Planning with affordances: Integrating learned affordance models and symbolic planning

TL;DR

This paper presents a method that combines learned affordance models with symbolic planning to enable agents to perform complex multi-step tasks in photorealistic environments, improving adaptability and task execution.

Contribution

It introduces an integrated framework that augments existing planning with learned affordance models, allowing flexible and efficient task planning in real-world-like settings.

Findings

Agents learn to interact with environment quickly.

The approach successfully completes tasks like object relocation.

Effective in virtual and real-world environments.

Abstract

Intelligent agents working in real-world environments must be able to learn about the environment and its capabilities which enable them to take actions to change to the state of the world to complete a complex multi-step task in a photorealistic environment. Learning about the environment is especially important to perform various multiple-step tasks without having to redefine an agent's action set for different tasks or environment settings. In our work, we augment an existing task and motion planning framework with learned affordance models of objects in the world to enable planning and executing multi-step tasks using learned models. Each task can be seen as changing the current state of the world to a given goal state. The affordance models provide us with what actions are possible and how to perform those actions in any given state. A symbolic planning algorithm uses this information and the starting and goal state to create a feasible plan to reach the desired goal state to complete a given task. We demonstrate our approach in a virtual 3D photorealistic environment, AI2-Thor, and evaluate it on real-world tasks. Our results show that our agent quickly learns how to interact with the environment and is well prepared to perform tasks such as "Moving an object out of the way to reach the desired location."