RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation

TL;DR

This paper introduces an image-only robotic manipulation framework using an active monocular camera to estimate object poses, balancing perception accuracy and manipulation efficiency with reinforcement learning, achieving state-of-the-art results.

Contribution

The novel framework enables effective 6D object pose estimation and manipulation using only RGB images with active perception and reinforcement learning, eliminating the need for point-cloud data.

Findings

Achieves state-of-the-art manipulation accuracy in both simulation and real-world tests.

Effectively balances pose estimation accuracy and manipulation speed.

Demonstrates robustness of the approach in diverse environments.

Abstract

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two commonly used modalities in visual-based robotic manipulation, but each of these modalities have their own limitations. Commercial point-cloud observations often suffer from issues like sparse sampling and noisy output due to the limits of the emission-reception imaging principle. On the other hand, RGB images, while rich in texture information, lack essential depth and 3D information crucial for robotic manipulation. To mitigate these challenges, we propose an image-only robotic manipulation framework that leverages an eye-on-hand monocular camera installed on the robot's parallel gripper. By moving with the robot gripper, this camera gains the ability to actively perceive object from multiple perspectives during the manipulation process. This enables the estimation of 6D object poses, which can be utilized for manipulation. While, obtaining images from more and diverse viewpoints typically improves pose estimation, it also increases the manipulation time. To address this trade-off, we employ a reinforcement learning policy to synchronize the manipulation strategy with active perception, achieving a balance between 6D pose accuracy and manipulation efficiency. Our experimental results in both simulated and real-world environments showcase the state-of-the-art effectiveness of our approach. %, which, to the best of our knowledge, is the first to achieve robust real-world robotic manipulation through active pose estimation. We believe that our method will inspire further research on real-world-oriented robotic manipulation.