Search

With the rapid advancement of robotics technology, an increasing number of researchers are exploring the use of natural language as a communication channel between humans and robots. In scenarios where language conditioned manipulation grounding, prevailing methods rely heavily on supervised multimodal deep learning. In this paradigm, robots assimilate knowledge from both language instructions and visual input. However, these approaches lack external knowledge for comprehending natural language instructions and are hindered by the substantial demand for a large amount of paired data, where vision and language are usually linked through manual annotation for the creation of realistic datasets. To address the above problems, we propose the knowledge enhanced bottom-up affordance grounding network (KBAG-Net), which enhances natural language understanding through external knowledge, improving accuracy in object grasping affordance segmentation. In addition, we introduce a semi-automatic data generation method aimed at facilitating the quick establishment of the language following manipulation grounding dataset. The experimental results on two standard dataset demonstrate that our method outperforms existing methods with the external knowledge. Specifically, our method outperforms the two-stage method by 12.98% and 1.22% of mIoU on the two dataset, respectively. For broader community engagement, we will make the semi-automatic data construction method publicly available at https://github.com/wmqu/Automated-Dataset-Construction4LGM. [ABSTRACT FROM AUTHOR]

The integration of language and vision for object affordance understanding is pivotal for the advancement of embodied agents. Current approaches are often limited by reliance on segregated pre-processing stages for language interpretation and object localization, leading to inefficiencies and error propagation in affordance segmentation. To overcome these limitations, this study introduces a unique task, part-level affordance grounding, in direct response to natural language instructions. We present the Instruction-based Affordance Grounding Network (IAG-Net), a novel architecture that unifies language–vision interactions through a varied-scale multimodal attention mechanism. Unlike existing models, IAG-Net employs two textual–visual feature fusion strategies, capturing both sentence-level and task-specific textual features alongside multiscale visual features for precise and efficient affordance prediction. Our evaluation on two newly constructed vision–language affordance datasets, ITT-AFF VL and UMD VL, demonstrates a significant leap in performance, with an improvement of 11.78% and 0.42% in mean Intersection over Union (mIoU) over cascaded models, bolstering both accuracy and processing speed. We contribute to the research community by releasing our source code and datasets, fostering further innovation and replication of our findings. [ABSTRACT FROM AUTHOR]

OBJECTIVES Ion-adsorption type rare earth ore is extremely important in China and rare in the world. It is China's dominant mineral resource. At present, all the rare earth elements in the existing REE reference materials are oxide minerals, not ion-adsorption type, and cannot be exchanged with strong electrolytes. These reference materials cannot be used to monitor the leaching process of ion-adsorption type REE. METHODS The samples were collected from the typical ion-adsorption type REE weathering crust in Jiangxi Province. After being dried and ball-milled to 200 mesh, they were mixed for 1.5h. The contents of rare earth elements in the ionic phase were analyzed to test the homogeneity by ammonium sulfate leaching and inductively coupled plasma-mass spectrometry (ICP-MS). RESULTS Results showed that the F values for the variance test were less than the threshold, which indicated a good homogeneity. The stability of monitoring samples was tested 4 times in two years, and no statistically significant changes were observed, indicating good stability of the samples. An accurate and reliable leaching analytical method was used in 8 technologically significant laboratories to finalize the contents of ionic phase rare earth elements. The determined values of nine monitoring samples were given by statistical calculation, including weighted average value and total uncertainty results which were from uncertainties in certified values, between-bottle homogeneity and long-term stability. These nine monitoring samples have certified values of 15 ionic phase rare earth elements except Sc. CONCLUSIONS The reference materials can be used to monitor the leaching process and provide metrological support for the analysis of rare earth elements in ionic phase during the evaluation and effective utilization of REE mineral resources.

BACKGROUND Strategic critical metal mineral resources including rare, dispersed, rare earth and platinum group elements play an increasingly critical role in emerging industries such as new materials, new energy and information technology. With the deepening of the geological survey of key mineral resources in China, the critical metal elements present new challenges to analytical techniques due to their complex matrix, large differences in different mineral contents, and unstable chemical properties. OBJECTIVES To introduce recent analytical techniques and applications for critical metal elements in different types of geological samples. METHODS Based on different chemical composition, the main matrices of critical metal elements were classified, mainly divided into silicate, carbonate, sulfate, tungstate, phosphate, oxide, sulfide and halide. For different types of rocks and minerals, chemical digestion was largely carried out by traditional dissolution methods such as the acid dissolution method (nitric acid-hydrofluoric acid combination, aqua regia) or alkali fusion methods. RESULTS The characteristics and application of commonly used instruments including electronic probe microanalyzer, inductively coupled plasma-mass spectrometry, inductively coupled plasma-optical emission spectroscopy, and X-ray fluorescence spectroscopy were reviewed. The problems during critical metal analysis including incomplete dissolution, low recovery, oxides and isobaric interference, inconsistency between samples and standard matrices were reviewed and corresponding solutions were proposed. CONCLUSIONS In situ microanalysis with the advantages of high efficiency, low cost, and high spatial resolution, and field on-site geoanalysis with its simple, fast and close to field work features are the main trends in the development of critical metal elements analytical techniques.