon Alexa, Apple Siri, Microsoft Cortana, and Google Home. The interest in such assistants, in turn, has amplified the novel developments in ASR research. However, despite this popularity, there has not been a detailed training efficiency analysis of modern ASR systems. This mainly stems from: the proprietary nature of many modern applications that depend on ASR, like the ones listed above; the relatively expensive co-processor hardware that is used to accelerate ASR by big vendors to enable such applications; and the absence of well-established benchmarks. The goal of this paper is to address the latter two of these challenges. The paper first describes an ASR model, based on a deep neural network inspired by recent work in this domain, and our experiences building it. Then we evaluate this model on three CPU-GPU co-processor platforms that represent different budget categories. Our results demonstrate that utilizing hardware acceleration yields good results even without high-end equipment. While the most expensive platform (10X price of the least expensive one) converges to the initial accuracy target 10-30% and 60-70% faster than the other two, the differences among the platforms almost disappear at slightly higher accuracy targets. In addition, our results further highlight both the difficulty of evaluating ASR systems due to the complex, long, and resource intensive nature of the model training in this domain, and the importance of establishing benchmarks for ASR.

Johannes Wienke, Sebastian Wrede

In January 2015 we distributed an online survey about failures in robotics and intelligent systems across robotics researchers. The aim of this survey was to find out which types of failures currently exist, what their origins are, and how systems are monitored and debugged - with a special focus on performance bugs. This report summarizes the findings of the survey.

Arne Nordmann, Sebastian Wrede

Model-driven software development is a promising way to cope with the complexity of system integration in advanced robotics, as it already demonstrated its benefits in domains with comparably challenging system integration requirements. This paper reports on work in progress in this area which aims to improve the research and experimentation process in a collaborative research project developing motor skill architectures for compliant robots. Our goal is to establish a model-driven development process throughout the project around a domain-specific language (DSL) facilitating the compact description of adaptive modular architectures for rich motor skills. Incorporating further languages for other aspects (e.g. mapping to a technical component architecture) the approach allows not only the formal description of motor skill architectures but also automated code-generation for experimentation on technical robot platforms. This paper reports on a first case study exemplifying how the developed AMARSi DSL helps to conceptualize different architectural approaches and to identify their similarities and differences.