W e introduce F oreSight, a novel joint detection and forecasting framework for vision-based 3D perception in autonomous vehicles. Traditional approaches treat detection and forecasting as separate sequential tasks, limiting their ability to leverage temporal cues. F oreSight addresses this limitation with a multi-task streaming and bidirectional learning approach, allowing detection and forecasting to share query memory and propagate information seamlessly. The forecast-aware detection transformer enhances spatial reasoning by integrating trajectory predictions from a multiple hypothesis forecast memory queue, while the streaming forecast transformer improves temporal consistency using past forecasts and refined detections. Unlike tracking-based methods, F oreSight eliminates the need for explicit object association, reducing error propagation with a tracking-free model that efficiently scales across multi-frame sequences. Experiments on the nuScenes dataset show that F oreSight achieves state-of-the-art performance, achieving an EP A of 54.9%, surpassing previous methods by 9.3%, while also attaining the best mAP and minADE among multi-view detection and forecasting models.

Homelessness in the United States has surged to levels unseen since the Great Depression. However, existing methods for monitoring it, such as point-in-time (PIT) counts, have limitations in terms of frequency, consistency, and spatial detail. This study proposes a new approach using publicly available, crowdsourced data, specifically 311 Service Calls and street-level imagery, to track and forecast homeless tent trends in San Francisco. Our predictive model captures fine-grained daily and neighborhood-level variations, uncovering patterns that traditional counts often overlook, such as rapid fluctuations during the COVID-19 pandemic and spatial shifts in tent locations over time. By providing more timely, localized, and cost-effective information, this approach serves as a valuable tool for guiding policy responses and evaluating interventions aimed at reducing unsheltered homelessness.

Hyperspectral satellite imagery offers sub-30 m views of Earth in hundreds of contiguous spectral bands, enabling fine-grained mapping of soils, crops, and land cover. While self-supervised Masked Autoencoders excel on RGB and low-band multispectral data, they struggle to exploit the intricate spatial-spectral correlations in 200+ band hyperspectral images. We introduce TerraMAE, a novel HSI encoding framework specifically designed to learn highly representative spatial-spectral embeddings for diverse geospatial analyses. TerraMAE features an adaptive channel grouping strategy, based on statistical reflectance properties to capture spectral similarities, and an enhanced reconstruction loss function that incorporates spatial and spectral quality metrics. We demonstrate TerraMAE's effectiveness through superior spatial-spectral information preservation in high-fidelity image reconstruction. Furthermore, we validate its practical utility and the quality of its learned representations through strong performance on three key downstream geospatial tasks: crop identification, land cover classification, and soil texture prediction.

Autonomous navigation in mobile robots, reliant on perception and planning, faces major hurdles in large-scale, complex environments. These include heavy computational burdens for mapping, sensor occlusion failures for UAVs, and traversal challenges on irregular terrain for UGVs, all compounded by a lack of perception-aware strategies. To address these challenges, we introduce Random Mapping and Random Projection (RMRP). This method constructs a lightweight linear parametric map by first mapping data to a high-dimensional space, followed by a sparse random projection for dimensionality reduction. Our novel Residual Energy Preservation Theorem provides theoretical guarantees for this process, ensuring critical geometric properties are preserved. Based on this map, we propose the RPATR (Robust Perception-Aware Trajectory Planner) framework. For UAVs, our method unifies grid and Euclidean Signed Distance Field (ESDF) maps. The front-end uses an analytical occupancy gradient to refine initial paths for safety and smoothness, while the back-end uses a closed-form ESDF for trajectory optimization. Leveraging the trained RMRP model's generalization, the planner predicts unobserved areas for proactive navigation. For UGVs, the model characterizes terrain and provides closed-form gradients, enabling online planning to circumvent large holes. Validated in diverse scenarios, our framework demonstrates superior mapping performance in time, memory, and accuracy, and enables computationally efficient, safe navigation for high-speed UAVs and UGVs. The code will be released to foster community collaboration.

Autonomous web-based geographical information systems (AWebGIS) aim to perform geospatial operations from natural language input, providing intuitive, intelligent, and hands-free interaction. However, most current solutions rely on cloud-based large language models (LLMs), which require continuous internet access and raise users' privacy and scalability issues due to centralized server processing. This study compares three approaches to enabling AWebGIS: (1) a fully-automated online method using cloud-based LLMs (e.g., Cohere); (2) a semi-automated offline method using classical machine learning classifiers such as support vector machine and random forest; and (3) a fully autonomous offline (client-side) method based on a fine-tuned small language model (SLM), specifically T5-small model, executed in the client's web browser. The third approach, which leverages SLMs, achieved the highest accuracy among all methods, with an exact matching accuracy of 0.93, Levenshtein similarity of 0.99, and recall-oriented understudy for gisting evaluation ROUGE-1 and ROUGE-L scores of 0.98. Crucially, this client-side computation strategy reduces the load on backend servers by offloading processing to the user's device, eliminating the need for server-based inference. These results highlight the feasibility of browser-executable models for AWebGIS solutions.

Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to generalize across object types, spatial layouts, and manipulator configurations. We propose Graph-Fused Vision-Language-Action (GF-VLA), a framework that enables dual-arm robotic systems to perform task-level reasoning and execution directly from RGB and Depth human demonstrations. GF-VLA first extracts Shannon-information-based cues to identify hands and objects with the highest task relevance, then encodes these cues into temporally ordered scene graphs that capture both hand-object and object-object interactions. These graphs are fused with a language-conditioned transformer that generates hierarchical behavior trees and interpretable Cartesian motion commands. To improve execution efficiency in bimanual settings, we further introduce a cross-hand selection policy that infers optimal gripper assignment without explicit geometric reasoning. We evaluate GF-VLA on four structured dual-arm block assembly tasks involving symbolic shape construction and spatial generalization. Experimental results show that the information-theoretic scene representation achieves over 95 percent graph accuracy and 93 percent subtask segmentation, supporting the LLM planner in generating reliable and human-readable task policies. When executed by the dual-arm robot, these policies yield 94 percent grasp success, 89 percent placement accuracy, and 90 percent overall task success across stacking, letter-building, and geometric reconfiguration scenarios, demonstrating strong generalization and robustness across diverse spatial and semantic variations.

We explore the application of large language models (LLMs) to empower domain experts in integrating large, heterogeneous, and noisy urban spatial datasets. Traditional rule-based integration methods are unable to cover all edge cases, requiring manual verification and repair. Machine learning approaches require collecting and labeling of large numbers of task-specific samples. In this study, we investigate the potential of LLMs for spatial data integration. Our analysis first considers how LLMs reason about environmental spatial relationships mediated by human experience, such as between roads and sidewalks. We show that while LLMs exhibit spatial reasoning capabilities, they struggle to connect the macro-scale environment with the relevant computational geometry tasks, often producing logically incoherent responses. But when provided relevant features, thereby reducing dependence on spatial reasoning, LLMs are able to generate high-performing results. We then adapt a review-and-refine method, which proves remarkably effective in correcting erroneous initial responses while preserving accurate responses. We discuss practical implications of employing LLMs for spatial data integration in real-world contexts and outline future research directions, including post-training, multi-modal integration methods, and support for diverse data formats. Our findings position LLMs as a promising and flexible alternative to traditional rule-based heuristics, advancing the capabilities of adaptive spatial data integration.

For tourists visiting South Korea, one of the world's most technologically advanced nations, navigating the country's urban heartlands can prove surprisingly frustrating for one simple reason: Google Maps just doesn't work effectively. But on 11 August that could change, as South Korean authorities are set to decide whether to finally grant Google's request to export the country's detailed mapping data to overseas servers. Such a move would open up functionality that allows the app to give detailed directions and show users the best routes to travel. It is a debate spanning nearly two decades which has evolved into a broader test of how democracies balance digital sovereignty with economic openness. Local industry groups are warning of market domination from foreign companies, while those who back Google's request argue restrictions harm tourism and innovation.

Collecting real-world data for rare high-risk scenarios, long-tailed driving events, and complex interactions remains challenging, leading to poor performance of existing autonomous driving systems in these critical situations. In this paper, we propose RoboTron-Sim that improves real-world driving in critical situations by utilizing simulated hard cases. First, we develop a simulated dataset called Hard-case Augmented Synthetic Scenarios (HASS), which covers 13 high-risk edge-case categories, as well as balanced environmental conditions such as day/night and sunny/rainy. Second, we introduce Scenario-aware Prompt Engineering (SPE) and an Image-to-Ego Encoder (I2E Encoder) to enable multimodal large language models to effectively learn real-world challenging driving skills from HASS, via adapting to environmental deviations and hardware differences between real-world and simulated scenarios. Extensive experiments on nuScenes show that RoboTron-Sim improves driving performance in challenging scenarios by around 50%, achieving state-of-the-art results in real-world open-loop planning. Qualitative results further demonstrate the effectiveness of RoboTron-Sim in better managing rare high-risk driving scenarios. Project page: https://stars79689.github.io/RoboTron-Sim/

Embodied navigation is a fundamental capability of embodied intelligence, enabling robots to move and interact within physical environments. However, existing navigation tasks primarily focus on predefined object navigation or instruction following, which significantly differs from human needs in real-world scenarios involving complex, open-ended scenes. To bridge this gap, we introduce a challenging long-horizon navigation task that requires understanding high-level human instructions and performing spatial-aware object navigation in real-world environments. Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary. In this paper, we propose $NavA^3$, a hierarchical framework divided into two stages: global and local policies. In the global policy, we leverage the reasoning capabilities of Reasoning-VLM to parse high-level human instructions and integrate them with global 3D scene views. This allows us to reason and navigate to regions most likely to contain the goal object. In the local policy, we have collected a dataset of 1.0 million samples of spatial-aware object affordances to train the NaviAfford model (PointingVLM), which provides robust open-vocabulary object localization and spatial awareness for precise goal identification and navigation in complex environments. Extensive experiments demonstrate that $NavA^3$ achieves SOTA results in navigation performance and can successfully complete longhorizon navigation tasks across different robot embodiments in real-world settings, paving the way for universal embodied navigation. The dataset and code will be made available. Project website: https://NavigationA3.github.io/.