Four-phase generative-AI physics workflow: video generation, Tracker tracking, Excel Solver curve fitting, parameter validation

Design · All designs
Evidence · 5 claims (5 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 5 claims rest on one study

Description

A replicable instructional workflow combining generative-AI video platforms (PixVerse.ai, Grok Imagine, Pippit), the open-source Tracker video analysis tool, and the Microsoft Excel Solver GRG Nonlinear algorithm. As the article states, "The proposed workflow is organized into four sequential phases: (i) generation of synthetic videos using generative AI, (ii) extraction of kinematic data throug video analysis with software Tracker, (iii) estimation of model parameters by means of non-linear curve fitting, and (iv) identification and validation of the recovered physical parameters." It functions as a virtual laboratory mirroring experimental practice from model construction to quantitative validation.

Design Implications

Context

Requirements

• Access to generative-AI video platforms, the Tracker open-source video analysis tool, and the Excel Solver add-in with the GRG Nonlinear algorithm

Constraints

• The agreement achieved is approximate rather than exact, since videos are generated from natural-language descriptions rather than explicit physical equations

Target Learners

• introductory engineering physics students

Learning Goals

• experimental design
• data acquisition
• parameter estimation
• model evaluation
• modelling of physical systems

Claims

• Ai Generated Video Trajectories Fit Resistive Force Models [+M]
• The authors observe that more specific physical descriptions in generation prompts tend to produce more physically coherent AI-generated motion [+W]
• The linear-drag AI video yields a fitted glycerin viscosity (≈ 0.234 Pa·s) consistent with an aqueous glycerin solution of about 85% by weight [+W]
• The quadratic-drag AI video yields a fitted drag coefficient (CD ≈ 3.18) within the literature range reported for skydivers [+W]
• The constant-friction AI video yields a fitted friction coefficient (µ ≈ 0.169) consistent with literature values for wood on smooth or waxed surfaces [+W]

Related Designs

Examples

-

Key Sources

• Laura B. Alvarado-Cruz, Josep Ll. Suñer, Pedro Yuste, Juan C. Castro-Palacio, Juan A. Monsoriu, and Francisco M. Muñoz-Pérez. (2026). From Prompts to Physical Laws: A Generative AI Workflow for Engineering Physics Education. https://arxiv.org/abs/2609.19400

Page metadata

Field	Value
type	design
id	genai-video-tracking-fitting-workflow
title	Four-phase generative-AI physics workflow: video generation, Tracker tracking, Excel Solver curve fitting, parameter validation
description	A replicable instructional workflow combining generative-AI video platforms (PixVerse.ai, Grok Imagine, Pippit), the open-source Tracker video analysis tool, and the Microsoft Excel Solver GRG Nonlinear algorithm.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — laura-b-alvarado-cruz-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.