Co-design of Embodied Intelligence: A Structured Approach

  title={Co-design of Embodied Intelligence: A Structured Approach},
  author={Gioele Zardini and Dejan Milojevic and Andrea Censi and Emilio Frazzoli},
  journal={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  • G. Zardini, Dejan Milojevic, +1 author E. Frazzoli
  • Published 21 November 2020
  • Computer Science, Engineering
  • 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
We consider the problem of co-designing embodied intelligence as a whole in a structured way, from hardware components such as propulsion systems and sensors to software modules such as control and perception pipelines. We propose a principled approach to formulate and solve complex embodied intelligence co-design problems, leveraging a monotone co-design theory. The methods we propose are intuitive and integrate heterogeneous engineering disciplines, allowing analytical and simulation-based… 

Figures and Tables from this paper

Analysis and Control of Autonomous Mobility-on-Demand Systems
This article presents the emerging concept of autonomous mobility-on-demand, whereby centrally orchestrated fleets of autonomous vehicles provide mobility service to customers, and provides a comprehensive review of methods and tools to model and solve problems related to autonomous Mobility- on-demand systems.
Analysis and Control of Autonomous Mobility-on-Demand Systems: A Review
This article presents the emerging concept of Autonomous Mobility-on-Demand, whereby centrally orchestrated fleets of autonomous vehicles provide mobility service to customers, and provides a comprehensive review of methods and tools to model and solve problems related to Aut autonomous Mobility- on-Demand systems.
Limits and colimits in a category of lenses
Lenses are an important tool in applied category theory. While individual lenses have been widely used in applications, many of the mathematical properties of the corresponding categories of lenses
Co-Design of Autonomous Systems: From Hardware Selection to Control Synthesis
This work uses a monotone theory of codesign to formalize variations of the LQG control problem as monot one feasibility relations and shows how this enables the embedding of control co-design problems in the higher level co- design problem of a robotic platform.
Game Theory to Study Interactions between Mobility Stakeholders
A game-theoretic framework to study interactions between stakeholders of the mobility ecosystem, modeling regulatory aspects such as taxes and public transport prices, as well as operational matters for Mobility Service Providers such as pricing strategy, fleet sizing, and vehicle design is provided.
Operads for complex system design specification, analysis and synthesis
It is argued that operads provide an effective knowledge representation to address scalability challenges for complex system design and recent progress in effective modelling is described.


One Robot for Many Tasks: Versatile Co-Design Through Stochastic Programming
This letter considers the problems of designing a planar manipulator to transport a range of loads and a hopping monopod robot that must jump across a variety of terrains and details an approach to combine methods from stochastic programming with trajectory optimization to address the scalability of these multi-task co-design problems.
Abstractions for computing all robotic sensors that suffice to solve a planning problem
The algorithm aids in helping understand what attributes sensors must possess and what information they must provide in order to ensure a robot can achieve its goals despite non-determinism.
Robot Design: Formalisms, Representations, and the Role of the Designer
This paper's first aim is to draw together multiple threads---specifically those of formalization, minimality, automation, and integration---and to argue that robot design questions involve some of the most interesting and fundamental challenges for the discipline.
A Class of Co-Design Problems With Cyclic Constraints and Their Solution
  • A. Censi
  • Computer Science
    IEEE Robotics and Automation Letters
  • 2017
This letter shows that a large class of codesign problems have a common structure, as they are described by two posets, representing functionality, and resources, as the codesign constraints can be expressed as two maps in opposite directions between the two poset.
A Mathematical Theory of Co-Design
  • A. Censi
  • Mathematics, Computer Science
  • 2015
A theory of co-design is introduced that describes "design problems", defined as tuples of "functionality space", "implementation space", and "resources space", together with a feasibility relation that relates the three spaces.
Resource-Performance Tradeoff Analysis for Mobile Robots
The design of mobile autonomous robots is challenging due to the limited on-board resources such as processing power and energy. A promising approach is to generate intelligent schedules that reduce
On the Design of Minimal Robots That Can Solve Planning Problems
This article examines the selection of a robot’s actuation and sensing hardware to minimize the cost of that design while ensuring that the robot is capable of carrying out a plan to complete a task and delineates some circumstances in which one can do better and achieve genuine optima with practical algorithms.
Co-Design to Enable User-Friendly Tools to Assess the Impact of Future Mobility Solutions
This paper uses the recently developed mathematical theory of co-design to frame and solve the problem of designing and deploying an intermodal mobility system, whereby autonomous vehicles service travel demands jointly with micromobility solutions and public transit, in terms of fleets sizing, vehicle characteristics, and public Transit service frequency.
A Multiobjective Systems Architecture Model for Sensor Selection in Autonomous Vehicle Navigation
Understanding and quantifying the performance of sensing architectures on autonomous vehicles is a necessary step towards certification. However, once this evaluation can be performed, the
Functional co-optimization of articulated robots
By optimizing robot body parameters alongside robot trajectories, motion planning problems which would otherwise be infeasible can be made feasible, and actuation requirements can be significantly reduced.