TL;DR
APPLE is a reinforcement learning framework that jointly trains perception and decision policies, enabling versatile active perception across various tasks like tactile exploration, demonstrating high accuracy and generality.
Contribution
Introduces APPLE, a task-agnostic RL framework that combines perception and decision-making modules for broad active perception applications.
Findings
APPLE achieves high accuracy on tactile exploration tasks.
Joint training of perception and policy improves active perception performance.
Demonstrates versatility across different active perception problems.
Abstract
Active perception is a fundamental skill that enables us humans to deal with uncertainty in our inherently partially observable environment. For senses such as touch, where the information is sparse and local, active perception becomes crucial. In recent years, active perception has emerged as an important research domain in robotics. However, current methods are often bound to specific tasks or make strong assumptions, which limit their generality. To address this gap, this work introduces APPLE (Active Perception Policy Learning) - a novel framework that leverages reinforcement learning (RL) to address a range of different active perception problems. APPLE jointly trains a transformer-based perception module and decision-making policy with a unified optimization objective, learning how to actively gather information. By design, APPLE is not limited to a specific task and can, in…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
