Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Abstract Hardware Grounding towards the Automated Design of Automation Systems

Yu-Zhe Shi, Qiao Xu, Fanxu Meng, Lecheng Ruan, Qining Wang

TL;DR

Results on designing self-driving laboratories for enhancing experiment-driven scientific discovery and an automated design framework in a hybrid data-driven and principle-derived fashion suggest the framework's potential to produce compact systems that fully satisfy domain-specific and user-customized requirements with no redundancy.

Abstract

Crafting automation systems tailored for specific domains requires aligning the space of human experts' semantics with the space of robot executable actions, and scheduling the required resources and system layout accordingly. Regrettably, there are three major gaps, fine-grained domain-specific knowledge injection, heterogeneity between human knowledge and robot instructions, and diversity of users' preferences, resulting automation system design a case-by-case and labour-intensive effort, thus hindering the democratization of automation. We refer to this challenging alignment as the abstract hardware grounding problem, where we firstly regard the procedural operations in humans' semantics space as the abstraction of hardware requirements, then we ground such abstractions to instantiated hardware devices, subject to constraints and preferences in the real world -- optimizing this problem is essentially standardizing and automating the design of automation systems. On this basis, we develop an automated design framework in a hybrid data-driven and principle-derived fashion. Results on designing self-driving laboratories for enhancing experiment-driven scientific discovery suggest our framework's potential to produce compact systems that fully satisfy domain-specific and user-customized requirements with no redundancy.

Abstract Hardware Grounding towards the Automated Design of Automation Systems

TL;DR

Results on designing self-driving laboratories for enhancing experiment-driven scientific discovery and an automated design framework in a hybrid data-driven and principle-derived fashion suggest the framework's potential to produce compact systems that fully satisfy domain-specific and user-customized requirements with no redundancy.

Abstract

Crafting automation systems tailored for specific domains requires aligning the space of human experts' semantics with the space of robot executable actions, and scheduling the required resources and system layout accordingly. Regrettably, there are three major gaps, fine-grained domain-specific knowledge injection, heterogeneity between human knowledge and robot instructions, and diversity of users' preferences, resulting automation system design a case-by-case and labour-intensive effort, thus hindering the democratization of automation. We refer to this challenging alignment as the abstract hardware grounding problem, where we firstly regard the procedural operations in humans' semantics space as the abstraction of hardware requirements, then we ground such abstractions to instantiated hardware devices, subject to constraints and preferences in the real world -- optimizing this problem is essentially standardizing and automating the design of automation systems. On this basis, we develop an automated design framework in a hybrid data-driven and principle-derived fashion. Results on designing self-driving laboratories for enhancing experiment-driven scientific discovery suggest our framework's potential to produce compact systems that fully satisfy domain-specific and user-customized requirements with no redundancy.
Paper Structure (39 sections, 9 equations, 4 figures)

This paper contains 39 sections, 9 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Specific domains
  3. Heterogeneous spaces
  4. User-centered preferences
  5. The abstract hardware grounding problem
  6. dsl as hardware abstraction
  7. ahg problem definition
  8. Input
  9. Target Output
  10. Optimization on the grounded hardware layout
  11. Solving ahg for executability
  12. Initialization
  13. Preference-based optimization
  14. Flexibility
  15. Reliability
  16. ...and 24 more sections

Figures (4)

  • Figure 1: Illustration of the paired inverse problems --- hardware abstraction and ahg
  • Figure 2: Illustration of the ahg problem.(A) Demonstration of the original protocols and the protocols compiled into dsl programs with corresponding protocol dependence graphs, serving as the hardware abstraction. (B) Workflow of the pipeline solving the ahg problem.
  • Figure 3: Results on executability level.(A) Distribution of operation dependency (adjacent matrix). (B) Showcases of k-minimal cut initialization. (C) Illustration of the Pareto frontiers in multi-objective optimization on executability level. (Two axis are a pair of normalized objectives) (D) Showcases of the resulting layouts by different trade-offs.
  • Figure 4: Results on efficiency level.(A) Intermediate process of resource scheduling. (B) Showcases of iterative algorithm initialization. Left: Layout of the starting point of the iterative algorithm. Right: Histograms of the required types and quantities of devices. (C) Illustration of the Pareto frontiers in multi-objective optimization on efficiency level. (D) Showcases of the resulting layouts by different trade-offs in histograms of the required types and quantities of devices. Color difference indicates the observation point switching from all (dark) to individual protocols.