arXiv subjects

Christian Rauch

Publications and source records attributed to Christian Rauch.

14 recordsLinked to original sources

arXiv2026

SteelDS: A High-Resolution Video Dataset of E40 Steel Scrap for Object Detection and Instance Segmentation

This dataset provides high-resolution, annotated video sequences of shredded E40-grade steel and copper scrap on a conveyor belt. Captured in a controlled laboratory environment, the data reflects the industrial post-magnetic sorting stage, where manual intervention is typically required to remove copper contaminants. The dataset comprises 24,297 labeled frames across five subsets, featuring 396 steel and 101 copper objects categorized by size. It supports the development of machine learning models for material classification, object detection, and instance segmentation. Variations in object spacing and density are included to simulate realistic industrial sorting conditions. Ground truth annotations include pixel-wise segmentation masks and material classes. This dataset serves as a benchmark for evaluating automated sorting algorithms aiming to identify copper impurities within complex, heterogeneous steel scrap streams.

cs.RO↗

arXiv2026

PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation

Detecting unseen anomalies in unstructured environments presents a critical challenge for industrial and agricultural applications such as material recycling and weeding. Existing perception systems frequently fail to satisfy the strict operational requirements of these domains, specifically real-time processing, pixel-level segmentation precision, and robust accuracy, due to their reliance on exhaustively annotated datasets. To address these limitations, we propose a weakly supervised pipeline for object segmentation and classification using weak image-level supervision called 'Patch Aggregation for Segmentation of Targets and Anomalies' (PASTA). By comparing an observed scene with a nominal reference, PASTA identifies Target and Anomaly objects through distribution analysis in self-supervised Vision Transformer (ViT) feature spaces. Our pipeline utilizes semantic text-prompts via the Segment Anything Model 3 to guide zero-shot object segmentation. Evaluations on a custom steel scrap recycling dataset and a plant dataset demonstrate a 75.8% training time reduction of our approach to domain-specific baselines. While being domain-agnostic, our method achieves superior Target (up to 88.3% IoU) and Anomaly (up to 63.5% IoU) segmentation performance in the industrial and agricultural domain.

cs.CV↗

arXiv2025

SIL: Symbiotic Interactive Learning for Language-Conditioned Human-Agent Co-Adaptation

Today's autonomous agents, largely driven by foundation models (FMs), can understand natural language instructions and solve long-horizon tasks with human-like reasoning. However, current human-robot interaction frameworks largely follow a one-way master-apprentice technique where the embodied agent passively executes commands without reciprocal learning. This neglects the co-adaptive, multi-turn nature of everyday human-to-human interactions. We introduce symbiotic interactive learning (SIL), a bidirectional co-adaptation framework in a shared latent task space, where both the human and the agent maintain joint belief states that evolve with the interaction history. This enables proactive clarification, adaptive suggestions, and shared plan refinement. SIL leverages FMs for spatial perception and reasoning, together with a triplet-loss-trained neural encoder that grounds the FMs' outputs into task-specific latent representations. To support long-term stability as tasks evolve, SIL utilises episodic and semantic memory architectures, regularised via elastic weight consolidation to mitigate catastrophic forgetting. We evaluate SIL on simulated and real-world embodied tasks, including instruction following, information retrieval, query-oriented reasoning, and interactive dialogue, achieving a $90.4\%$ task completion rate and a belief alignment score of $\rho \approx 0.83$, an absolute improvement of about $20$ percentage points over the best ablations. Demos and resources: https://linusnep.github.io/SIL/.

cs.RO↗

arXiv2025

Real-Time 3D Vision-Language Embedding Mapping

A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time. We combine a local embedding masking strategy, for a more distinct embedding distribution, with a confidence-weighted 3D integration for more reliable 3D embeddings. The resulting metric-accurate embedding representation is task-agnostic and can represent semantic concepts on a global multi-room, as well as on a local object-level. This enables a variety of interactive robotic applications that require the localisation of objects-of-interest via natural language. We evaluate our approach on a variety of real-world sequences and demonstrate that these strategies achieve a more accurate object-of-interest localisation while improving the runtime performance in order to meet our real-time constraints. We further demonstrate the versatility of our approach in a variety of interactive handheld, mobile robotics and manipulation tasks, requiring only raw image data.

cs.RO↗

arXiv2023

On Minimal Pumping Constants for Regular Languages

The study of the operational complexity of minimal pumping constants started in [J. DASSOW and I. JECKER. Operational complexity and pumping lemmas. Acta Inform., 59:337-355, 2022], where an almost complete picture of the operational complexity of minimal pumping constants for two different variants of pumping lemmata from the literature was given. We continue this research by considering a pumping lemma for regular languages that allows pumping of sub-words at any position of the considered word, if the sub-word is long enough [S. J. SAVITCH. Abstract Machines and Grammars. 1982]. First we improve on the simultaneous regulation of minimal pumping constants induced by different pumping lemmata including Savitch's pumping lemma. In this way we are able to simultaneously regulate four different minimal pumping constants. This is a novel result in the field of descriptional complexity. Moreover, for Savitch's pumping lemma we are able to completely classify the range of the minimal pumping constant for the operations Kleene star, reversal, complement, prefix- and suffix-closure, union, set-subtraction, concatenation, intersection, and symmetric difference. In this way, we also solve some of the open problems from the paper that initiated the study of the operational complexity of minimal pumping constants mentioned above.

cs.FL↗

arXiv2023

RGB-D-Inertial SLAM in Indoor Dynamic Environments with Long-term Large Occlusion

This work presents a novel RGB-D-inertial dynamic SLAM method that can enable accurate localisation when the majority of the camera view is occluded by multiple dynamic objects over a long period of time. Most dynamic SLAM approaches either remove dynamic objects as outliers when they account for a minor proportion of the visual input, or detect dynamic objects using semantic segmentation before camera tracking. Therefore, dynamic objects that cause large occlusions are difficult to detect without prior information. The remaining visual information from the static background is also not enough to support localisation when large occlusion lasts for a long period. To overcome these problems, our framework presents a robust visual-inertial bundle adjustment that simultaneously tracks camera, estimates cluster-wise dense segmentation of dynamic objects and maintains a static sparse map by combining dense and sparse features. The experiment results demonstrate that our method achieves promising localisation and object segmentation performance compared to other state-of-the-art methods in the scenario of long-term large occlusion.

cs.RO↗

arXiv2022

RGB-D SLAM in Indoor Planar Environments with Multiple Large Dynamic Objects

This work presents a novel dense RGB-D SLAM approach for dynamic planar environments that enables simultaneous multi-object tracking, camera localisation and background reconstruction. Previous dynamic SLAM methods either rely on semantic segmentation to directly detect dynamic objects; or assume that dynamic objects occupy a smaller proportion of the camera view than the static background and can, therefore, be removed as outliers. Our approach, however, enables dense SLAM when the camera view is largely occluded by multiple dynamic objects with the aid of camera motion prior. The dynamic planar objects are separated by their different rigid motions and tracked independently. The remaining dynamic non-planar areas are removed as outliers and not mapped into the background. The evaluation demonstrates that our approach outperforms the state-of-the-art methods in terms of localisation, mapping, dynamic segmentation and object tracking. We also demonstrate its robustness to large drift in the camera motion prior.

cs.RO↗

arXiv2022

ROS-PyBullet Interface: A Framework for Reliable Contact Simulation and Human-Robot Interaction

Reliable contact simulation plays a key role in the development of (semi-)autonomous robots, especially when dealing with contact-rich manipulation scenarios, an active robotics research topic. Besides simulation, components such as sensing, perception, data collection, robot hardware control, human interfaces, etc. are all key enablers towards applying machine learning algorithms or model-based approaches in real world systems. However, there is a lack of software connecting reliable contact simulation with the larger robotics ecosystem (i.e. ROS, Orocos), for a more seamless application of novel approaches, found in the literature, to existing robotic hardware. In this paper, we present the ROS-PyBullet Interface, a framework that provides a bridge between the reliable contact/impact simulator PyBullet and the Robot Operating System (ROS). Furthermore, we provide additional utilities for facilitating Human-Robot Interaction (HRI) in the simulated environment. We also present several use-cases that highlight the capabilities and usefulness of our framework. Please check our video, source code, and examples included in the supplementary material. Our full code base is open source and can be found at https://github.com/cmower/ros_pybullet_interface.

cs.RO↗

arXiv2022

On the Accepting State Complexity of Operations on Permutation Automata

We investigate the accepting state complexity of deterministic finite automata for regular languages obtained by applying one of the following operations to languages accepted by permutation automata: union, quotient, complement, difference, intersection, Kleene star, Kleene plus, and reversal. The paper thus joins the study of accepting state complexity of regularity preserving language operations which was initiated by the work [J. Dassow: On the number of accepting states of finite automata, J. Autom., Lang. Comb., 21, 2016]. We show that for almost all of the operations, except for reversal and quotient, there is no difference in the accepting state complexity for permutation automata compared to deterministic finite automata in general. For both reversal and quotient we prove that certain accepting state complexities cannot be obtained; these number are called "magic" in the literature. Moreover, we solve the left open accepting state complexity problem for the intersection of unary languages accepted by permutation automata and deterministic finite automata in general.

cs.FL↗

arXiv2022

Sparse-Dense Motion Modelling and Tracking for Manipulation without Prior Object Models

This work presents an approach for modelling and tracking previously unseen objects for robotic grasping tasks. Using the motion of objects in a scene, our approach segments rigid entities from the scene and continuously tracks them to create a dense and sparse model of the object and the environment. While the dense tracking enables interaction with these models, the sparse tracking makes this robust against fast movements and allows to redetect already modelled objects. The evaluation on a dual-arm grasping task demonstrates that our approach 1) enables a robot to detect new objects online without a prior model and to grasp these objects using only a simple parameterisable geometric representation, and 2) is much more robust compared to the state of the art methods.

cs.RO↗

arXiv2021

RigidFusion: Robot Localisation and Mapping in Environments with Large Dynamic Rigid Objects

This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. Previous approaches treat dynamic parts of a scene as outliers and are thus limited to a small amount of changes in the scene, or rely on prior information for all objects in the scene to enable robust camera tracking. Here, we propose to treat all dynamic parts as one rigid body and simultaneously segment and track both static and dynamic components. We, therefore, enable simultaneous localisation and reconstruction of both the static background and rigid dynamic components in environments where dynamic objects cause large occlusion. We evaluate our approach on multiple challenging scenes with large dynamic occlusion. The evaluation demonstrates that our approach achieves better motion segmentation, localisation and mapping without requiring prior knowledge of the dynamic object's shape and appearance.

cs.RO↗

arXiv2011

Defect evolution and interplay in n-type InN

The nature and interplay of intrinsic point and extended defects in n-type Si-doped InN epilayers with free carrier concentrations up to 6.6x10E20cm-3 are studied using positron annihilation spectroscopy and transmission electron microscopy and compared to results from undoped irradiated films. In as-grown Si-doped samples, V_In-V_N complexes are the dominant III-sublattice related vacancy defects. Enhanced formation of larger V_In-mV_N clusters is observed at the interface, which speaks for high concentrations of additional V_N in the near-interface region and coincides with an increase in the density of screw and edge type dislocations in that area.

cond-mat.mtrl-sci↗

arXiv2011

Tracking defect-induced ferromagnetism in GaN:Gd

We report on the magnetic properties of GaN:Gd layers grown by molecular beam epitaxy (MBE). A poor reproducibility with respect to the magnetic properties is found in these samples. Our results show strong indications that defects with a concentration of the order of 10^19 cm^-3 might play an important role for the magnetic properties. Positron annihilation spectroscopy does not support the suggested connection between the ferromagnetism and the Ga vacancy in GaN:Gd. Oxygen co-doping of GaN:Gd promotes ferromagnetism at room temperature and points to a role of oxygen for mediating ferromagnetic interactions in Gd doped GaN.

cond-mat.mtrl-sci↗

arXiv2011

Identifying vacancy complexes in compound semiconductors with positron annihilation spectroscopy: a case study of InN

We present a comprehensive study of vacancy and vacancy-impurity complexes in InN combining positron annihilation spectroscopy and ab-initio calculations. Positron densities and annihilation characteristics of common vacancy-type defects are calculated using density functional theory and the feasibility of their experimental detection and distinction with positron annihilation methods is discussed. The computational results are compared to positron lifetime and conventional as well as coincidence Doppler broadening measurements of several representative InN samples. The particular dominant vacancy-type positron traps are identified and their characteristic positron lifetimes, Doppler ratio curves and lineshape parameters determined. We find that In vacancies and their complexes with N vacancies or impurities act as efficient positron traps, inducing distinct changes in the annihilation parameters compared to the InN lattice. Neutral or positively charged N vacancies and pure N vacancy complexes on the other hand do not trap positrons. The predominantly introduced positron trap in irradiated InN is identified as the isolated In vacancy, while in as-grown InN layers In vacancies do not occur isolated but complexed with one or more N vacancies. The number of N vacancies per In vacancy in these complexes is found to increase from the near surface region towards the layer-substrate interface.

cond-mat.mtrl-sci↗