Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Goal-Oriented End-User Programming of Robots

David Porfirio, Mark Roberts, Laura M. Hiatt

TL;DR

Polaris is a novel EUP system that is equipped with a Plan Visualizer that exposes the planner’s output to the user before runtime, and which supports the Plan Visualizer’s ability to help users craft higher-quality programs.

Abstract

End-user programming (EUP) tools must balance user control with the robot's ability to plan and act autonomously. Many existing task-oriented EUP tools enforce a specific level of control, e.g., by requiring that users hand-craft detailed sequences of actions, rather than offering users the flexibility to choose the level of task detail they wish to express. We thereby created a novel EUP system, Polaris, that in contrast to most existing EUP tools, uses goal predicates as the fundamental building block of programs. Users can thereby express high-level robot objectives or lower-level checkpoints at their choosing, while an off-the-shelf task planner fills in any remaining program detail. To ensure that goal-specified programs adhere to user expectations of robot behavior, Polaris is equipped with a Plan Visualizer that exposes the planner's output to the user before runtime. In what follows, we describe our design of Polaris and its evaluation with 32 human participants. Our results support the Plan Visualizer's ability to help users craft higher-quality programs. Furthermore, there are strong associations between user perception of the robot and Plan Visualizer usage, and evidence that robot familiarity has a key role in shaping user experience.

Goal-Oriented End-User Programming of Robots

TL;DR

Polaris is a novel EUP system that is equipped with a Plan Visualizer that exposes the planner’s output to the user before runtime, and which supports the Plan Visualizer’s ability to help users craft higher-quality programs.

Abstract

End-user programming (EUP) tools must balance user control with the robot's ability to plan and act autonomously. Many existing task-oriented EUP tools enforce a specific level of control, e.g., by requiring that users hand-craft detailed sequences of actions, rather than offering users the flexibility to choose the level of task detail they wish to express. We thereby created a novel EUP system, Polaris, that in contrast to most existing EUP tools, uses goal predicates as the fundamental building block of programs. Users can thereby express high-level robot objectives or lower-level checkpoints at their choosing, while an off-the-shelf task planner fills in any remaining program detail. To ensure that goal-specified programs adhere to user expectations of robot behavior, Polaris is equipped with a Plan Visualizer that exposes the planner's output to the user before runtime. In what follows, we describe our design of Polaris and its evaluation with 32 human participants. Our results support the Plan Visualizer's ability to help users craft higher-quality programs. Furthermore, there are strong associations between user perception of the robot and Plan Visualizer usage, and evidence that robot familiarity has a key role in shaping user experience.
Paper Structure (28 sections, 5 figures, 2 tables)

This paper contains 28 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Robot End-User Programming
  4. Goal-Oriented Specification Paradigm
  5. Automated Planning in HRI
  6. System Design
  7. User Perspective
  8. Representing Goal Automata
  9. Creating a Branching Plan
  10. Viewing the Branching Plan
  11. Plan Execution
  12. Implementation
  13. System Evaluation
  14. Study Design
  15. Study Scenario
  16. ...and 13 more sections

Figures (5)

  • Figure 1: With Polaris, end-user programmers specify goal automata and view the resulting plan in the Plan Visualizer.
  • Figure 2: The Polaris user interface, which includes (a) the Drawing Board for specifying goal automata and (b) the Plan Visualizer for displaying the robot's plan. (c) A single branch of the branching plan from the caregiving scenario is displayed.
  • Figure 3: Computing branching plans from goal automata.
  • Figure 4: The smallest solution to the tidying scenario and its execution (left). The physical layout of the study room (right).
  • Figure 5: Plan quality (top left), usability (top right), competence and task load (bottom left), and expectations matched (bottom right) plotted against robot familiarity. Linear trendlines indicate the direction of the relationship. Blue is plan-vis. Grey is no-vis. Lower is better only for human effort and task load. Error bars represent standard error.