Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automatic Configuration of Multi-Agent Model Predictive Controllers based on Semantic Graph World Models

K. de Vos, E. Torta, H. Bruyninckx, C. A. Lopez Martinez, M. J. G. van de Molengraft

TL;DR

The paper provides simulations of various representative situations, showing that the approach of runtime configuration of the MPC drastically decreases computation time, while retaining task execution performance similar to an approach in which each robot always includes all other robots in its MPC computations.

Abstract

We propose a shared semantic map architecture to construct and configure Model Predictive Controllers (MPC) dynamically, that solve navigation problems for multiple robotic agents sharing parts of the same environment. The navigation task is represented as a sequence of semantically labeled areas in the map, that must be traversed sequentially, i.e. a route. Each semantic label represents one or more constraints on the robots' motion behaviour in that area. The advantages of this approach are: (i) an MPC-based motion controller in each individual robot can be (re-)configured, at runtime, with the locally and temporally relevant parameters; (ii) the application can influence, also at runtime, the navigation behaviour of the robots, just by adapting the semantic labels; and (iii) the robots can reason about their need for coordination, through analyzing over which horizon in time and space their routes overlap. The paper provides simulations of various representative situations, showing that the approach of runtime configuration of the MPC drastically decreases computation time, while retaining task execution performance similar to an approach in which each robot always includes all other robots in its MPC computations.

Automatic Configuration of Multi-Agent Model Predictive Controllers based on Semantic Graph World Models

TL;DR

The paper provides simulations of various representative situations, showing that the approach of runtime configuration of the MPC drastically decreases computation time, while retaining task execution performance similar to an approach in which each robot always includes all other robots in its MPC computations.

Abstract

We propose a shared semantic map architecture to construct and configure Model Predictive Controllers (MPC) dynamically, that solve navigation problems for multiple robotic agents sharing parts of the same environment. The navigation task is represented as a sequence of semantically labeled areas in the map, that must be traversed sequentially, i.e. a route. Each semantic label represents one or more constraints on the robots' motion behaviour in that area. The advantages of this approach are: (i) an MPC-based motion controller in each individual robot can be (re-)configured, at runtime, with the locally and temporally relevant parameters; (ii) the application can influence, also at runtime, the navigation behaviour of the robots, just by adapting the semantic labels; and (iii) the robots can reason about their need for coordination, through analyzing over which horizon in time and space their routes overlap. The paper provides simulations of various representative situations, showing that the approach of runtime configuration of the MPC drastically decreases computation time, while retaining task execution performance similar to an approach in which each robot always includes all other robots in its MPC computations.
Paper Structure (12 sections, 7 equations, 3 figures, 6 tables, 2 algorithms)

This paper contains 12 sections, 7 equations, 3 figures, 6 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Method
  3. MPC Formulation
  4. Semantic Map
  5. Navigation Strategy
  6. Validation
  7. Implementation
  8. Results
  9. Completion
  10. Completion Time
  11. Computation Time
  12. Conclusions

Figures (3)

  • Figure 1: (Left) Simplified structured environment consisting of three areas. (Right) Excerpt of a graph world model describing the environment on the left. The colors of the nodes signify their different types.
  • Figure 2: Illustration of two agents with overlapping semantic horizons with $N_{h} = 2$. Red and blue polygons illustrate the environmental no-collision constraints of the red and blue agent respectively. Purple polygons show the overlap between the two. Dashed lines illustrate the virtual boundary constraints.
  • Figure 3: The tested scenarios 1-4. Agents are initialized in the darkest shade of their respective color, and are tasked with navigating through the lighter shades. Overlaid are the resulting trajectories of one of the runs of the D configuration.

Theorems & Definitions (1)

  • Definition 1: Semantic Map