Recent robotic manipulation competitions have highlighted that sophisticated robots still struggle to achieve fast and reliable perception of task-relevant objects in complex, realistic scenarios. To improve these systems' perceptive speed and robustness, we present SegICP, a novel integrated solution to object recognition and pose estimation. SegICP couples convolutional neural networks and multi-hypothesis point cloud registration to achieve both robust pixel-wise semantic segmentation as well as accurate and real-time 6-DOF pose estimation for relevant objects.Our architecture achieves 1 cm position error and < 5 • angle error in real time without an initial seed. We evaluate and benchmark SegICP against an annotated dataset generated by motion capture.
Nested reconfiguration is an emerging research area in modular robotics. Such a novel design concept utilizes individual robots with distinctive reconfiguration characteristics (intra-reconfigurability) capable of combining with other homogeneous/heterogeneous robots (inter-reconfigurability). The objective of this approach is to generate more complex morphologies for performing specific tasks that are far from the capabilities of a single module or to respond to programmable assembly requirements. The two-level reconfiguration process in nested reconfigurable robotic system implies several technical challenges in hardware design, planning algorithms, and control strategies. In this paper, we discuss the theory, concept, and initial mechanical design of Hinged-Tetro, a self-reconfigurable module conceived for the study of nested reconfiguration. Hinged-Tetro is a mobile robot that uses the principle of hinged dissection of polyominoes to transform itself into any of the seven one-sided tetrominoes, the Tetris pieces, in a straightforward way. The robot can also combine with other modules for shaping complex structures or giving rise to a robot with new capabilities. Some preliminary experiments of intrareconfigurability with an implemented prototype are presented.
In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our endto-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement.
Rather than the conventional classification method, we propose to divide modular and reconfigurable robots into intra-, inter-, and nested reconfigurations. We suggest designing the robot with nested reconfigurability, which utilizes individual robots with intra-reconfigurability capable of combining with other homogeneous/heterogeneous robots (inter-reconfigurability). The objective of this approach is to generate more complex morphologies for performing specific tasks that are far from the capabilities of a single module or to respond to programmable assembly requirements. In this paper, we discuss the theory, concept, and initial mechanical design of Hinged-Tetro, a self-reconfigurable module conceived for the study of nested reconfiguration. Hinged-Tetro is a mobile robot that uses the principle of hinged dissection of polyominoes to transform itself into any of the seven one-sided tetrominoes in a straightforward way. The robot can also combine with other modules for shaping complex structures or giving rise to a robot with new capabilities. Finally, the validation experiments verify the nested reconfigurability of Hinged-Tetro. Extensive tests and analyses of intra-reconfiguration are provided in terms of energy and time consumptions. Experiments using two robots validate the inter-reconfigur ability of the proposed module
To enable autonomous robotic manipulation in unstructured environments, we present SegICP-DSR, a realtime, dense, semantic scene reconstruction and pose estimation algorithm that achieves mm-level pose accuracy and standard deviation (7.9 mm, σ=7.6 mm and 1.7 deg, σ=0.7 deg) and successfully identified the object pose in 97% of test cases. This represents a 29% increase in accuracy, and a 14% increase in success rate compared to SegICP in cluttered, unstructured environments. The performance increase of SegICP-DSR arises from (1) improved deep semantic segmentation under adversarial training, (2) precise automated calibration of the camera intrinsic and extrinsic parameters, (3) viewpoint specific ray-casting of the model geometry, and (4) dense semantic ElasticFusion point clouds for registration. We benchmark the performance of SegICP-DSR on thousands of pose-annotated video frames and demonstrate its accuracy and efficacy on two tight tolerance grasping and insertion tasks using a KUKA LBR iiwa robotic arm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.