Selective Visual Representations Improve Convergence and Generalization for Embodied AI

TL;DR

This paper introduces a task-conditioned filtering method using a learnable codebook to improve visual representation relevance, leading to better convergence, generalization, and performance in embodied AI tasks across multiple benchmarks.

Contribution

A novel, parameter-efficient approach employing a learnable codebook to filter visual inputs based on task relevance, enhancing embodied AI performance and generalization.

Findings

Achieves state-of-the-art results in object goal navigation and object displacement.

Filtered representations generalize better across different simulation environments.

Agents explore environments more effectively and focus on task-relevant visual cues.

Abstract

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this information is often irrelevant to the specific task at hand. This introduces noise within the learning process and distracts the agent's focus from task-relevant visual cues. Inspired by selective attention in humans-the process through which people filter their perception based on their experiences, knowledge, and the task at hand-we introduce a parameter-efficient approach to filter visual stimuli for embodied AI. Our approach induces a task-conditioned bottleneck using a small learnable codebook module. This codebook is trained jointly to optimize task reward and acts as a task-conditioned selective filter over the visual observation. Our experiments showcase state-of-the-art performance for object goal navigation and object displacement across 5 benchmarks, ProcTHOR, ArchitecTHOR, RoboTHOR, AI2-iTHOR, and ManipulaTHOR. The filtered representations produced by the codebook are also able generalize better and converge faster when adapted to other simulation environments such as Habitat. Our qualitative analyses show that agents explore their environments more effectively and their representations retain task-relevant information like target object recognition while ignoring superfluous information about other objects. Code and pretrained models are available at our project website: https://embodied-codebook.github.io.