Anurag Purwar

About

Anurag Purwar is an Associate Professor at the Department of Mechanical Engineering at Stony Brook University. He holds a Ph.D. from Stony Brook University obtained in 2005. His research focuses on CAD/CAM, computational kinematics, design automation, mechanisms and robotics, virtual reality applications in science and engineering, and design education. His work involves developing advanced computational methods and tools to enhance design processes and robotic systems, contributing to the fields of mechanical design and automation.

Research topics

• Artificial Intelligence
• Computer Science
• Theoretical computer science
• Mathematics
• Geometry
• Algorithm
• Library science
• Engineering

Selected publications

• An Image-Based Approach to Variational Path Synthesis of Linkages

  Journal of Computing and Information Science in Engineering · 2020 · 27 citations

  Senior authorCorresponding

  Abstract This paper brings together computer vision, mechanism synthesis, and machine learning to create an image-based variational path synthesis approach for linkage mechanisms. An image-based approach is particularly amenable to mechanism synthesis when the input from mechanism designers is deliberately imprecise or inherently uncertain due to the nature of the problem. In addition, it also lends itself naturally to the creation of a unified approach to mechanism synthesis for different types…

  DOI

• Deep Learning-Driven Design of Robot Mechanisms

  Journal of Computing and Information Science in Engineering · 2023 · 22 citations

  1st authorCorresponding

  Abstract In this paper, we discuss the convergence of recent advances in deep neural networks (DNNs) with the design of robotic mechanisms, which entails the conceptualization of the design problem as a learning problem from the space of design specifications to a parameterization of the space of mechanisms. We identify three key inter-related problems that are at the forefront of using the versatility of DNNs in solving mechanism design problems. The first problem is that of representation of m…

  DOI

• A Dataset of 3M Single-DOF Planar 4-, 6-, and 8-Bar Linkage Mechanisms With Open and Closed Coupler Curves for Machine Learning-Driven Path Synthesis

  Journal of Mechanical Design · 2024-10-28 · 11 citations

  articleSenior author

  Abstract In recent years, there has been a strong interest in applying machine learning techniques to path synthesis of linkage mechanisms. However, progress has been stymied due to a scarcity of high-quality datasets. In this article, we present a comprehensive dataset comprising nearly three million samples of 4-, 6-, and 8-bar linkage mechanisms with open and closed coupler curves. Current machine learning approaches to path synthesis also lack standardized metrics for evaluating outcomes. To…

  PublisherDOI

• Deep Learning Conceptual Design of Sit-to-Stand Parallel Motion Six-Bar Mechanisms

  Journal of Mechanical Design · 2024-07-19 · 9 citations

  articleSenior author

  Abstract The sit-to-stand (STS) motion is a crucial activity in the daily lives of individuals, and its impairment can significantly impact independence and mobility, particularly among disabled individuals. Addressing this challenge necessitates the design of mobility assist devices that can simultaneously satisfy multiple conflicting constraints. The effective design of such devices often involves the generation of numerous conceptual mechanism designs. This paper introduces an innovative sing…

  PublisherDOI

• Path Generative Model Based on Conditional <i>β</i> -Variational Auto Encoder for Four-Bar Mechanism Design

  Journal of Mechanisms and Robotics · 2024-11-14 · 8 citations

  articleSenior author

  Abstract This article introduces a novel methodology based on conditional β-variational autoencoder (cβ-VAE) architecture to generate diverse types of planar four-bar mechanisms for a given coupler curve. Central to our contribution is the novel integration of cross- and self-attention layers within the VAE framework, facilitating an encoding and decoding process that captures the complex interdependencies of mechanism parameters and associated coupler curves. We propose a unified representation…

  PublisherDOI

Recent grants

• A Computational Framework for Data-Driven Mechanism Design Innovation

  NSF · $535k · 2016–2022

Frequent coauthors

• N. Saito

  The University of Tokyo

  479 shared

• M. Gonin

  Laboratoire Leprince-Ringuet

  462 shared

• L. Aphecetche

  IMT Atlantique

  462 shared

• X. He

  Beihang University

  450 shared

• K. Tanida

  450 shared

• Y. Goto

  Augustana University

  443 shared

• R. Granier de Cassagnac

  Laboratoire Leprince-Ringuet

  433 shared

• F. Staley

  422 shared

Education

• Ph.D., Mechanical Engineering

  Stony Brook University

  2010

• M.S., Mechanical Engineering

  Stony Brook University

  2006

• B.S., Mechanical Engineering

  Indian Institute of Technology (IIT) Kanpur

  2004

Awards & honors

• A.T. Yang award for the best paper in Theoretical Kinematics…
• MSC Software Simulation award for the best paper at the 2009…
• Presidential Award for Excellence in Teaching by Stony Brook…
• 2018 FACT2 award for Excellence in Instruction
• 2021 Distinguished Teaching Award from the American Society…

Similar researchers at Stony Brook University

• Lifeng Wangh-49
• Nilanjan Chakrabortyh-48
• William Stewarth-44