Joachim Hertzberg

Felix Igelbrink, Lennart Niecksch, Martin Atzmueller et al.

Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive crop-based feature extraction. To overcome this fundamental limitation, we introduce DISC (Dense Integrated Semantic Context), featuring a novel single-pass, distance-weighted extraction mechanism. By deriving high-fidelity CLIP embeddings directly from the vision transformer's intermediate layers, our approach eliminates the latency and domain-shift artifacts of traditional image cropping, yielding pure, mask-aligned semantic representations. To fully leverage these features in large-scale continuous mapping, DISC is built upon a fully GPU-accelerated architecture that replaces periodic offline processing with precise, on-the-fly voxel-level instance refinement. We evaluate our approach on standard benchmarks (Replica, ScanNet) and a newly generated large-scale-mapping dataset based on Habitat-Matterport 3D (HM3DSEM) to assess scalability across complex scenes in multi-story buildings. Extensive evaluations demonstrate that DISC significantly surpasses current state-of-the-art zero-shot methods in both semantic accuracy and query retrieval, providing a robust, real-time capable framework for robotic deployment. The full source code, data generation and evaluation pipelines will be made available at https://github.com/DFKI-NI/DISC.

Oscar Lima, Marc Vinci, Martin Günther et al.

Recent work leverages the capabilities and commonsense priors of generative models for robot control. In this paper, we present an agentic control system in which a reasoning-capable language model plans and executes tasks by selecting and invoking robot skills within an iterative planner and executor loop. We deploy the system on two physical robot platforms in two settings: (i) tabletop grasping, placement, and box insertion in indoor mobile manipulation (Mobipick) and (ii) autonomous agricultural navigation and sensing (Valdemar). Both settings involve uncertainty, partial observability, sensor noise, and ambiguous natural-language commands. The system exposes structured introspection of its planning and decision process, reacts to exogenous events via explicit event checks, and supports operator interventions that modify or redirect ongoing execution. Across both platforms, our proof-of-concept experiments reveal substantial fragility, including non-deterministic suboptimal behavior, instruction-following errors, and high sensitivity to prompt specification. At the same time, the architecture is flexible: transfer to a different robot and task domain largely required updating the system prompt (domain model, affordances, and action catalogue) and re-binding the same tool interface to the platform-specific skill API.

Felix Igelbrink, Marian Renz, Martin Günther et al.

Semantic mapping is a key component of robots operating in and interacting with objects in structured environments. Traditionally, geometric and knowledge representations within a semantic map have only been loosely integrated. However, recent advances in deep learning now allow full integration of prior knowledge, represented as knowledge graphs or language concepts, into sensor data processing and semantic mapping pipelines. Semantic scene graphs and language models enable modern semantic mapping approaches to incorporate graph-based prior knowledge or to leverage the rich information in human language both during and after the mapping process. This has sparked substantial advances in semantic mapping, leading to previously impossible novel applications. This survey reviews these recent developments comprehensively, with a focus on online integration of knowledge into semantic mapping. We specifically focus on methods using semantic scene graphs for integrating symbolic prior knowledge and language models for respective capture of implicit common-sense knowledge and natural language concepts

Juan Carlos Saborio, Joachim Hertzberg

Intention recognition, or the ability to anticipate the actions of another agent, plays a vital role in the design and development of automated assistants that can support humans in their daily tasks. In particular, industrial settings pose interesting challenges that include potential distractions for a decision-maker as well as noisy or incomplete observations. In such a setting, a robotic assistant tasked with helping and supporting a human worker must interleave information gathering actions with proactive tasks of its own, an approach that has been referred to as active goal recognition. In this paper we describe a partially observable model for online intention recognition, show some preliminary experimental results and discuss some of the challenges present in this family of problems.

Zongyao Yi, Joachim Hertzberg, Martin Atzmueller

We present a learnable physics simulator that provides accurate motion and force-torque prediction of robot end effectors in contact-rich manipulation. The proposed model extends the state-of-the-art GNN-based simulator (FIGNet) with novel node and edge types, enabling action-conditional predictions for control and state estimation tasks. In simulation, the MPC agent using our model matches the performance of the same controller with the ground truth dynamics model in a challenging peg-in-hole task, while in the real-world experiment, our model achieves a 50% improvement in motion prediction accuracy and 3$\times$ increase in force-torque prediction precision over the baseline physics simulator. Source code and data are publicly available.

Juan Carlos Saborío, Marc Vinci, Oscar Lima et al.

Purposeful behavior in robotic assistants requires the integration of multiple components and technological advances. Often, the problem is reduced to recognizing explicit prompts, which limits autonomy, or is oversimplified through assumptions such as near-perfect information. We argue that a critical gap remains unaddressed -- specifically, the challenge of reasoning about the uncertain outcomes and perception errors inherent to human intention recognition. In response, we present a framework designed to be resilient to uncertainty and sensor noise, integrating real-time sensor data with a combination of planners. Centered around an intention-recognition POMDP, our approach addresses cooperative planning and acting under uncertainty. Our integrated framework has been successfully tested on a physical robot with promising results.

Oscar Lima, Marc Vinci, Sunandita Patra et al.

Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment for an object collection task. Our experiments demonstrate robust task execution under action failures and sensor noise, and provide empirical insights into the interleaved acting-and-planning decision making process.

Till Grenzdörffer, Martin Günther, Joachim Hertzberg

While a great variety of 3D cameras have been introduced in recent years, most publicly available datasets for object recognition and pose estimation focus on one single camera. In this work, we present a dataset of 32 scenes that have been captured by 7 different 3D cameras, totaling 49,294 frames. This allows evaluating the sensitivity of pose estimation algorithms to the specifics of the used camera and the development of more robust algorithms that are more independent of the camera model. Vice versa, our dataset enables researchers to perform a quantitative comparison of the data from several different cameras and depth sensing technologies and evaluate their algorithms before selecting a camera for their specific task. The scenes in our dataset contain 20 different objects from the common benchmark YCB object and model set [1], [2]. We provide full ground truth 6DoF poses for each object, per-pixel segmentation, 2D and 3D bounding boxes and a measure of the amount of occlusion of each object. We have also performed an initial evaluation of the cameras using our dataset on a state-of-the-art object recognition and pose estimation system [3].