Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Risk-Averse Planning and Plan Assessment for Marine Robots

Mahya Mohammadi Kashani, Tobias John, Jeremy P. Coffelt, Einar Broch Johnsen, Andrzej Wasowski

TL;DR

A method that first generates a selection of diverse high-level plans and then assesses them in a low-level simulation to select the optimal and most reliable candidate is introduced, demonstrating feasibility and effectiveness of the approach.

Abstract

Autonomous Underwater Vehicles (AUVs) need to operate for days without human intervention and thus must be able to do efficient and reliable task planning. Unfortunately, efficient task planning requires deliberately abstract domain models (for scalability reasons), which in practice leads to plans that might be unreliable or under performing in practice. An optimal abstract plan may turn out suboptimal or unreliable during physical execution. To overcome this, we introduce a method that first generates a selection of diverse high-level plans and then assesses them in a low-level simulation to select the optimal and most reliable candidate. We evaluate the method using a realistic underwater robot simulation, estimating the risk metrics for different scenarios, demonstrating feasibility and effectiveness of the approach.

Risk-Averse Planning and Plan Assessment for Marine Robots

TL;DR

A method that first generates a selection of diverse high-level plans and then assesses them in a low-level simulation to select the optimal and most reliable candidate is introduced, demonstrating feasibility and effectiveness of the approach.

Abstract

Autonomous Underwater Vehicles (AUVs) need to operate for days without human intervention and thus must be able to do efficient and reliable task planning. Unfortunately, efficient task planning requires deliberately abstract domain models (for scalability reasons), which in practice leads to plans that might be unreliable or under performing in practice. An optimal abstract plan may turn out suboptimal or unreliable during physical execution. To overcome this, we introduce a method that first generates a selection of diverse high-level plans and then assesses them in a low-level simulation to select the optimal and most reliable candidate. We evaluate the method using a realistic underwater robot simulation, estimating the risk metrics for different scenarios, demonstrating feasibility and effectiveness of the approach.
Paper Structure (11 sections, 2 equations, 6 figures, 2 tables)

This paper contains 11 sections, 2 equations, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. A Method for Risk-Averse Planning
  4. Framework
  5. Plan Generation
  6. Plan Evaluation
  7. Experimental Results
  8. Evaluation Scenario
  9. Design and Implementation
  10. Results
  11. Conclusion and Outlook

Figures (6)

  • Figure 1: An underwater scene visualized in Gazebo
  • Figure 2: Comparison of simulated execution times for different plans. Plan IDs refer to those in \ref{['table:plans']}.
  • Figure 3: Flow diagram of proposed method.
  • Figure 4: Example scenario described by an MDP. It includes three waypoints, which are the critical ones for the mission.
  • Figure 5: Blue line: a plan fragment following the safest path as returned by our method. Green line: a risky path suggested by a high-level risk-neutral planner
  • ...and 1 more figures

Theorems & Definitions (3)

  • Example 1
  • Example 2
  • Definition 1: Transformed Transition System