arXiv subjects

Bogdan Franczyk

Publications and source records attributed to Bogdan Franczyk.

8 recordsLinked to original sources

arXiv2026

Semantic Radiance Fields as Simulators for Spatial Reasoning in Real-World Scenes

Training and evaluating spatial reasoning in embodied agents requires diverse environments that are both geometrically faithful and semantically queryable. Synthetic simulators offer ground truth semantics but sacrifice realism; simulators based on reconstructions of real-world environments have realistic appearance but lack ground truth semantics by default. We propose using Semantic Radiance Fields (SRF) as simulators for spatial reasoning agents. SRFs are a representation that unifies these requirements by lifting 2D semantic segmentations from pretrained vision models into a 3D radiance field that jointly encodes geometry, appearance, and per-class semantic identity. The resulting fields are reconstructed from posed RGB captures of real scenes and support novel-view synthesis, semantic and free-space queries within a single grounded representation. This enables the efficient generation of diverse real-world environments to train and evaluate spatial reasoning models. As an example application, we outline an SRF-driven simulator for an orchard apple-reaching task, in which the radiance field supplies camera rendering, semantic ground truth, and occupancy queries to a physics engine.

cs.RO↗

arXiv2026

From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP

Emerging foundation models (FMs) in electroencephalography (EEG) promise a path to scale deep learning in diagnostics and brain-computer interfaces despite data scarcity, yet their opaque nature remains a barrier to wider adoption. We investigate attention-aware Layer-wise relevance propagation (LRP) as a post-hoc attribution method for EEG-FMs, extending LRP's use on convolutional neural network (CNN)-based EEG models to the Transformer architectures that current FMs are based on. We find that LRP can both verify EEG-FM decisions and surface novel, biologically plausible hypotheses from them. In motor imagery, it unmasks 'Clever Hans' behavior where models prioritize task correlated ocular signals over the intended motor correlates. In a naturalistic paradigm for affect prediction, it reveals a recurring reliance on a central electrode cluster, suggesting a candidate sensorimotor signature of arousal. Though heatmap interpretation remains ambiguous in this complex domain, the results position LRP as a tool for both verification and exploration of EEG-FMs, a role that will grow in both importance and discovery potential as the underlying models mature.

cs.AI↗

arXiv2026

Real-time windrow detection from onboard tractor sensors for automated following

Proprietary design in commercial windrow-detection systems restricts transparency and limits progress in open autonomous forage-harvesting research. We present a multi-modal dataset combining stereo vision and LiDAR from tractor-mounted sensors during real baling operations. The dataset includes synchronized sensor data with GNSS trajectories, partly released as ROS2 Humble bags on Zenodo, with additional data available on request. Using this dataset, we implement a real-time (>20 Hz) centroid-based windrow-following method on an NVIDIA Jetson AGX Orin. Across the critical 4-10 m guidance range, stereo and LiDAR depth measurements show strong agreement (0.965 +/- 0.021), indicating that low-cost stereo sensors can approach LiDAR performance. Our open-source ROS 2 pipeline provides a reproducible benchmark for GPS-free windrow detection and supports development of practical autonomous forage-harvesting systems. Dataset: https://zenodo.org/records/17486318

cs.RO↗

arXiv2025

MapAnything: Evaluating Monocular Metric Depth Models for 3D Urban Asset Localization

City administrations increasingly rely on comprehensive databases and digital twins of city assets, such as traffic signs and trees, as well as incidents such as graffiti or road damage, to maintain an effective overview of urban conditions. Digitization has increased the demand for continuously updated spatial datasets, yet current data acquisition and maintenance processes still involve considerable manual effort, posing significant scalability challenges. This paper introduces MapAnything, a systematic evaluation pipeline that automates the spatial mapping of urban objects and incidents from a single monocular image. By leveraging advanced Metric Depth Estimation models, MapAnything accurately calculates object geocoordinates, converting 2D image data into valuable 3D spatial information. The methodology integrates the estimated camera-to-object distance with geometric principles and known camera specifications. We present a detailed validation of the framework, comparing its distance-estimation accuracy against high-precision LiDAR point clouds in complex urban environments. Our evaluation provides a granular analysis of spatial performance across various distance intervals and semantic areas, such as roads and vegetation. Finally, we demonstrate the framework's practical efficacy through specific use cases, including mapping traffic signs and road pavement damage, and provide recommendations for its integration into automated urban inventory systems.

cs.CV↗

arXiv2024

Trends, Advancements and Challenges in Intelligent Optimization in Satellite Communication

Efficient satellite communications play an enormously important role in all of our daily lives. This includes the transmission of data for communication purposes, the operation of IoT applications or the provision of data for ground stations. More and more, AI-based methods are finding their way into these areas. This paper gives an overview of current research in the field of intelligent optimization of satellite communication. For this purpose, a text-mining based literature review was conducted and the identified papers were thematically clustered and analyzed. The identified clusters cover the main topics of routing, resource allocation and, load balancing. Through such a clustering of the literature in overarching topics, a structured analysis of the research papers was enabled, allowing the identification of latest technologies and approaches as well as research needs for intelligent optimization of satellite communication.

cs.NI↗

arXiv2024

Enhancing Roadway Safety: LiDAR-based Tree Clearance Analysis

In the efforts for safer roads, ensuring adequate vertical clearance above roadways is of great importance. Frequently, trees or other vegetation is growing above the roads, blocking the sight of traffic signs and lights and posing danger to traffic participants. Accurately estimating this space from simple images proves challenging due to a lack of depth information. This is where LiDAR technology comes into play, a laser scanning sensor that reveals a three-dimensional perspective. Thus far, LiDAR point clouds at the street level have mainly been used for applications in the field of autonomous driving. These scans, however, also open up possibilities in urban management. In this paper, we present a new point cloud algorithm that can automatically detect those parts of the trees that grow over the street and need to be trimmed. Our system uses semantic segmentation to filter relevant points and downstream processing steps to create the required volume to be kept clear above the road. Challenges include obscured stretches of road, the noisy unstructured nature of LiDAR point clouds, and the assessment of the road shape. The identified points of non-compliant trees can be projected from the point cloud onto images, providing municipalities with a visual aid for dealing with such occurrences. By automating this process, municipalities can address potential road space constraints, enhancing safety for all. They may also save valuable time by carrying out the inspections more systematically. Our open-source code gives communities inspiration on how to automate the process themselves.

cs.CV↗

arXiv2021

Framework Artifact for the Road-Based Physical Internet based on Internet Protocols

The Physical Internet (PI) raises high expectations for efficiency gains in transport and logistics. The PI represents the network of logistics networks for physical objects in analogy to the Data Internet (DI). Road based traffic represents one of these logistics networks. Here, many empty runs and underutilized trips still take place. Hence, there is a lot of potential in the road-based Physical Internet (RBPI), which will have an impact on transport and logistics strategies, but also on vehicle design. On the DI, logistics strategies are implemented in protocols. In order to transfer such concepts to the RBPI, relevant protocols of the DI had been analyzed and transferred to the world of physical objects. However, not all functionalities can be transferred one-to-one, e.g. a data packet in the DI can simply be re-generated by a hub in case of damage or loss. To compensate for the challenges, a framework artifact has been designed with appropriate transformation customizations based on design science principles. From this, resulting requirements for future vehicles were derived. This paper makes a contribution to the implementation of the RBPI in order to fit road based vehicles to the future world of transport and logistics.

cs.NI↗

arXiv2020

Design and Evaluation of Routing Artifacts as a Part of the Physical Internet Framework

Global freight demand will triple between 2015 and 2050, based on the current demand pathway, as predicted in the Transport Outlook 2019. Hence, a revolutionary change in transport efficiency is urgently needed. One approach to tackle this change is to transfer the successful model of the Digital Internet for data exchange to the physical transport of goods: The so-called Physical Internet (PI, or $π$). The potential of the Physical Internet lies in dynamic routing, which increases the utilization of transport modalities, like trucks and vans, and makes transport more efficient. Previous concept transfers have identified and determined the $π$-nodes as routing entities. Here, the problem is that the $π$-nodes have no information about real-time data on transport vacancies. This leads to a great challenge for the $π$-nodes with regard to routing, in particular in determining the next best appropriate node for onward transport of the freight package. This paper evolved the state of research concept as an artifact that considers the $π$-nodes as routers in a way that it distributes and replicates real-time data to the $π$-nodes in order to enable more effective routing decisions. This real-time data is provided by vehicles, or so-called $π$-transporters, on the road. Therefore, a second artifact will be designed in which $π$-transporters take over the routing role. In order to be able to take a holistic perspective on the routing topic, the goods that are actually to be moved, the so-called $π$-containers, are also designed as routing entities in a third artifact. These three artifacts are then compared and evaluated for the consideration of real-time traffic data. This paper proposes $π$-transporters as routing entities whose software representatives negotiate freight handover points in a cloud-based marketplace.

cs.NI↗