Nigel Morris
Nigel Morris has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Adrian Butscher
2 shared publications- Pradeep Kumar Jayaraman
School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore
2 shared publications - Aditya Sanghi
Autodesk Research Autodesk Research Autodesk Research Autodesk Research Autodesk Research University
1 shared publication - Adrian Butscher
661 University Avenue Autodesk Research Toronto, ON, M5G 1M1
1 shared publication - Adrian Humphry
Institute for Aerospace Studies University of Toronto Toronto Ontario Canada
1 shared publication Adrian Tatnall
1 shared publication
Latest Publications
- 7 October 2025
- Published by Elsevier in Computers & Structures
- Vol. 319
An interface-preserving level set update strategy for topology optimisation of mechanical assemblies
- 7 October 2025
- Published by Elsevier in Computers & Structures
- Vol. 319
An interface-preserving level set update strategy for topology optimisation of mechanical assemblies
- Top Cited Papers
- 16 January 2025
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 25 (2) , 1-12
Elicitron: A Large Language Model Agent-Based Simulation Framework for Design Requirements Elicitation
Requirement elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of user expectations. This article introduces a novel framework that leverages large language models (LLMs) to automate and enhance the requirement elicitation process. LLMs are used to generate a vast array of simulated users (LLM agents), enabling the exploration of a much broader range of user needs and unforeseen use cases. These agents engage in product experience scenarios, explaining their actions, observations, and challenges. Subsequent agent interviews and analysis uncover valuable user needs, including latent ones. We validate our framework with three experiments. First, we explore different methodologies for the challenge of diverse agent generation, discussing their advantages and shortcomings. We measure the diversity of identified user needs and demonstrate that context-aware agent generation leads to greater diversity. Second, we show how our framework effectively mimics empathic lead user interviews, identifying a greater number of latent needs than conventional human interviews. Third, we show that LLMs can be used to analyze interviews, capture needs, and classify them as latent or not. Our work highlights the potential of using LLMs to accelerate early-stage product development with minimal costs and increase innovation.
- 16 January 2025
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 25 (2) , 1-12
Top Cited PapersElicitron: A Large Language Model Agent-Based Simulation Framework for Design Requirements Elicitation
Requirement elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of user expectations. This article introduces a novel framework that leverages large language models (LLMs) to automate and enhance the requirement elicitation process. LLMs are used to generate a vast array of simulated users (LLM agents), enabling the exploration of a much broader range of user needs and unforeseen use cases. These agents engage in product experience scenarios, explaining their actions, observations, and challenges. Subsequent agent interviews and analysis uncover valuable user needs, including latent ones. We validate our framework with three experiments. First, we explore different methodologies for the challenge of diverse agent generation, discussing their advantages and shortcomings. We measure the diversity of identified user needs and demonstrate that context-aware agent generation leads to greater diversity. Second, we show how our framework effectively mimics empathic lead user interviews, identifying a greater number of latent needs than conventional human interviews. Third, we show that LLMs can be used to analyze interviews, capture needs, and classify them as latent or not. Our work highlights the potential of using LLMs to accelerate early-stage product development with minimal costs and increase innovation.
- Open Access
SolidGen: An Autoregressive Model for Direct B-rep Synthesis
The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling sequences that are executed by a solid modeling kernel in postprocess to recover a B-rep. In this paper we present a new approach that enables learning from and synthesizing B-reps without the need for supervision through CAD modeling sequence data. Our method SolidGen, is an autoregressive neural network that models the B-rep directly by predicting the vertices, edges, and faces using Transformer-based and pointer neural networks. Key to achieving this is our Indexed Boundary Representation that references B-rep vertices, edges and faces in a well-defined hierarchy to capture the geometric and topological relations suitable for use with machine learning. SolidGen can be easily conditioned on contexts e.g., class labels, images, and voxels thanks to its probabilistic modeling of the B-rep distribution. We demonstrate qualitatively, quantitatively, and through perceptual evaluation by human subjects that SolidGen can produce high quality, realistic CAD models.
Open AccessSolidGen: An Autoregressive Model for Direct B-rep Synthesis
The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling sequences that are executed by a solid modeling kernel in postprocess to recover a B-rep. In this paper we present a new approach that enables learning from and synthesizing B-reps without the need for supervision through CAD modeling sequence data. Our method SolidGen, is an autoregressive neural network that models the B-rep directly by predicting the vertices, edges, and faces using Transformer-based and pointer neural networks. Key to achieving this is our Indexed Boundary Representation that references B-rep vertices, edges and faces in a well-defined hierarchy to capture the geometric and topological relations suitable for use with machine learning. SolidGen can be easily conditioned on contexts e.g., class labels, images, and voxels thanks to its probabilistic modeling of the B-rep distribution. We demonstrate qualitatively, quantitatively, and through perceptual evaluation by human subjects that SolidGen can produce high quality, realistic CAD models.
- 23 November 2022
- Published by Elsevier in Computer-Aided Design
- Vol. 156
BeNTO: Beam Network Topology Optimization
- 23 November 2022
- Published by Elsevier in Computer-Aided Design
- Vol. 156
BeNTO: Beam Network Topology Optimization
- 15 February 2020
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 61 (4) , 1573-1588
A subtractive manufacturing constraint for level set topology optimization
- 15 February 2020
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 61 (4) , 1573-1588
A subtractive manufacturing constraint for level set topology optimization
- 1 January 2009
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 47 (1) , 219-228
Dimensional Stability Testing on a Space Optical Bench Structure
High-performance space-based optical systems typically require structures that exhibit high levels of dimensional stability over their lifetimes. To better understand the mechanisms for dimensional instability, a novel series of tests were carried out at Rutherford Appleton Laboratory on a breadboard high-stability optical bench structure. Goals of the testing were to assess the relative stability of a pair of reference surfaces and to determine the contributions of various structural elements and joints to dimensional instability. The breadboard was subject to an intensive environmental test campaign that included thermal cycling under vacuum and random vibration testing. Metrology was performed throughout the campaign to assess the dimensional stability response to the various environmental loads. The metrology requirement was challenging, with measurements of micron-level displacement and arcsecond-level tilt over 1-meter distances being necessary in situ during environmental testing. This issue was resolved using a combination of techniques: a contacting coordinate measurement machine, laser interferometry, and optical autocollimation. The greatest levels of instability were produced by random vibration testing, though evidence of a bedding-in process implies that vibratory conditioning could be used to improve stability. Copyright © 2008 by the American Institute of Aeronautics and Astronautics. Inc. All rights reserved
- 1 January 2009
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 47 (1) , 219-228
Dimensional Stability Testing on a Space Optical Bench Structure
High-performance space-based optical systems typically require structures that exhibit high levels of dimensional stability over their lifetimes. To better understand the mechanisms for dimensional instability, a novel series of tests were carried out at Rutherford Appleton Laboratory on a breadboard high-stability optical bench structure. Goals of the testing were to assess the relative stability of a pair of reference surfaces and to determine the contributions of various structural elements and joints to dimensional instability. The breadboard was subject to an intensive environmental test campaign that included thermal cycling under vacuum and random vibration testing. Metrology was performed throughout the campaign to assess the dimensional stability response to the various environmental loads. The metrology requirement was challenging, with measurements of micron-level displacement and arcsecond-level tilt over 1-meter distances being necessary in situ during environmental testing. This issue was resolved using a combination of techniques: a contacting coordinate measurement machine, laser interferometry, and optical autocollimation. The greatest levels of instability were produced by random vibration testing, though evidence of a bedding-in process implies that vibratory conditioning could be used to improve stability. Copyright © 2008 by the American Institute of Aeronautics and Astronautics. Inc. All rights reserved
- Open Access
- 25 May 2004
- Published by Association for Computing Machinery (ACM)
- p. 175-178
Temporal Thumbnails
- 25 May 2004
- Published by Association for Computing Machinery (ACM)
- p. 175-178
Open AccessTemporal Thumbnails