Self-supervised 6D Object Pose Estimation for Robot Manipulation
Xinke Deng, Xiang Yu, Arsalan Mousavian et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 2020
To teach robots skills, it is crucial to obtain data with supervision. Since annotating real world data is time-consuming and expensive, enabling robots to learn in a self- supervised way is important. In this work, we introduce a robot system for self-supervised 6D object pose estimation. Starting from modules trained in simulation, our system is able to label real world images with accurate 6D object poses for self-supervised learning. In addition, the robot interacts with objects in the environment to change the object configuration by grasping or pushing objects. In this way, our system is able to continuously collect data and improve its pose estimation modules. We show that the self-supervised learning improves object segmentation and 6D pose estimation performance, and consequently enables the system to grasp objects more reliably. A video showing the experiments can be found at https://youtu.be/W1Y0Mmh1Gd8.
Cited by 207 works. doi:10.1109/icra40945.2020.9196714 Open-access PDF
Authors
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- You Only Look Once: Unified, Real-Time Object Detection
- Object recognition from local scale-invariant features
- AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
- SSD: Single Shot MultiBox Detector
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Curriculum learning
- Self-taught learning
- Unsupervised Visual Representation Learning by Context Prediction
- 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints