Navigating autonomous vehicles efficiently across unstructured and off-road terrains remains a formidable challenge, often requiring intricate mapping or multi-step pipelines. However, these conventional approaches struggle to adapt to dynamic environments. This paper presents TerrainSense, an end-to-end framework that overcomes these limitations. By utilizing a transformers, TerrainSense detects lane semantics and topology from camera images, enabling mapless path planning without the reliance on highly detailed maps. The efficacy of TerrainSense was rigorously assessed on six diverse datasets, evaluating its efficacy in detection, segmentation, and path prediction using various metrics. Notably, it outperforms the other state-of-the-art methods by 9.32% in precisely predicting the path with 18.28% faster inference time.

The efficient navigation of autonomous vehicles across rugged and unstructured terrains remains a significant challenge. Most existing research in this area emphasizes the need for complex mappings or intricate multi-step methodologies. However, these traditional approaches often struggle to adapt to dynamic changes in environmental conditions. In this paper, we introduce PathFormer, an end-to-end framework designed specifically to address these challenges. PathFormer utilizes transformers to decode free-space semantics and configurations directly from camera images, enabling efficient path planning without the reliance on detailed, pre-existing maps. The performance of PathFormer was rigorously evaluated across diverse datasets, where it demonstrated superior capabilities, outperforming other state-of-the-art methods by 3.68% in precisely segmenting free-space regions and showing a 13.65% improvement in correctly predicting traversable paths.

The digital transformation in the finance and enterprise sector has been driven by the advances made in big data and artificial intelligence technologies. For instance, data integration enables businesses to make better decisions by consolidating and mining heterogeneous data repositories. In particular, knowledge graphs (KGs) are used to facilitate the integration of disparate data sources and can be utilized to answer complex queries. This work proposes a new dataset for question-answering on knowledge graphs (KGQA) to reflect the challenges we identified in real-world applications which are not covered by existing benchmarks, namely, multi-hop constraints, numeric and literal embeddings, ranking, reification, and hyper-relations. To build the dataset, we create a new Knowledge Graph from the Crunchbase database using a lightweight schema to support high-quality entity embeddings in large graphs. Next, we create a Question Answering dataset based on natural language question generation using predefined multiple-hop templates and paraphrasing. Finally, we conduct extensive experiments with state-of-the-art KGQA models and compare their performance on CrunchQA. The results show that the existing models do not perform well, for example, on multi-hop constrained queries. Hence, CrunchQA can be used as a challenging benchmark dataset for future KGQA reasoning models. The dataset and scripts are available on the project repository.1

Knowledge Graph Question Answering (KGQA) models enable users to acquire entity-based answers from a Knowledge Graph by asking natural language questions (NLQs) without the need to learn a specialized graph query language or knowing the underlying schema of the knowledge graph. This work investigates hyperbolic graph representation learning methods to effectively and efficiently represent knowledge base items and natural questions. Our system, HyperKGQA, proposes a technique that embeds the knowledge graph in a hyperbolic manifold, then learns an adaptive transformation of pre-trained sentence representations into the space of entities and relations. Finally, a post-processing step refines the ranking of the candidate answers by computing the relevance score of the set of relations and the question. An extensive set of experiments conducted on two datasets shows that our method outperforms the current state-of-the-art models when reasoning over sparse graphs to answer multi-hop questions.

Over the last decade, robotics has experienced a rapid increase in research related to human-robot interaction. Developments in artificial skin research can equip robots with tactile sensing in a similar manner to the human sense of touch. This capability will make human-robot communication more natural and safer since an important part of perception indeed relies on tactile sensing. Electrical impedance tomography (EIT)-based sensors are considered as a potentially promising alternative for tactile sensing. These sensors can reconstruct images of the conductivity variation, which appear as a response to the applied pressure. However, due to the ill-posedness of the EIT inverse problem, reconstructed images have low spatial resolution and object boundaries are not preserved. In this research, we explore the hypothesis that performing image segmentation in conjunction with preserving the object boundaries may increase the accuracy of a subsequent classification of the reconstructed images. We compare the quality of EIT images segmented by a splitting and merging segmentation algorithm, Morphological Active Contours without Edges, Random Walker and transfer learning. While the explored classical techniques appear to have predilection towards over-segmentation, the deep learning approach results to a remarkable improvement of approximately 118% in terms of the similarity index.