Towards Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Generative Models

TL;DR

This paper presents a framework combining generative skill documentation, abstraction mapping, and POMDP planning to enable plug-and-play task-level autonomy in robots, simplifying integration and improving decision-making under uncertainty.

Contribution

It introduces GSDL for expressive skill documentation, an abstraction mapping for bridging low-level code and planning models, and a POMDP-based scheduler for autonomous skill management.

Findings

GSDL simplifies skill documentation and enhances expressiveness.

The abstraction mapping effectively bridges low-level code and high-level planning.

The POMDP scheduler balances uncertainty, noise, and stochasticity in robot control.

Abstract

To enable robots to achieve high level objectives, engineers typically write scripts that apply existing specialized skills, such as navigation, object detection and manipulation to achieve these goals. Writing good scripts is challenging since they must intelligently balance the inherent stochasticity of a physical robot's actions and sensors, and the limited information it has. In principle, AI planning can be used to address this challenge and generate good behavior policies automatically. But this requires passing three hurdles. First, the AI must understand each skill's impact on the world. Second, we must bridge the gap between the more abstract level at which we understand what a skill does and the low-level state variables used within its code. Third, much integration effort is required to tie together all components. We describe an approach for integrating robot skills into a working autonomous robot controller that schedules its skills to achieve a specified task and carries four key advantages. 1) Our Generative Skill Documentation Language (GSDL) makes code documentation simpler, compact, and more expressive using ideas from probabilistic programming languages. 2) An expressive abstraction mapping (AM) bridges the gap between low-level robot code and the abstract AI planning model. 3) Any properly documented skill can be used by the controller without any additional programming effort, providing a Plug'n Play experience. 4) A POMDP solver schedules skill execution while properly balancing partial observability, stochastic behavior, and noisy sensing.