arXiv subjects

Kai O. Arras

Publications and source records attributed to Kai O. Arras.

At least 19 recordsLinked to original sources

arXiv2026

FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents

To operate effectively in human environments, robots must identify articulated objects, segment their movable and interactive parts, and estimate their kinematic models. Existing articulated scene representations typically recover kinematics from observed interactions, while methods operating on static scans often decouple articulation from functional interactive elements. We present FunArt, a framework that constructs articulation-aware functional 3D scene graphs from posed RGB-D observations captured in a single static configuration. FunArt reconstructs object instances, converts their fused geometry directly into the O-Voxel representation of TRELLIS.2, and exploits its frozen, sparse-compression VAE as a structural prior. A lightweight query-based decoder combines compact object-level latents with dense, surface-aligned features to jointly segment movable parts and functional interactive elements while estimating motion type, axis, origin, and range. On the Articulate3D dataset, FunArt achieves state-of-the-art performance across movable-part segmentation, articulation estimation, and functional-element segmentation, both with and without ground-truth object input. In the end-to-end setting, it outperforms the strongest baselines by 1.5 AP_{50} points for movable parts, 2.8 AP_{50} points under joint origin-and-axis constraints, and 6.7 AP_{50} points for functional elements. These results demonstrate that generative 3D latents encode actionable structural cues that can initialize robotic perception and planning before physical interaction.

cs.CV↗

arXiv2026

GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes

Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how individual interactions compose into goal-directed activities. Existing 4D scene graphs preserve object and place histories but omit activity structure, whereas activity representations are either not grounded in persistent 3D scenes or rely on externally provided event boundaries and object associations. We present GESTO (Grounded Event and Spatio-Temporal memOry), a spatio-temporal memory that couples a persistent 4D scene graph with a two-level hierarchy of atomic human--object interactions and goal-driven events. From an RGB-D observation stream, GESTO automatically extracts timestamped interactions, grounds them to persistent scene entities, groups them into events, and uses event context to refine uncertain object associations. A relation-aware tool-calling agent queries the resulting memory for activity-centric spatio-temporal reasoning. We evaluate GESTO on the reproducible text, binary, and time categories of an existing benchmark, together with 40 new Space2Event and Event2Space queries. GESTO achieves scores of 0.71, 0.75, and 0.70 on the standard categories, approaching a method supplied with ground-truth event and object grounding, while substantially outperforming the same reasoning framework when these inputs are removed. It further achieves 0.73 and 0.75 on Space2Event and Event2Space queries. Ablations show that hierarchical event structure and context-aware grounding refinement provide complementary benefits, supporting activity-grounded hierarchical memory for retrospective reasoning in dynamic human environments.

cs.CV↗

arXiv2026

Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots

Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-aware ways. While 3D Scene Graphs have emerged as a powerful semantic representation for scene understanding, existing approaches largely ignore humans in the scene, also due to the lack of annotated human-environment relationships. Moreover, existing methods typically capture only open-vocabulary relations from single image frames, which limits their ability to model long-range interactions beyond the observed content. We introduce Social 3D Scene Graphs, an augmented 3D Scene Graph representation that captures humans, their attributes, activities and relationships in the environment, both local and remote, using an open-vocabulary framework. Furthermore, we introduce a new benchmark consisting of synthetic environments with comprehensive human-scene relationship annotations and diverse types of queries for evaluating social scene understanding in 3D. The experiments demonstrate that our representation improves human activity prediction and reasoning about human-environment relations, paving the way toward socially intelligent robots.

cs.CV↗

arXiv2026

3D Scene Graphs: Open Challenges and Future Directions

3D Scene Graphs (3DSGs) have emerged as a powerful representation for spatial AI by combining geometric grounding with semantic and relational abstractions of the environment. Their expressiveness has made them relevant to a broad range of problems in robotics and computer vision, including manipulation, navigation, task planning, scene understanding, and many others. However, the field remains fragmented: different communities adopt distinct formulations, construction pipelines, and evaluation protocols, making it difficult to compare methods, identify common assumptions, and assess remaining challenges for robust real-world deployment. This survey provides a unified and critical review of 3DSGs, with particular emphasis on open challenges and future directions. We first formalize 3DSGs under a common definition and analyze the principal modeling choices that characterize existing formulations, including node and edge attributes, hierarchical structure, dynamic scene representations, and affordance-aware extensions. We then review how 3DSGs are built from raw sensory observations, discussing the most common terminologies, conventions, and techniques. Finally, we examine downstream applications and evaluation strategies, from intrinsic graph quality to task-level performance. To support the community, we also provide a dedicated website that organizes and extends the surveyed content, accessible at https://3dscenegraphs.com/.

cs.RO↗

arXiv2026

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs

In recent years, 3D scene graphs have emerged as a powerful world representation, offering both geometric accuracy and semantic richness. Combining 3D scene graphs with large language models enables robots to reason, plan, and navigate in complex human-centered environments. However, current approaches for constructing 3D scene graphs are semantically limited to a predefined set of relationships, and their serialization in large environments can easily exceed an LLM's context window. We introduce KeySG, a framework that represents 3D scenes as a hierarchical graph consisting of floors, rooms, objects, and functional elements, where nodes are augmented with multi-modal information extracted from keyframes selected to optimize geometric and visual coverage. The keyframes allow us to efficiently leverage VLMs to extract scene information, alleviating the need to explicitly model relationship edges between objects, enabling more general, task-agnostic reasoning and planning. Our approach can process complex and ambiguous queries while mitigating the scalability issues associated with large scene graphs by utilizing a hierarchical multi-modal retrieval-augmented generation (RAG) pipeline to extract relevant context from the graph. Evaluated across three distinct benchmarks, 3D object semantic segmentation, functional element segmentation, and complex query retrieval, KeySG outperforms prior approaches on most metrics, demonstrating its superior semantic richness and efficiency.

cs.CV↗

arXiv2025

Interactive Expressive Motion Generation Using Dynamic Movement Primitives

Our goal is to enable social robots to interact autonomously with humans in a realistic, engaging, and expressive manner. The 12 Principles of Animation are a well-established framework animators use to create movements that make characters appear convincing, dynamic, and emotionally expressive. This paper proposes a novel approach that leverages Dynamic Movement Primitives (DMPs) to implement key animation principles, providing a learnable, explainable, modulable, online adaptable and composable model for automatic expressive motion generation. DMPs, originally developed for general imitation learning in robotics and grounded in a spring-damper system design, offer mathematical properties that make them particularly suitable for this task. Specifically, they enable modulation of the intensities of individual principles and facilitate the decomposition of complex, expressive motion sequences into learnable and parametrizable primitives. We present the mathematical formulation of the parameterized animation principles and demonstrate the effectiveness of our framework through experiments and application on three robotic platforms with different kinematic configurations, in simulation, on actual robots and in a user study. Our results show that the approach allows for creating diverse and nuanced expressions using a single base model.

cs.RO↗

arXiv2025

FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction

The concept of 3D scene graphs is increasingly recognized as a powerful semantic and hierarchical representation of the environment. Current approaches often address this at a coarse, object-level resolution. In contrast, our goal is to develop a representation that enables robots to directly interact with their environment by identifying both the location of functional interactive elements and how these can be used. To achieve this, we focus on detecting and storing objects at a finer resolution, focusing on affordance-relevant parts. The primary challenge lies in the scarcity of data that extends beyond instance-level detection and the inherent difficulty of capturing detailed object features using robotic sensors. We leverage currently available 3D resources to generate 2D data and train a detector, which is then used to augment the standard 3D scene graph generation pipeline. Through our experiments, we demonstrate that our approach achieves functional element segmentation comparable to state-of-the-art 3D models and that our augmentation enables task-driven affordance grounding with higher accuracy than the current solutions. See our project page at https://fungraph.github.io.

cs.CV↗

arXiv2025

Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs

Long-term planning for robots operating in domestic environments poses unique challenges due to the interactions between humans, objects, and spaces. Recent advancements in trajectory planning have leveraged vision-language models (VLMs) to extract contextual information for robots operating in real-world environments. While these methods achieve satisfying performance, they do not explicitly model human activities. Such activities influence surrounding objects and reshape spatial constraints. This paper presents a novel approach to trajectory planning that integrates human preferences, activities, and spatial context through an enriched 3D scene graph (3DSG) representation. By incorporating activity-based relationships, our method captures the spatial impact of human actions, leading to more context-sensitive trajectory adaptation. Preliminary results demonstrate that our approach effectively assigns costs to spaces influenced by human activities, ensuring that the robot trajectory remains contextually appropriate and sensitive to the ongoing environment. This balance between task efficiency and social appropriateness enhances context-aware human-robot interactions in domestic settings. Future work includes implementing a full planning pipeline and conducting user studies to evaluate trajectory acceptability.

cs.RO↗

arXiv2024

The Child Factor in Child-Robot Interaction: Discovering the Impact of Developmental Stage and Individual Characteristics

Social robots, owing to their embodied physical presence in human spaces and the ability to directly interact with the users and their environment, have a great potential to support children in various activities in education, healthcare and daily life. Child-Robot Interaction (CRI), as any domain involving children, inevitably faces the major challenge of designing generalized strategies to work with unique, turbulent and very diverse individuals. Addressing this challenging endeavor requires to combine the standpoint of the robot-centered perspective, i.e. what robots technically can and are best positioned to do, with that of the child-centered perspective, i.e. what children may gain from the robot and how the robot should act to best support them in reaching the goals of the interaction. This article aims to help researchers bridge the two perspectives and proposes to address the development of CRI scenarios with insights from child psychology and child development theories. To that end, we review the outcomes of the CRI studies, outline common trends and challenges, and identify two key factors from child psychology that impact child-robot interactions, especially in a long-term perspective: developmental stage and individual characteristics. For both of them we discuss prospective experiment designs which support building naturally engaging and sustainable interactions.

cs.RO↗

arXiv2023

CLiFF-LHMP: Using Spatial Dynamics Patterns for Long-Term Human Motion Prediction

Human motion prediction is important for mobile service robots and intelligent vehicles to operate safely and smoothly around people. The more accurate predictions are, particularly over extended periods of time, the better a system can, e.g., assess collision risks and plan ahead. In this paper, we propose to exploit maps of dynamics (MoDs, a class of general representations of place-dependent spatial motion patterns, learned from prior observations) for long-term human motion prediction (LHMP). We present a new MoD-informed human motion prediction approach, named CLiFF-LHMP, which is data efficient, explainable, and insensitive to errors from an upstream tracking system. Our approach uses CLiFF-map, a specific MoD trained with human motion data recorded in the same environment. We bias a constant velocity prediction with samples from the CLiFF-map to generate multi-modal trajectory predictions. In two public datasets we show that this algorithm outperforms the state of the art for predictions over very extended periods of time, achieving 45% more accurate prediction performance at 50s compared to the baseline.

cs.RO↗

arXiv2023

Advantages of Multimodal versus Verbal-Only Robot-to-Human Communication with an Anthropomorphic Robotic Mock Driver

Robots are increasingly used in shared environments with humans, making effective communication a necessity for successful human-robot interaction. In our work, we study a crucial component: active communication of robot intent. Here, we present an anthropomorphic solution where a humanoid robot communicates the intent of its host robot acting as an "Anthropomorphic Robotic Mock Driver" (ARMoD). We evaluate this approach in two experiments in which participants work alongside a mobile robot on various tasks, while the ARMoD communicates a need for human attention, when required, or gives instructions to collaborate on a joint task. The experiments feature two interaction styles of the ARMoD: a verbal-only mode using only speech and a multimodal mode, additionally including robotic gaze and pointing gestures to support communication and register intent in space. Our results show that the multimodal interaction style, including head movements and eye gaze as well as pointing gestures, leads to more natural fixation behavior. Participants naturally identified and fixated longer on the areas relevant for intent communication, and reacted faster to instructions in collaborative tasks. Our research further indicates that the ARMoD intent communication improves engagement and social interaction with mobile robots in workplace settings.

cs.RO↗

arXiv2023

The e-Bike Motor Assembly: Towards Advanced Robotic Manipulation for Flexible Manufacturing

Robotic manipulation is currently undergoing a profound paradigm shift due to the increasing needs for flexible manufacturing systems, and at the same time, because of the advances in enabling technologies such as sensing, learning, optimization, and hardware. This demands for robots that can observe and reason about their workspace, and that are skillfull enough to complete various assembly processes in weakly-structured settings. Moreover, it remains a great challenge to enable operators for teaching robots on-site, while managing the inherent complexity of perception, control, motion planning and reaction to unexpected situations. Motivated by real-world industrial applications, this paper demonstrates the potential of such a paradigm shift in robotics on the industrial case of an e-Bike motor assembly. The paper presents a concept for teaching and programming adaptive robots on-site and demonstrates their potential for the named applications. The framework includes: (i) a method to teach perception systems onsite in a self-supervised manner, (ii) a general representation of object-centric motion skills and force-sensitive assembly skills, both learned from demonstration, (iii) a sequencing approach that exploits a human-designed plan to perform complex tasks, and (iv) a system solution for adapting and optimizing skills online. The aforementioned components are interfaced through a four-layer software architecture that makes our framework a tangible industrial technology. To demonstrate the generality of the proposed framework, we provide, in addition to the motivating e-Bike motor assembly, a further case study on dense box packing for logistics automation.

cs.RO↗

arXiv2022

The Magni Human Motion Dataset: Accurate, Complex, Multi-Modal, Natural, Semantically-Rich and Contextualized

Rapid development of social robots stimulates active research in human motion modeling, interpretation and prediction, proactive collision avoidance, human-robot interaction and co-habitation in shared spaces. Modern approaches to this end require high quality datasets for training and evaluation. However, the majority of available datasets suffers from either inaccurate tracking data or unnatural, scripted behavior of the tracked people. This paper attempts to fill this gap by providing high quality tracking information from motion capture, eye-gaze trackers and on-board robot sensors in a semantically-rich environment. To induce natural behavior of the recorded participants, we utilise loosely scripted task assignment, which induces the participants navigate through the dynamic laboratory environment in a natural and purposeful way. The motion dataset, presented in this paper, sets a high quality standard, as the realistic and accurate data is enhanced with semantic information, enabling development of new algorithms which rely not only on the tracking information but also on contextual cues of the moving agents, static and dynamic environment.

cs.RO↗

arXiv2022

The Atlas Benchmark: an Automated Evaluation Framework for Human Motion Prediction

Human motion trajectory prediction, an essential task for autonomous systems in many domains, has been on the rise in recent years. With a multitude of new methods proposed by different communities, the lack of standardized benchmarks and objective comparisons is increasingly becoming a major limitation to assess progress and guide further research. Existing benchmarks are limited in their scope and flexibility to conduct relevant experiments and to account for contextual cues of agents and environments. In this paper we present Atlas, a benchmark to systematically evaluate human motion trajectory prediction algorithms in a unified framework. Atlas offers data preprocessing functions, hyperparameter optimization, comes with popular datasets and has the flexibility to setup and conduct underexplored yet relevant experiments to analyze a method's accuracy and robustness. In an example application of Atlas, we compare five popular model- and learning-based predictors and find that, when properly applied, early physics-based approaches are still remarkably competitive. Such results confirm the necessity of benchmarks like Atlas.

cs.RO↗

arXiv2021

Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study

Advances in sensing and learning algorithms have led to increasingly mature solutions for human detection by robots, particularly in selected use-cases such as pedestrian detection for self-driving cars or close-range person detection in consumer settings. Despite this progress, the simple question "which sensor-algorithm combination is best suited for a person detection task at hand?" remains hard to answer. In this paper, we tackle this issue by conducting a systematic cross-modal analysis of sensor-algorithm combinations typically used in robotics. We compare the performance of state-of-the-art person detectors for 2D range data, 3D lidar, and RGB-D data as well as selected combinations thereof in a challenging industrial use-case. We further address the related problems of data scarcity in the industrial target domain, and that recent research on human detection in 3D point clouds has mostly focused on autonomous driving scenarios. To leverage these methodological advances for robotics applications, we utilize a simple, yet effective multi-sensor transfer learning strategy by extending a strong image-based RGB-D detector to provide cross-modal supervision for lidar detectors in the form of weak 3D bounding box labels. Our results show a large variance among the different approaches in terms of detection performance, generalization, frame rates and computational requirements. As our use-case contains difficulties representative for a wide range of service robot applications, we believe that these results point to relevant open challenges for further research and provide valuable support to practitioners for the design of their robot system.

cs.RO↗

arXiv2021

Learning Occupancy Priors of Human Motion from Semantic Maps of Urban Environments

Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a powerful approach to discover recurrent motion patterns, generalization to new environments, where sufficient motion data are not readily available, remains a challenge. In many cases, however, semantic information about the environment is a highly informative cue for the prediction of pedestrian motion or the estimation of collision risks. In this work, we infer occupancy priors of human motion using only semantic environment information as input. To this end we apply and discuss a traditional Inverse Optimal Control approach, and propose a novel one based on Convolutional Neural Networks (CNN) to predict future occupancy maps. Our CNN method produces flexible context-aware occupancy estimations for semantically uniform map regions and generalizes well already with small amounts of training data. Evaluated on synthetic and real-world data, it shows superior results compared to several baselines, marking a qualitative step-up in semantic environment assessment.

cs.RO↗

arXiv2020

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and Z to metric depth around the subject. To obtain metric-scale predictions, 2.5D methods need a separate post-processing step to resolve scale ambiguity. Further, they cannot localize body joints outside the image boundaries, leading to incomplete estimates for truncated images. To address these limitations, we propose metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are all defined in metric 3D space, instead of being aligned with image space. This reinterpretation of heatmap dimensions allows us to directly estimate complete, metric-scale poses without test-time knowledge of distance or relying on anthropometric heuristics, such as bone lengths. To further demonstrate the utility our representation, we present a differentiable combination of our 3D metric-scale heatmaps with 2D image-space ones to estimate absolute 3D pose (our MeTRAbs architecture). We find that supervision via absolute pose loss is crucial for accurate non-root-relative localization. Using a ResNet-50 backbone without further learned layers, we obtain state-of-the-art results on Human3.6M, MPI-INF-3DHP and MuPoTS-3D. Our code will be made publicly available to facilitate further research.

cs.CV↗

arXiv2020

CIAO$^\star$: MPC-based Safe Motion Planning in Predictable Dynamic Environments

Robots have been operating in dynamic environments and shared workspaces for decades. Most optimization based motion planning methods, however, do not consider the movement of other agents, e.g. humans or other robots, and therefore do not guarantee collision avoidance in such scenarios. This paper builds upon the Convex Inner ApprOximation (CIAO) method and proposes a motion planning algorithm that guarantees collision avoidance in predictable dynamic environments. Furthermore, it generalizes CIAO's free region concept to arbitrary norms and proposes a cost function to approximate time optimal motion planning. The proposed method, CIAO$^\star$, finds kinodynamically feasible and collision free trajectories for constrained single body robots using model predictive control (MPC). It optimizes the motion of one agent and accounts for the predicted movement of surrounding agents and obstacles. The experimental evaluation shows that CIAO$^\star$ reaches close to time optimal behavior.

cs.RO↗