Arne Roennau

David Oberacker, Julia Richter, Philip Arm et al.

Mobile robots have become indispensable for exploring hostile environments, such as in space or disaster relief scenarios, but often remain limited to teleoperation by a human operator. This restricts the deployment scale and requires near-continuous low-latency communication between the operator and the robot. We present MOSAIC: a scalable autonomy framework for multi-robot scientific exploration using a unified mission abstraction based on Points of Interest (POIs) and multiple layers of autonomy, enabling supervision by a single operator. The framework dynamically allocates exploration and measurement tasks based on each robot's capabilities, leveraging team-level redundancy and specialization to enable continuous operation. We validated the framework in a space-analog field experiment emulating a lunar prospecting scenario, involving a heterogeneous team of five robots and a single operator. Despite the complete failure of one robot during the mission, the team completed 82.3% of assigned tasks at an Autonomy Ratio of 86%, while the operator workload remained at only 78.2%. These results demonstrate that the proposed framework enables robust, scalable multi-robot scientific exploration with limited operator intervention. We further derive practical lessons learned in robot interoperability, networking architecture, team composition, and operator workload management to inform future multi-robot exploration missions.

Lea Steffen, Tobias Weyer, Katharina Glueck et al.

Motion planning in the configuration space (C-space) induces benefits, such as smooth trajectories. It becomes more complex as the degrees of freedom (DOF) increase. This is due to the direct relation between the dimensionality of the search space and the DOF. Self-organizing neural networks (SONN) and their famous candidate, the Self-Organizing Map, have been proven to be useful tools for C-space reduction while preserving its underlying topology, as presented in [29]. In this work, we extend our previous study with additional models and adapt the approach from human motion data towards robots' kinematics. The evaluation includes the best performant models from [29] and three additional SONN architectures, representing the consequent continuation of this previous work. Generated Trajectories, planned with the different SONN models, were successfully tested in a robot simulation.

Stefan Scherzinger, Arne Roennau, Rüdiger Dillmann

The programming of robotic assembly tasks is a key component in manufacturing and automation. Force-sensitive assembly, however, often requires reactive strategies to handle slight changes in positioning and unforeseen part jamming. Learning such strategies from human performance is a promising approach, but faces two common challenges: the handling of low part clearances which is difficult to capture from demonstrations and learning intuitive strategies offline without access to the real hardware. We address these two challenges by learning probabilistic force strategies from data that are easily acquired offline in a robot-less simulation from human demonstrations with a joystick. We combine a Long Short Term Memory (LSTM) and a Mixture Density Network (MDN) to model human-inspired behavior in such a way that the learned strategies transfer easily onto real hardware. The experiments show a UR10e robot that completes a plastic assembly with clearances of less than 100 micrometers whose strategies were solely demonstrated in simulation.

Julia Richter, David Oberacker, Gabriela Ligeza et al.

Robotic prospecting for critical resources on the Moon, such as ilmenite, rare earth elements, and water ice, requires robust exploration methods given the diverse terrain and harsh environmental conditions. Although numerous analog field trials address these goals, comparing their results remains challenging because of differences in robot platforms and experimental setups. These missions typically assess performance using selected, scenario-specific engineering metrics that fail to establish a clear link between field performance and science-driven objectives. In this paper, we address this gap by deriving a structured framework of KPI from three realistic multi-robot lunar scenarios reflecting scientific objectives and operational constraints. Our framework emphasizes scenario-dependent priorities in efficiency, robustness, and precision, and is explicitly designed for practical applicability in field deployments. We validated the framework in a multi-robot field test and found it practical and easy to apply for efficiency- and robustness-related KPI, whereas precision-oriented KPI require reliable ground-truth data that is not always feasible to obtain in outdoor analog environments. Overall, we propose this framework as a common evaluation standard enabling consistent, goal-oriented comparison of multi-robot field trials and supporting systematic development of robotic systems for future planetary exploration.

Lea Steffen, Thomas Trapp, Arne Roennau et al.

As intelligent systems become increasingly important in our daily lives, new ways of interaction are needed. Classical user interfaces pose issues for the physically impaired and are partially not practical or convenient. Gesture recognition is an alternative, but often not reactive enough when conventional cameras are used. This work proposes a Spiking Convolutional Neural Network, processing event- and depth data for gesture recognition. The network is simulated using the open-source neuromorphic computing framework LAVA for offline training and evaluation on an embedded system. For the evaluation three open source data sets are used. Since these do not represent the applied bi-modality, a new data set with synchronized event- and depth data was recorded. The results show the viability of temporal encoding on depth information and modality fusion, even on differently encoded data, to be beneficial to network performance and generalization capabilities.

Stefan Scherzinger, Pascal Becker, Arne Roennau et al.

Assistive robotic manipulators are becoming increasingly important for people with disabilities. Teleoperating the manipulator in mundane tasks is part of their daily lives. Instead of steering the robot through all actions, applying self-recorded motion macros could greatly facilitate repetitive tasks. Dynamic Movement Primitives (DMP) are a powerful method for skill learning via teleoperation. For this use case, however, they need simple heuristics to specify where to start, stop, and parameterize a skill without a background in computer science and academic sensor setups for autonomous perception. To achieve this goal, this paper provides the concept of local, global, and hybrid skills that form a modular basis for composing single-handed tasks of daily living. These skills are specified implicitly and can easily be programmed by users themselves, requiring only their basic robotic manipulator. The paper contributes all details for robot-agnostic implementations. Experiments validate the developed methods for exemplary tasks, such as scratching an itchy spot, sorting objects on a desk, and feeding a piggy bank with coins. The paper is accompanied by an open-source implementation at https://github.com/fzi-forschungszentrum-informatik/ArNe

David Oberacker, Meike Deitersen, Niklas Spielbauer et al.

Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed multi-layer world model capturing the complex relations of its surroundings. Hierarchical 3D scene graphs address this challenge by integrating geometric, semantic, and relational data within a unified spatial framework. However, current 3D scene graph approaches often restrict themselves to rigid structures of pre-determined relationship classes, mostly neglecting important semantic connections, like causal connections or environmental contexts. This paper explores the potential of foundation models to build forests of 3D scene graphs with open semantic relationships to improve scene understanding and robotic task execution. We propose a method where instance-specific concept-nodes and relationships are first identified by a VLM and extended upon by a LLM, inferring broader, more abstract concept-nodes and relationships through reasoning. These object-nodes, concept-nodes, and relationships are then assembled into a forest of hierarchical 3D scene graphs, enhanced with concept-nodes to represent abstract concepts. Evaluations were conducted on the uHumans2 and ScanNet indoor dataset, validating the accuracy and relevance of the generated relationships. Downstream suitability of scene-graph forests for robotics applications is demonstrated in an open-vocabulary object-retrieval task utilizing both ScanNet data and a real-world indoor deployment using a Boston Dynamics Spot. This paper leverages foundation models to create more expressive, semantically deep 3D hierarchical scene graphs and demonstrates their potential to advance semantic and environmental understanding in robotics.

Roberto Corlito, Fabian Schmidt, Nils Seibert et al.

Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion. Quadrupeds introduce distinct embodiment-induced sensory challenges, including foot-impact shocks, high-frequency mechanical vibrations, and rapid angular rotations, which degrade standard perception pipelines. To address this gap, we present a systematic evaluation of state-of-the-art visual, visual-inertial, and LiDAR-visual-inertial SLAM methods using the GrandTour dataset recorded on an ANYmal D quadruped. We isolate and quantify the impacts of camera modalities, shutter techniques, and inertial sensor tiers, analyzing their trade-offs across localization accuracy, algorithmic robustness, and computational resource utilization. Our empirical findings demonstrate that hardware selection has substantial influence on system resilience: stereo configurations consistently outperform monocular and RGB-D modalities, global shutter cameras significantly mitigate motion-induced tracking failures compared to rolling shutter cameras, and, crucially, standard inertial integration can degrade the performance of primarily vision-based frameworks under harsh legged locomotion. These insights additionally offer concrete design guidelines for tailoring custom sensor payloads to achieve dependable perception on agile legged systems.

Stefan Scherzinger, Arne Roennau, Rüdiger Dillmann

Tracking Cartesian motion with end~effectors is a fundamental task in robot control. For motion that is not known in advance, the solvers must find fast solutions to the inverse kinematics (IK) problem for discretely sampled target poses. On joint control level, however, the robot's actuators operate in a continuous domain, requiring smooth transitions between individual states. In this work, we present a boost to the well-known Jacobian transpose method to address this goal, using the mass matrix of a virtually conditioned twin of the manipulator. Results on the UR10 show superior convergence and quality of our dynamics-based solver against the plain Jacobian method. Our algorithm is straightforward to implement as a controller, using common robotics libraries.

Jacques Kaiser, Alexander Friedrich, J. Camilo Vasquez Tieck et al.

Spike-based communication between biological neurons is sparse and unreliable. This enables the brain to process visual information from the eyes efficiently. Taking inspiration from biology, artificial spiking neural networks coupled with silicon retinas attempt to model these computations. Recent findings in machine learning allowed the derivation of a family of powerful synaptic plasticity rules approximating backpropagation for spiking networks. Are these rules capable of processing real-world visual sensory data? In this paper, we evaluate the performance of Event-Driven Random Back-Propagation (eRBP) at learning representations from event streams provided by a Dynamic Vision Sensor (DVS). First, we show that eRBP matches state-of-the-art performance on the DvsGesture dataset with the addition of a simple covert attention mechanism. By remapping visual receptive fields relatively to the center of the motion, this attention mechanism provides translation invariance at low computational cost compared to convolutions. Second, we successfully integrate eRBP in a real robotic setup, where a robotic arm grasps objects according to detected visual affordances. In this setup, visual information is actively sensed by a DVS mounted on a robotic head performing microsaccadic eye movements. We show that our method classifies affordances within 100ms after microsaccade onset, which is comparable to human performance reported in behavioral study. Our results suggest that advances in neuromorphic technology and plasticity rules enable the development of autonomous robots operating at high speed and low energy consumption.