AIMED: AI-Mediated Exploration of Design: An Experience Report

Sanjai Narain, Dana Chee, Pranav Iyer, Emily Mak, Ricardo Valdez, Manli Zhu, Niraj Jha, Jaime Fisac, Kai Chieh Hsu, Prerit Terway, Kishore Pochiraju, Brendan Englot, Emil Pitz, Sean Rooney, Yewei Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The goal of DARPA's Symbiotic Design of Cyber Physical Systems (SDCPS) program is to develop tools for "correct-by-synthesis"design of cyber physical systems (CPS) and reduce the time from concept to deployment from years to months. Achieving this goal poses several hard challenges. Design spaces are high-dimensional cross-products of discrete and continuous spaces. It can take minutes to hours to evaluate the performance of a design. The human designer's intent is often not concretely articulated. Sometimes designs are not created from scratch but rather by completing or repairing existing ones. This paper outlines how the AIMED system addresses these challenges. AIMED consists of three core technologies. The first is "deformable connector"that eliminates an important type of discreteness from design spaces. Thus, not only is the design space vastly simplified, efficient optimization engines for purely continuous spaces can be used in the search for a design. The second core technology is Inverse Specification, based on inverse reinforcement learning that infers human intent by asking the human a small number of simple preference questions. The third core technology is Gaussian Mixture Models that allows completion and repair of designs and finds not just one but a diversity of solutions. AIMED is illustrated in the context of Unmanned Airborne Vehicles (UAVs) although it was also applied to the design of Unmanned Underwater Vehicles (UUVs). AIMED was used to automatically discover high-scoring, novel UAVs, unencumbered by biases of planarity and symmetry: a UAV with non-coplanar propellers and another with asymmetric wings. We expect our experience will apply to design of other CPS.

Original languageEnglish (US)
Title of host publicationProceedings of 2023 Cyber-Physical Systems and Internet-of-Things Week, CPS-IoT Week 2023 - Workshops
PublisherAssociation for Computing Machinery
Number of pages5
ISBN (Electronic)9798400700491
StatePublished - May 9 2023
Event2023 Cyber-Physical Systems and Internet-of-Things Week, CPS-IoT Week 2023 - San Antonio, United States
Duration: May 9 2023May 12 2023

Publication series

NameACM International Conference Proceeding Series


Conference2023 Cyber-Physical Systems and Internet-of-Things Week, CPS-IoT Week 2023
Country/TerritoryUnited States
CitySan Antonio

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software


  • AI
  • Bayesian
  • Connector
  • Deformable
  • Design
  • Exploration
  • Gaussian
  • Inverse
  • Learning
  • Mixture
  • Models
  • Optimization
  • Reinforcement
  • Space


Dive into the research topics of 'AIMED: AI-Mediated Exploration of Design: An Experience Report'. Together they form a unique fingerprint.

Cite this