Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach

TL;DR

This paper proposes a new approach for robot foundation models called Diffusion for Policy Parameters (DPP), which generates task-specific policies to improve interpretability and modularity, enabling easier updates and personalization.

Contribution

The paper introduces DPP, a method for creating stand-alone, task-specific policies that are detached from the foundation model, enhancing interpretability and update flexibility.

Findings

DPP can generate effective task-specific policies in simulation.

Policies are modular and can be updated independently.

The approach improves interpretability and user interaction.

Abstract

Foundation models are a promising path toward general-purpose and user-friendly robots. The prevalent approach involves training a generalist policy that, like a reinforcement learning policy, uses observations to output actions. Although this approach has seen much success, several concerns arise when considering deployment and end-user interaction with these systems. In particular, the lack of modularity between tasks means that when model weights are updated (e.g., when a user provides feedback), the behavior in other, unrelated tasks may be affected. This can negatively impact the system's interpretability and usability. We present an alternative approach to the design of robot foundation models, Diffusion for Policy Parameters (DPP), which generates stand-alone, task-specific policies. Since these policies are detached from the foundation model, they are updated only when a user wants, either through feedback or personalization, allowing them to gain a high degree of familiarity with that policy. We demonstrate a proof-of-concept of DPP in simulation then discuss its limitations and the future of interpretable foundation models.