Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Human-Robot Collaborative Minimum Time Search through Sub-priors in Ant Colony Optimization

Oscar Gil Viyuela, Alberto Sanfeliu

TL;DR

This letter presents an extension of the Ant Colony Optimization (ACO) meta-heuristic to solve the Minimum Time Search (MTS) task, in the case where humans and robots perform an object searching task together.

Abstract

Human-Robot Collaboration (HRC) has evolved into a highly promising issue owing to the latest breakthroughs in Artificial Intelligence (AI) and Human-Robot Interaction (HRI), among other reasons. This emerging growth increases the need to design multi-agent algorithms that can manage also human preferences. This paper presents an extension of the Ant Colony Optimization (ACO) meta-heuristic to solve the Minimum Time Search (MTS) task, in the case where humans and robots perform an object searching task together. The proposed model consists of two main blocks. The first one is a convolutional neural network (CNN) that provides the prior probabilities about where an object may be from a segmented image. The second one is the Sub-prior MTS-ACO algorithm (SP-MTS-ACO), which takes as inputs the prior probabilities and the particular search preferences of the agents in different sub-priors to generate search plans for all agents. The model has been tested in real experiments for the joint search of an object through a Vizanti web-based visualization in a tablet computer. The designed interface allows the communication between a human and our humanoid robot named IVO. The obtained results show an improvement in the search perception of the users without loss of efficiency.

Human-Robot Collaborative Minimum Time Search through Sub-priors in Ant Colony Optimization

TL;DR

This letter presents an extension of the Ant Colony Optimization (ACO) meta-heuristic to solve the Minimum Time Search (MTS) task, in the case where humans and robots perform an object searching task together.

Abstract

Human-Robot Collaboration (HRC) has evolved into a highly promising issue owing to the latest breakthroughs in Artificial Intelligence (AI) and Human-Robot Interaction (HRI), among other reasons. This emerging growth increases the need to design multi-agent algorithms that can manage also human preferences. This paper presents an extension of the Ant Colony Optimization (ACO) meta-heuristic to solve the Minimum Time Search (MTS) task, in the case where humans and robots perform an object searching task together. The proposed model consists of two main blocks. The first one is a convolutional neural network (CNN) that provides the prior probabilities about where an object may be from a segmented image. The second one is the Sub-prior MTS-ACO algorithm (SP-MTS-ACO), which takes as inputs the prior probabilities and the particular search preferences of the agents in different sub-priors to generate search plans for all agents. The model has been tested in real experiments for the joint search of an object through a Vizanti web-based visualization in a tablet computer. The designed interface allows the communication between a human and our humanoid robot named IVO. The obtained results show an improvement in the search perception of the users without loss of efficiency.
Paper Structure (17 sections, 10 equations, 7 figures, 2 tables)

This paper contains 17 sections, 10 equations, 7 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. BACKGROUND
  3. The ACO Meta-heuristic
  4. RELATED WORK
  5. PS algorithms
  6. Human-Robot Collaborative Search
  7. OUR APPROACH
  8. Problem Formulation
  9. System Overview
  10. Probabilistic Map Predictor
  11. Sub-prior MTS-ACO
  12. SIMULATIONS AND REAL-LIFE EXPERIMENTS
  13. Sub-prior MTS-ACO Results
  14. Real-life Experiments
  15. User's Study
  16. ...and 2 more sections

Figures (7)

  • Figure 1: Human-Robot Collaborative Search with the IVO robot. The left picture shows the IVO robot and a person searching for an object. The right picture shows the tablet computer interface with the search plans information and the human participant's preferences.
  • Figure 2: System-Overview. The Segmented Map is used to predict the Probability Map and generate the restricted areas. These elements combined with the preferred areas are used to obtain the optimal paths with the Sub-Prior MTS ACO in a common representation for the IVO robot and Humans.
  • Figure 3: Labelling Interface for Users. Participants select the areas by marking the vertices of a polygon with the computer mouse over the segmented image until the polygon is closed. The semantic classes are shown in the image.
  • Figure 4: Gaussian sub-priors. The left image shows a probability map of 2 gaussian functions in blue. The white lines inside the gaussians are obstacles where the probability is zero. The right images are the 2 Gaussian functions separately as sub-priors to allow the distribution of the search task between 2 agents.
  • Figure 5: Sub-prior MTS-ACO planning of 2 agents exchanging sub-priors. This figure presents the search plans for 2 agents (red and blue) in 2 different cases for the same map exchanging their sub-priors.
  • ...and 2 more figures