The advancement of 3D language fields has enabled intuitive interactions with 3D scenes via natural language. However, existing approaches are typically limited to small-scale environments, lacking the scalability and compositional reasoning capabilities necessary for large, complex urban settings. To overcome these limitations, we propose GeoProg3D, a visual programming framework that enables natural language-driven interactions with city-scale high-fidelity 3D scenes. GeoProg3D consists of two key components: (i) a Geography-aware City-scale 3D Language Field (GCLF) that leverages a memory-efficient hierarchical 3D model to handle large-scale data, integrated with geographic information for efficiently filtering vast urban spaces using directional cues, distance measurements, elevation data, and landmark references; and (ii) Geographical Vision APIs (GV-APIs), specialized geographic vision tools such as area segmentation and object detection. Our framework employs large language models (LLMs) as reasoning engines to dynamically combine GV-APIs and operate GCLF, effectively supporting diverse geographic vision tasks. To assess performance in city-scale reasoning, we introduce GeoEval3D, a comprehensive benchmark dataset containing 952 query-answer pairs across five challenging tasks: grounding, spatial reasoning, comparison, counting, and measurement. Experiments demonstrate that GeoProg3D significantly outperforms existing 3D language fields and vision-language models across multiple tasks. To our knowledge, GeoProg3D is the first framework enabling compositional geographic reasoning in high-fidelity city-scale 3D environments via natural language. The code is available at https://snskysk.github.io/GeoProg3D/.

We present a novel task for cross-dataset visual grounding in 3D scenes (Cross3DVG), which overcomes limitations of existing 3D visual grounding models, specifically their restricted 3D resources and consequent tendencies of overfitting a specific 3D dataset. We created RIORefer, a large-scale 3D visual grounding dataset, to facilitate Cross3DVG. It includes more than 63 k diverse descriptions of 3D objects within 1,380 indoor RGB-D scans from 3RScan [48], with human annotations. After training the Cross3DVG model using the source 3D visual grounding dataset, we evaluate it without target labels using the target dataset with, e.g., different sensors, 3D reconstruction methods, and language annotators. Comprehensive experiments are conducted using established visual grounding models and with CLIP-based multi-view 2D and 3D integration designed to bridge gaps among 3D datasets. For Cross3DVG tasks, (i) cross-dataset 3D visual grounding exhibits significantly worse performance than learning and evaluation with a single dataset because of the 3D data and language variants across datasets. Moreover, (ii) better object detector and localization modules and fusing 3D data and multi-view CLIP-based image features can alleviate this lower performance. Our Cross3DVG task can provide a benchmark for developing robust 3D visual grounding models to handle diverse 3D scenes while leveraging deep language understanding.11Project page: https://github.com/ATR-DBI/Cross3DVG

We propose Answerability Fields (AnsFields), a novel approach for predicting the answerability of questions at different locations within indoor environments. AnsFields is represented as a map, where each grid’s score reflects how well a question can be answered using the panoramic image at that location. Using a 3D question-answering dataset, we construct comprehensive AnsFields covering diverse scenes from ScanNet. Additionally, we employ a diffusion model to infer AnsFields from a scene’s top-down view image and the question. We then conduct 3D question-answering using these predicted AnsFields and achieve a 24% improvement in accuracy over the standard 3D-QA method. Our results demonstrate the importance of object locations for answering questions in the environment, highlighting the potential of AnsFields for applications in robotics, augmented reality, and human-robot interaction.

Embodied Question Answering (EQA) serves as a benchmark task to evaluate the capability of robots to navigate within novel environments and identify objects in response to human queries. However, existing EQA methods often rely on simulated environments and operate with limited vocabularies. This paper presents a map-based modular approach to EQA, enabling real-world robots to explore and map unknown environments. By leveraging foundation models, our method facilitates answering a diverse range of questions using natural language. We conducted extensive experiments in both virtual and real-world settings, demonstrating the robustness of our approach in navigating and comprehending queries within unknown environments.

We propose a new 3D spatial understanding task for 3D question answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of a rich RGB-D indoor scan and answer given textual questions about the 3D scene. Unlike the 2D-question answering of visual question answering, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail in object localization from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, called the ScanQA11https://github.com/ATR-DBI/ScanQA, which learns a fused descriptor from 3D object proposals and encoded sentence embeddings. This learned descriptor correlates language expressions with the underlying geometric features of the 3D scan and facilitates the regression of 3D bounding boxes to determine the described objects in textual questions. We collected human-edited question-answer pairs with free-form answers grounded in 3D objects in each 3D scene. Our new ScanQA dataset contains over 41k question-answer pairs from 800 indoor scenes obtained from the ScanNet dataset. To the best of our knowledge, ScanQA is the first large-scale effort to perform object-grounded question answering in 3D environments.

This paper proposes dependable parallel multi-population global-best brain storm optimization with differential evolution strategies (DPMP-GBSODE) for distribution system state estimation (DSSE) using just-in-time (JIT) modeling and correntropy. In electric power distribution systems, DSSE is utilized by power utility operators to grasp whole distribution system conditions such as voltages and currents. By applying JIT modeling and correntropy to DSSE problems, voltages and currents can be correctly estimated even if false measurement values (outliers) are measured. Considering equipment of the distribution systems and penetration of renewable energies (REs), it is necessary that an evolutionary computation technique with parallel and distributed processing (PDP) is applied to the DSSE problems. When some computational processes are distributed by PDP in server systems of distribution automation systems, some calculation results from the distributed computational processes may not be returned because of various congestions of the processes. Therefore, appropriate estimation results should be obtained even if the congestions occur (dependability). The proposed DPMP-GBSODE is verified to improve dependability and computation time for the DSSE problem in comparison with conventional method even if faults of the processes occur and the outliers are measured.

This paper proposes modified storm brain optimization (MBSO) for load adjustment distribution state estimation (DSE) using correntropy. Minimization of sum of square errors by a weighted least squares (WLS) method has a problem when outliers exit in measured values. This problem can be solved by correntropy. Practical equipment in distribution systems causes nonlinear characteristics in an objective function and evolutionary computation methods such as Particle Swarm Optimization (PSO), hybrid PSO (HPSO) and differential evolutionary PSO (DEEPSO) have been applied to DSE so far. However, there is still room for improvement on estimation accuracy. The proposed method is applied to a typical distribution model system. The results indicate that the proposed method can improve estimation accuracy than the conventional DEEPSO and original BSO based method.