Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification

TL;DR

This paper introduces a deep reinforcement learning approach using Soft Actor-Critic to determine optimal viewpoints for object classification, improving accuracy in identifying objects from multiple perspectives.

Contribution

It presents a novel application of deep RL for next-best-view estimation in object classification, demonstrating learned viewpoint selection for improved recognition accuracy.

Findings

The agent successfully learns to select informative viewpoints.

Viewpoint optimization enhances object classification accuracy.

The method is validated on a specific set of objects.

Abstract

The presentation and analysis of image data from a single viewpoint are often not sufficient to solve a task. Several viewpoints are necessary to obtain more information. The next-best-view problem attempts to find the optimal viewpoint with the greatest information gain for the underlying task. In this work, a robot arm holds an object in its end-effector and searches for a sequence of next-best-view to explicitly identify the object. We use Soft Actor-Critic (SAC), a method of deep reinforcement learning, to learn these next-best-views for a specific set of objects. The evaluation shows that an agent can learn to determine an object pose to which the robot arm should move an object. This leads to a viewpoint that provides a more accurate prediction to distinguish such an object from other objects better. We make the code publicly available for the scientific community and for reproducibility.