Optimal Constrained Task Planning as Mixed Integer Programming

TL;DR

This paper introduces a novel method for robot task planning by formulating it as a mixed integer convex program, enabling the computation of optimal action sequences that satisfy all constraints in both simulation and real-world scenarios.

Contribution

The paper presents a new approach that encodes robot task planning as a single mixed integer convex program, solved with existing MIP solvers, ensuring optimality and constraint satisfaction.

Findings

Successfully plans optimal actions in mobile manipulation tasks

Handles complex numerical constraints effectively

Demonstrates real-world applicability with humanoid robots

Abstract

For robots to successfully execute tasks assigned to them, they must be capable of planning the right sequence of actions. These actions must be both optimal with respect to a specified objective and satisfy whatever constraints exist in their world. We propose an approach for robot task planning that is capable of planning the optimal sequence of grounded actions to accomplish a task given a specific objective function while satisfying all specified numerical constraints. Our approach accomplishes this by encoding the entire task planning problem as a single mixed integer convex program, which it then solves using an off-the-shelf Mixed Integer Programming solver. We evaluate our approach on several mobile manipulation tasks in both simulation and on a physical humanoid robot. Our approach is able to consistently produce optimal plans while accounting for all specified numerical constraints in the mobile manipulation tasks. Open-source implementations of the components of our approach as well as videos of robots executing planned grounded actions in both simulation and the physical world can be found at this url: https://adubredu.github.io/gtpmip