Stefana Parascho

Stefana Parascho

Auto-generated profile, based on publicly available information

Stefana Parascho

Lab for Creative Computation, EPFL, Lausanne, Switzerland

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2022 in Computer-Aided Design
Verified
Journal Article
Closed access
RPRafael Pastrana
Rafael Pastrana
POPatrick Ole Ohlbrock
Patrick Ole Ohlbrock
TOThomas Oberbichler
Thomas Oberbichler
PDPierluigi D’acunto
Pierluigi D’acunto
SPStefana Parascho
Stefana Parascho

25 November 2021 in International Journal of Architectural Computing
Verified
Journal Article
Closed access
PDF file
IHIsla Xi Han
Isla Xi Han
FMForrest Meggers
Forrest Meggers
SPStefana Parascho
Stefana Parascho
Advancements in multi-agent, autonomous, and intelligent robotic systems over the past decades point toward new design and fabrication possibilities. Exploring how humans and robots can create and construct collectively is essential in leveraging robotic technology in the building sector. However, only by making existing knowledge from relevant technological disciplines accessible to designers can we fully exploit current construction methods and further develop them to address the challenges in architecture. To do this, we present a review paper that bridges the gap between Collective Robotic Construction (CRC) and Human–Robot Interaction (HRI) and defines a new research domain in Collective Human–Robot Construction (CHRC) in the architectural design and fabrication context.

1 October 2020 in Digital Creativity
Verified
Journal Article
Closed access
EBEdvard P. G. Bruun
Edvard P. G. Bruun
ITIan Ting
Ian Ting
SASigrid Adriaenssens
Sigrid Adriaenssens
SPStefana Parascho
Stefana Parascho
Robots in traditional fabrication applications act as passive participants in the process of creation—simply performing a set of predetermined actions to materialize a completed design. We propose a novel bottom-up design framework in which robots are instead given the opportunity to participate centrally within a creative design process. This paper describes how two 6-axis industrial robotic arms were used to cooperatively aggregate a collection of solid spherical units. The branching spatial structure being constructed is unplanned at the outset of this process, and is instead designed in pseudo-realtime during construction. This ‘design-as-you-build’ approach relies on robotic input, in the form of path-planning constraints, in tandem with human evaluation and decision-making. The resulting structure emerges from a human–robot design collaboration operating within the specified physical domain.

18 August 2024 in Construction Robotics
Verified
Journal Article
Closed access
PDF file
EBEdvard P. G. Bruun
Edvard P. G. Bruun
EBErin Besler
Erin Besler
SASigrid Adriaenssens
Sigrid Adriaenssens
SPStefana Parascho
Stefana Parascho


8 October 2023
Verified
Conference Paper
Open access
GVGabriel Vallat
Gabriel Vallat
JWJingwen Wang
Jingwen Wang
AMAnna Maddux
Anna Maddux
MKMaryam Kamgarpour
Maryam Kamgarpour
SPStefana Parascho
Stefana Parascho
In construction robotics, a conventional design-to-fabrication workflow starts with designing a structure, followed by task and robotic motion planning, and ultimately, fabrication. However, this approach can prove unsuccessful, as we may only discover the infeasibility of a design at the final stages of the process. This can result in rework and a considerable waste of time and resources. To overcome this challenge, we propose a design method based on reinforcement learning (RL) where the agent makes decisions at every step of the sequential assembly of the structure while considering assembly’s stability. In this way, we take the construction constraints into consideration at the design stage. The research particularly focuses on the design of spanning structures that multiple robot arms can construct without the need for scaffolding. A series of experiments were conducted using both a centralized and a decentralized learning setup. Our results show that while the decentralized setup was successful in constructing smaller structures, only the centralized setup allowed active collaboration between robot arms, resulting in structures with larger spans. To validate our approach, we fabricated two of the designed structures with two collaborating robot arms, which confirmed the feasibility of these designs. In summary, the proposed method opens exciting possibilities for generating innovative designs that push the boundaries of architectural creativity while simultaneously fulfilling fabrication-related constraints.