Skip to content
Open access

Human-in-the-Loop Multirobot Information Gathering With Inverse Submodular Maximization

Mar 2024 · IEEE Transactions on robotics · Vol 42, pp. 3944-3963 · 3 citations · 76 references
Computer Science

Abstract

In this article, we consider a new type of inverse combinatorial optimization, inverse submodular maximization (ISM), and its application to human-in-the-loop multirobot information gathering. Forward combinatorial optimization, which solves a combinatorial problem given reward- or cost-related parameters, is widely used in multirobot coordination. These parameters are typically designed offline by domain experts and then used for online robot coordination. We consider settings in which human supervisors provide desired path primitives during task execution, and the robots adapt their internal decision-making parameters accordingly. From the perspective of inverse combinatorial optimization, we formulate ISM for a family of multirobot information gathering problems, where the goal is to find new parameters that minimally deviate from the current ones while causing a greedy algorithm to produce path primitives consistent with the human suggestions. For a single suggestion, the problem can be formulated as a mixed integer quadratic program, which becomes intractable for existing solvers as the problem size grows. We, therefore, propose a new branch-and-bound algorithm. For multiple suggestions from several human supervisors, the problem is formulated as a multiobjective optimization problem and addressed using a heuristic, with Pareto Monte Carlo tree search employed in the search stage. Numerical simulations in multirobot scientific data collection and event detection-driven coverage control demonstrate that the proposed formulations and algorithms enable robots to effectively adapt to human suggestions.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.