skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.
Attention:The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 7:00 AM ET to 7:30 AM ET on Friday, April 24 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: LEVIOSA: Natural Language-Based Uncrewed Aerial Vehicle Trajectory Generation
This paper presents LEVIOSA, a novel framework for text- and speech-based uncrewed aerial vehicle (UAV) trajectory generation. By leveraging multimodal large language models (LLMs) to interpret natural language commands, the system converts text and audio inputs into executable flight paths for UAV swarms. The approach aims to simplify the complex task of multi-UAV trajectory generation, which has significant applications in fields such as search and rescue, agriculture, infrastructure inspection, and entertainment. The framework involves two key innovations: a multi-critic consensus mechanism to evaluate trajectory quality and a hierarchical prompt structuring for improved task execution. The innovations ensure fidelity to user goals. The framework integrates several multimodal LLMs for high-level planning, converting natural language inputs into 3D waypoints that guide UAV movements and per-UAV low-level controllers to control each UAV in executing its assigned 3D waypoint path based on the high-level plan. The methodology was tested on various trajectory types with promising accuracy, synchronization, and collision avoidance results. The findings pave the way for more intuitive human–robot interactions and advanced multi-UAV coordination.  more » « less
Award ID(s):
2138206
PAR ID:
10637601
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Electronics
Volume:
13
Issue:
22
ISSN:
2079-9292
Page Range / eLocation ID:
4508
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, American Society of Mechanical Engineers)
    The evolution of multimodal large language models (LLMs) capable of processing diverse input modalities (e.g., text and images) holds new prospects for their application in engineering design, such as the generation of 3D computer-aided design (CAD) models. However, little is known about the ability of multimodal LLMs to generate 3D design objects, and there is a lack of quantitative assessment. In this study, we develop an approach to enable two LLMs, GPT-4 and GPT-4V, to generate 3D CAD models (i.e., LLM4CAD) and perform experiments to evaluate their efficacy. To address the challenge of data scarcity for multimodal LLM studies, we created a data synthesis pipeline to generate CAD models, sketches, and image data of typical mechanical components (e.g., gears and springs) and collect their natural-language descriptions with dimensional information using Amazon Mechanical Turk. We positioned the CAD program (programming script for CAD design) as a bridge, facilitating the conversion of LLMs’ textual output into tangible CAD design objects. We focus on two critical capabilities: the generation of syntactically correct CAD programs (Cap1) and the accuracy of the parsed 3D shapes (Cap2) quantified by intersection over union. The results show that both GPT-4 and GPT-4V demonstrate potential in 3D CAD generation. Specifically, on average, GPT-4V outperforms when processing only text-based input, exceeding the results obtained using multimodal inputs, such as text with image, for Cap 1 and Cap 2. However, when examining category-specific results of mechanical components, while the same trend still holds for Cap 2, the prominence of multimodal inputs is increasingly evident for more complex geometries (e.g., springs and gears) in Cap 1. The potential of multimodal LLMs in enhancing 3D CAD generation is clear, but their application must be carefully calibrated to the complexity of the target CAD models to be generated. 
    more » « less
  2. ; ; (, Journal of Computing and Information Science in Engineering)
    The evolution of multimodal large language models (LLMs) capable of processing diverse input modalities (e.g., text and images) holds new prospects for their application in engineering design, such as the generation of 3D computer-aided design (CAD) models. However, little is known about the ability of multimodal LLMs to generate 3D design objects, and there is a lack of quantitative assessment. In this study, we develop an approach to enable LLMs to generate 3D CAD models (i.e., LLM4CAD) and perform experiments to evaluate their efficacy where GPT-4 and GPT-4V were employed as examples. To address the challenge of data scarcity for multimodal LLM studies, we created a data synthesis pipeline to generate CAD models, sketches, and image data of typical mechanical components (e.g., gears and springs) and collect their natural language descriptions with dimensional information using Amazon Mechanical Turk. We positioned the CAD program (programming script for CAD design) as a bridge, facilitating the conversion of LLMs’ textual output into tangible CAD design objects. We focus on two critical capabilities: the generation of syntactically correct CAD programs (Cap1) and the accuracy of the parsed 3D shapes (Cap2) quantified by intersection over union. The results show that both GPT-4 and GPT-4V demonstrate great potential in 3D CAD generation by just leveraging their zero-shot learning ability. Specifically, on average, GPT-4V outperforms when processing only text-based input, exceeding the results obtained using multimodal inputs, such as text with image, for Cap 1 and Cap 2. However, when examining category-specific results of mechanical components, the prominence of multimodal inputs is increasingly evident for more complex geometries (e.g., springs and gears) in both Cap 1 and Cap 2. The potential of multimodal LLMs to improve 3D CAD generation is clear, but their application must be carefully calibrated to the complexity of the target CAD models to be generated. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging techniques such as prompt tuning to enable LLMs for recommendation tasks. Meanwhile, research interest has recently grown in multimodal recommendation systems that integrate data from images, text, and other sources using modality fusion techniques. This introduces new challenges to the existing LLM-based recommendation paradigm which relies solely on text modality information. Moreover, although Multimodal Large Language Models (MLLMs) capable of processing multi-modal inputs have emerged, how to equip MLLMs with multi-modal recommendation capabilities remains largely unexplored. To this end, in this paper, we propose the Multimodal Large Language Model-enhanced Sequential Multimodal Recommendation (MLLM-MSR) model. To capture the dynamic user preference, we design a two-stage user preference summarization method. Specifically, we first utilize an MLLM-based item-summarizer to extract image feature given an item and convert the image into text. Then, we employ a recurrent user preference summarization generation paradigm to capture the dynamic changes in user preferences based on an LLM-based user-summarizer. Finally, to enable the MLLM for multi-modal recommendation task, we propose to fine-tune a MLLM-based recommender using Supervised Fine-Tuning (SFT) techniques. Extensive evaluations across various datasets validate the effectiveness of MLLM-MSR, showcasing its superior ability to capture and adapt to the evolving dynamics of user preferences. 
    more » « less
  4. ; ; (, Journal of Mechanical Design)
    Despite the power of large language models (LLMs) in various cross-modal generation tasks, their ability to generate 3D computer-aided design (CAD) models from text remains underexplored due to the scarcity of suitable datasets. Additionally, there is a lack of multimodal CAD datasets that include both reconstruction parameters and text descriptions, which are essential for the quantitative evaluation of the CAD generation capabilities of multimodal LLMs. To address these challenges, we developed a dataset of CAD models, sketches, and image data for representative mechanical components such as gears, shafts, and springs, along with natural language descriptions collected via Amazon Mechanical Turk. By using CAD programs as a bridge, we facilitate the conversion of textual output from LLMs into precise 3D CAD designs. To enhance the text-to-CAD generation capabilities of GPT models and demonstrate the utility of our dataset, we developed a pipeline to generate fine-tuning training data for GPT-3.5. We fine-tuned four GPT-3.5 models with various data sampling strategies based on the length of a CAD program. We evaluated these models using parsing rate and intersection over union (IoU) metrics, comparing their performance to that of GPT-4 without fine-tuning. The new knowledge gained from the comparative study on the four different fine-tuned models provided us with guidance on the selection of sampling strategies to build training datasets in fine-tuning practices of LLMs for text-to-CAD generation, considering the trade-off between part complexity, model performance, and cost. 
    more » « less
  5. ; ; ; ; (, Mathematics)
    This paper introduces Harmonizer, a universal framework designed for tokenizing heterogeneous input signals, including text, audio, and video, to enable seamless integration into multimodal large language models (LLMs). Harmonizer employs a unified approach to convert diverse, non-linguistic signals into discrete tokens via its FusionQuantizer architecture, built on FluxFormer, to efficiently capture essential signal features while minimizing complexity. We enhance features through STFT-based spectral decomposition, Hilbert transform analytic signal extraction, and SCLAHE spectrogram contrast optimization, and train using a composite loss function to produce reliable embeddings and construct a robust vector vocabulary. Experimental validation on music datasets such as E-GMD v1.0.0, Maestro v3.0.0, and GTZAN demonstrates high fidelity across 288 s of vocal signals (MSE = 0.0037, CC = 0.9282, Cosine Sim. = 0.9278, DTW = 12.12, MFCC Sim. = 0.9997, Spectral Conv. = 0.2485). Preliminary tests on text reconstruction and UCF-101 video clips further confirm Harmonizer’s applicability across discrete and spatiotemporal modalities. Rooted in the universality of wave phenomena and Fourier theory, Harmonizer offers a physics-inspired, modality-agnostic fusion mechanism via wave superposition and interference principles. In summary, Harmonizer integrates natural language processing and signal processing into a coherent tokenization paradigm for efficient, interpretable multimodal learning. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email