Search for: All records

We introduce LAM, a system that explores collaboration between large language models and vision-language models to generate articulated objects from text prompts without a visual prior or prebuilt 3D assets. In contrast, we formulate articulated object generation as a unified code-generation task, in which geometry and articulations can be co-designed from scratch. Given an input text, LAM coordinates a team of specialized modules to generate code to represent the desired articulated object procedurally. LAM first reasons about the hierarchical structure of parts (links) with Link Designer, then writes code, compiles it, and debugs it with Geometry and Articulation Coders and self-corrects with Geometry and Articulation Checkers. The code serves as a structured, interpretable bridge between individual links, ensuring the correct relationships among them. Experiments demonstrate the power of leveraging code as a generative medium within a collaboration system, showcasing its effectiveness in automatically constructing complex articulated objects. 

Artificial Intelligence (AI)-aided vision-based Structural Health Monitoring (SHM) has emerged as an effective approach for monitoring and assessing structural condition by analyzing image and video data. By integrating Computer Vision (CV) and Deep Learning (DL), vision-based SHM can automatically identify and localize visual patterns associated with structural damage. However, previous works typically generate only discrete outputs, such as damage class labels and damage region coordinates, requiring engineers to further reorganize and analyze these results for evaluation and decision-making. In late 2022, Large Language Models (LLMs) became popular across multiple fields, providing new insights into AI-aided vision-based SHM. In this study, a novel LLM-based Disaster Reconnaissance Summarization (LLM-DRS) framework is proposed. It introduces a standard reconnaissance plan in which the collection of vision data and corresponding metadata follows a well-designed on-site investigation process. Text-based metadata and image-based vision data are then processed and integrated into a unified format, where well-trained Deep Convolutional Neural Networks extract key attributes, including damage state, material type, and damage level. Finally, all data are fed into an LLM with carefully designed prompts, enabling the LLM-DRS to generate summary reports for individual structures or affected regions based on aggregated attributes and metadata. Results show that integrating LLMs into vision-based SHM, particularly for rapid post-disaster reconnaissance, demonstrates promising potential for improving resilience of the built environment through effective reconnaissance. 

This work reports a platform based on ultrasound for mid-air particle manipulations using a 2×2 piezoelectric micromachined ultrasonic transducer (pMUT) array. Three achievements have been demonstrated as compared to the state-of-art: (1) high SPL (sound pressure level) of 120 dB at a distance 12 mm away by an individual lithium-niobate pMUT; (2) a numerically simulated and experimentally demonstrated 2D focal point control scheme by adjusting the phase-delay of individual pMUTs; and (3) the experimental demonstration of moving a 0.7 mg foam plastic particle of 12 mm away in the mid-air by ~1.8 mm. As such, this work shows the potential for practical applications in the broad fields of non-contact actuations, including particle manipulations in microfluidics, touchless haptic sensations, … etc. 

Microwave imaging has been a popular high resolution, non-invasive, and non-contact nondestructive testing (NDT) method for detecting defects and objects in non-metallic media with applications toward testing dielectric slabs, printed circuit board testing, biomedical diagnosis, etc. In this paper, we employ an array of microwave sensors designed based on the complementary split ring resonators (CSRR) along with nearfield holographic microwave imaging (NH-MWI) to assess the hidden features in the dielectric media. In this array, each element resonates at a different frequency in the range of 1 GHz to 10 GHz. Performance of the proposed method is demonstrated via simulation and experimental results.