Ziqi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ziqi Wang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Stelian Coros
ETH Zurich, Zurich, Switzerland
2 shared publications - Wenjun Liu
The Division of Integrative Systems and Design, Hong Kong University of Science and Technology, Hong Kong, China
2 shared publications - Yijiang Huang
ETH Zurich, Zurich, Switzerland
2 shared publications - Aurèle L. Gheyselinck1 shared publication
- Bailin Deng
Cardiff University, Wales, United Kingdom
1 shared publication - Bernhard Thomaszewski
ETH Zurich, Zurich, Switzerland
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Assembly-aware Tiling for Standing Polyominoes
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessAssembly-aware Tiling for Standing Polyominoes
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
PART: Learning 3D Part Assembly and Retrieval with Transformers
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessPART: Learning 3D Part Assembly and Retrieval with Transformers
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-16
Learning to Assemble with Alternative Plans
We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffolding to stabilize their intermediate assembly steps, making the process both labor-intensive and time-consuming. This work utilizes multiple robots to collaboratively assemble structures, offering temporary support by holding parts in place without additional scaffolding. Precomputing the robotic assembly process to ensure structural stability involves a time-consuming offline process due to the combinatorial nature of its search space. However, the precomputed assembly plans may get disrupted during real-world execution due to unforeseen changes, such as setup modifications or delays in part delivery. Recomputing these plans using traditional offline methods results in significant project delays. Therefore, we propose a reinforcement learning-based approach in which a neural network is trained to efficiently generate alternative assembly plans for a given structure online, enabling adaptation to external changes. To enable effective and efficient training, we introduce three key innovations: a GPU-based stability simulator for parallelizing simulations, a novel curriculum-based training scheme to address sparse rewards during training, and a new graph neural network architecture for efficiently encoding assembly geometry. We validate our approach by training reinforcement learning agents on various assemblies and evaluating their performance on unseen assembly tasks. Furthermore, we demonstrate the effectiveness of our framework in planning multi-robot assembly processes, effectively handling disruptions in both simulation and physical environments.
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-16
Open AccessLearning to Assemble with Alternative Plans
We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffolding to stabilize their intermediate assembly steps, making the process both labor-intensive and time-consuming. This work utilizes multiple robots to collaboratively assemble structures, offering temporary support by holding parts in place without additional scaffolding. Precomputing the robotic assembly process to ensure structural stability involves a time-consuming offline process due to the combinatorial nature of its search space. However, the precomputed assembly plans may get disrupted during real-world execution due to unforeseen changes, such as setup modifications or delays in part delivery. Recomputing these plans using traditional offline methods results in significant project delays. Therefore, we propose a reinforcement learning-based approach in which a neural network is trained to efficiently generate alternative assembly plans for a given structure online, enabling adaptation to external changes. To enable effective and efficient training, we introduce three key innovations: a GPU-based stability simulator for parallelizing simulations, a novel curriculum-based training scheme to address sparse rewards during training, and a new graph neural network architecture for efficiently encoding assembly geometry. We validate our approach by training reinforcement learning agents on various assemblies and evaluating their performance on unseen assembly tasks. Furthermore, we demonstrate the effectiveness of our framework in planning multi-robot assembly processes, effectively handling disruptions in both simulation and physical environments.
- Open Access
- 17 July 2025
- Published by Elsevier in Computer-Aided Design
- Vol. 188
Computational design and fabrication of reusable multi-tangent bar structures
- 17 July 2025
- Published by Elsevier in Computer-Aided Design
- Vol. 188
Open AccessComputational design and fabrication of reusable multi-tangent bar structures
- Open Access
- 27 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (5) , 1-14
Free-form Surface Approximation Using Rotational Patches
We present a method to approximate free-form surfaces using assemblies of rotational patches for architectural rationalization. Rotational surface patches inherently allow for the simultaneous repetition of multiple building elements along the arc direction. By assembling multiple patches, we can create diverse free-form-like geometries to satisfy broad design intents, while preserving local symmetry to enable cost-effective element fabrication. The main challenge lies in the strict constraint of maintaining local rotational symmetry, while ensuring the final tessellated form is seamless, smooth, and closely resembles the target surface. To address this, we propose a patch layout creation approach that segments the input surface into patches, resembling untrimmed rotational patches within a prescribed error threshold. Additionally, we develop a B-spline-based optimization framework to refine the fitted rotational patches for smooth connections and faithful surface approximation. To facilitate practical architectural applications, we provide a post-processing tool that converts the discrete patch assembly into a seamless, smooth quad mesh composed of locally repeated elements. We demonstrate that our approach is applicable to a variety of free-form surfaces, including those that mimic iconic architectural designs, and can address various practical requirements for a wide range of application scenarios.
- 27 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (5) , 1-14
Open AccessFree-form Surface Approximation Using Rotational Patches
We present a method to approximate free-form surfaces using assemblies of rotational patches for architectural rationalization. Rotational surface patches inherently allow for the simultaneous repetition of multiple building elements along the arc direction. By assembling multiple patches, we can create diverse free-form-like geometries to satisfy broad design intents, while preserving local symmetry to enable cost-effective element fabrication. The main challenge lies in the strict constraint of maintaining local rotational symmetry, while ensuring the final tessellated form is seamless, smooth, and closely resembles the target surface. To address this, we propose a patch layout creation approach that segments the input surface into patches, resembling untrimmed rotational patches within a prescribed error threshold. Additionally, we develop a B-spline-based optimization framework to refine the fitted rotational patches for smooth connections and faithful surface approximation. To facilitate practical architectural applications, we provide a post-processing tool that converts the discrete patch assembly into a seamless, smooth quad mesh composed of locally repeated elements. We demonstrate that our approach is applicable to a variety of free-form surfaces, including those that mimic iconic architectural designs, and can address various practical requirements for a wide range of application scenarios.
- Open Access
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-13
A Temporal Coherent Topology Optimization Approach for Assembly Planning of Bespoke Frame Structures
We present a computational framework for planning the assembly sequence of bespoke frame structures. Frame structures are one of the most commonly used structural systems in modern architecture, providing resistance to gravitational and external loads. Building frame structures requires traversing through several partially built states. If the assembly sequence is planned poorly, these partial assemblies can exhibit substantial deformation due to self-weight, slowing down or jeopardizing the assembly process. Finding a good assembly sequence that minimizes intermediate deformations is an interesting yet challenging combinatorial problem that is usually solved by heuristic search algorithms. In this paper, we propose a new optimization-based approach that models sequence planning using a series of topology optimization problems. Our key insight is that enforcing temporal coherent constraints in the topology optimization can lead to sub-structures with small deformations while staying consistent with each other to form an assembly sequence. We benchmark our algorithm on a large data set and show improvements in both performance and computational time over greedy search algorithms. In addition, we demonstrate that our algorithm can be extended to handle assembly with static or dynamic supports. We further validate our approach by generating a series of results in multiple scales, including a real-world prototype with a mixed reality assistant using our computed sequence and a simulated example demonstrating a multi-robot assembly application.
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-13
Open AccessA Temporal Coherent Topology Optimization Approach for Assembly Planning of Bespoke Frame Structures
We present a computational framework for planning the assembly sequence of bespoke frame structures. Frame structures are one of the most commonly used structural systems in modern architecture, providing resistance to gravitational and external loads. Building frame structures requires traversing through several partially built states. If the assembly sequence is planned poorly, these partial assemblies can exhibit substantial deformation due to self-weight, slowing down or jeopardizing the assembly process. Finding a good assembly sequence that minimizes intermediate deformations is an interesting yet challenging combinatorial problem that is usually solved by heuristic search algorithms. In this paper, we propose a new optimization-based approach that models sequence planning using a series of topology optimization problems. Our key insight is that enforcing temporal coherent constraints in the topology optimization can lead to sub-structures with small deformations while staying consistent with each other to form an assembly sequence. We benchmark our algorithm on a large data set and show improvements in both performance and computational time over greedy search algorithms. In addition, we demonstrate that our algorithm can be extended to handle assembly with static or dynamic supports. We further validate our approach by generating a series of results in multiple scales, including a real-world prototype with a mixed reality assistant using our computed sequence and a simulated example demonstrating a multi-robot assembly application.
- Open Access
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-12
Masonry Shell Structures with Discrete Equivalence Classes
This paper proposes a method to model masonry shell structures where the shell elements fall into a set of discrete equivalence classes. Such shell structure can reduce the fabrication cost and simplify the physical construction due to reuse of a few template shell elements. Given a freeform surface, our goal is to generate a small set of template shell elements that can be reused to produce a seamless and buildable structure that closely resembles the surface. The major technical challenge in this process is balancing the desire for high reusability of template elements with the need for a seamless and buildable final structure. To address the challenge, we define three error metrics to measure the seamlessness and buildability of shell structures made from discrete equivalence classes and develop a hierarchical cluster-and-optimize approach to generate a small set of template elements that produce a structure closely approximating the surface with low error metrics. We demonstrate the feasibility of our approach on various freeform surfaces and geometric patterns, and validate buildability of our results with four physical prototypes. Code and data of this paper are at https://github.com/Linsanity81/TileableShell.
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-12
Open AccessMasonry Shell Structures with Discrete Equivalence Classes
This paper proposes a method to model masonry shell structures where the shell elements fall into a set of discrete equivalence classes. Such shell structure can reduce the fabrication cost and simplify the physical construction due to reuse of a few template shell elements. Given a freeform surface, our goal is to generate a small set of template shell elements that can be reused to produce a seamless and buildable structure that closely resembles the surface. The major technical challenge in this process is balancing the desire for high reusability of template elements with the need for a seamless and buildable final structure. To address the challenge, we define three error metrics to measure the seamlessness and buildability of shell structures made from discrete equivalence classes and develop a hierarchical cluster-and-optimize approach to generate a small set of template elements that produce a structure closely approximating the surface with low error metrics. We demonstrate the feasibility of our approach on various freeform surfaces and geometric patterns, and validate buildability of our results with four physical prototypes. Code and data of this paper are at https://github.com/Linsanity81/TileableShell.
- 26 April 2018
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 15 (6) , 905-915
Machined sharp edge restoration for triangle mesh workpiece models derived from grid-based machining simulation
Grid-based machining simulation methods have become very popular due to their advantages in computational efficiency. However, these methods are prone to generating machined workpiece models with chamfer edges, which reduce model accuracy and visual quality. An effective method is presented in this paper targeting the restoration of machined edges from these chamfer edges for triangle mesh models derived from grid-based machining simulation. The method starts by detecting the chamfer edge triangles via utilizing both edge-based mesh segmentation and feature-based mesh segmentation. The outcomes of the two segmentation methods are then compared and combined to achieve improved detection accuracy. To restore the machined edges, the detected chamfer edge triangles are split by adding new points based on the neighbors of the chamfer edge triangles. Triangle quality checks are imposed during the point addition process in order to ensure that the restored edges do not negatively impact the triangle mesh quality. Once all the applicable new points are added for all the chamfer edge triangles, the edge restoration task is complete. The presented method has been implemented and executed on sample triangle mesh models derived from grid-based machining simulation. Improved edge restoration compared to that of existing edge restoration methods has been observed. Sub-second computational performance is attained for the majority of the test cases.
- 26 April 2018
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 15 (6) , 905-915
Machined sharp edge restoration for triangle mesh workpiece models derived from grid-based machining simulation
Grid-based machining simulation methods have become very popular due to their advantages in computational efficiency. However, these methods are prone to generating machined workpiece models with chamfer edges, which reduce model accuracy and visual quality. An effective method is presented in this paper targeting the restoration of machined edges from these chamfer edges for triangle mesh models derived from grid-based machining simulation. The method starts by detecting the chamfer edge triangles via utilizing both edge-based mesh segmentation and feature-based mesh segmentation. The outcomes of the two segmentation methods are then compared and combined to achieve improved detection accuracy. To restore the machined edges, the detected chamfer edge triangles are split by adding new points based on the neighbors of the chamfer edge triangles. Triangle quality checks are imposed during the point addition process in order to ensure that the restored edges do not negatively impact the triangle mesh quality. Once all the applicable new points are added for all the chamfer edge triangles, the edge restoration task is complete. The presented method has been implemented and executed on sample triangle mesh models derived from grid-based machining simulation. Improved edge restoration compared to that of existing edge restoration methods has been observed. Sub-second computational performance is attained for the majority of the test cases.