6D pose estimation with combined deep learning and 3D vision techniques for a fast and accurate object grasping

Le, Tuan-Tang; Le, Trung-Son; Chen, Yuru; Vidal, Joel; Lin, Chyi‐Yeu

doi:10.1016/j.robot.2021.103775

Cited by 22 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After each forward pass, Wahba's error was evaluated by using Equation (1). The weights given by the test case were considered-and are defined in Equation (12b)-and A pred was considered instead of A true to measure the true distance.…”

Section: Model Choicementioning

confidence: 99%

“…This difference is represented as a rotation operation; thus, the goal is to find the rotational axis and rotational angle that best rotate a frame given by (

, and

) to another frame given by (

, and

). Finding the rotation between frames is applied in many fields, such as robotics [ 1 , 2 ], navigation and control [ 3 ], and computer graphics [ 4 , 5 ], among others [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

“…where #» b i is an observation vector in the body frame, #» r i is a vector in the reference frame, a i is a weight value for each observation vector, and A is the optimal attitude matrix. This first approach to attitude determination led to the development of several new algorithms derived directly from Equation (1), resulting in a trade-off, as more robust models are slower to converge, requiring more computational effort, and very fast algorithms may result in low accuracy [8], thus requiring careful fine-tuning.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Static Attitude Determination Using Convolutional Neural Networks

Santos

Seman

Bezerra

et al. 2021

Sensors

View full text Add to dashboard Cite

The need to estimate the orientation between frames of reference is crucial in spacecraft navigation. Robust algorithms for this type of problem have been built by following algebraic approaches, but data-driven solutions are becoming more appealing due to their stochastic nature. Hence, an approach based on convolutional neural networks in order to deal with measurement uncertainty in static attitude determination problems is proposed in this paper. PointNet models were trained with different datasets containing different numbers of observation vectors that were used to build attitude profile matrices, which were the inputs of the system. The uncertainty of measurements in the test scenarios was taken into consideration when choosing the best model. The proposed model, which used convolutional neural networks, proved to be less sensitive to higher noise than traditional algorithms, such as singular value decomposition (SVD), the q-method, the quaternion estimator (QUEST), and the second estimator of the optimal quaternion (ESOQ2).

show abstract

Section: Model Choicementioning

confidence: 99%

“…This difference is represented as a rotation operation; thus, the goal is to find the rotational axis and rotational angle that best rotate a frame given by (

, and

) to another frame given by (

, and

). Finding the rotation between frames is applied in many fields, such as robotics [ 1 , 2 ], navigation and control [ 3 ], and computer graphics [ 4 , 5 ], among others [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Static Attitude Determination Using Convolutional Neural Networks

Santos

Seman

Bezerra

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning-based pose estimation techniques have been developed rapidly and have higher accuracy and better scalability than other traditional vision methods [15][16][17][18]. However, the huge amount of training samples and labeled data for matching usage scenarios are still an important constraint for deep learning in industrial applications [19,20].…”

Section: Introductionmentioning

confidence: 99%

A posture detection method for augmented reality–aided assembly based on YOLO-6D

Zhang

Liu

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The assembly of small batch electrical and mechanical products still relies on manual operation, with the problems of high rechecking time and low assembly efficiency and quality. The augmented reality technology can be used to assist assembly to improve efficiency. In view of the high professionalism, labor and time cost for the traditional posture detection method, a posture detection method is proposed to match the assembly posture by pre-calibrating the assembly posture template. YOLO-6D deep learning network is brought in to increase the accuracy of virtual information tracking registration. And the detection from both translation and rotation perspectives is designed to enhance the adaptability to different assembly tasks. For the generation of training datasets, a weighted sampling method based on part features is proposed to optimize the accuracy of position estimation with the limited training samples. Taking the assembly process of typical electronic products as an example, the developed augmented reality aided assembly system is used to boost the assembly efficiency of assembly operators. It is illustrated that the proposed positional detection method is effective in registering virtual assembly guidance information in real scenarios and can be applied to augmented reality assembly guidance of products.

show abstract

“…Regarding high stability in manipulation, the conventional grippers in [23][24][25] can be more outstanding candidates as compared to the soft grippers. The traditional robot hands with high stiffness fingers, rigid phalanxes and finite DoFs at each joint, enabled the gripper to easily control the grasping poses and lock the group objects with a constant squeeze.…”

Section: Introductionmentioning

confidence: 99%

Soft-Stable Interface in Grasping Multiple Objects by Wiring-tension

Nguyen

Bohra

Chow

2023

Preprint

View full text Add to dashboard Cite

Efficiently manipulating objects in a group state is an emergent challenge for the soft robot hands. Overcoming this problem requires such hands to have highly stable structures to bear the heavy loads and highly compliant design to universally adapt to diverse object geometries. This study proposed a novel platform to develop the robot hands in manipulating multiple objects at each trial. In this scenario, the objects were in soft contact with an elastic wire mounted on the finger skeletons. This combination formed a harmonious hybrid finger that inherited both the soft flexible properties of the wire and the strong-stable bearing of the finger skeleton. One theoretical model was proposed to estimate the kinematics of manipulating multiple objects by the wiring-based fingers. Based on this model, we designed a hybrid gripper comprising two wiring-based fingers for conducting experimentally evaluations in manipulating four group samples: double bevel gears, double bevel gears plus pneumatic connector, double glue bottles, and double silicon bottles. The experimental results indicated that our proposed gripper reached good performance with high success rates in durability tests at different levels of the lifting velocity and high adaption with objects in soft-friendly interaction. These outcomes are potential to efficiently manipulate multiple complex objects per trial without requiring complicated controls.

show abstract

6D pose estimation with combined deep learning and 3D vision techniques for a fast and accurate object grasping

Cited by 22 publications

References 21 publications

Static Attitude Determination Using Convolutional Neural Networks

Static Attitude Determination Using Convolutional Neural Networks

A posture detection method for augmented reality–aided assembly based on YOLO-6D

Soft-Stable Interface in Grasping Multiple Objects by Wiring-tension

Contact Info

Product

Resources

About