Transferring Grasp Configurations using Active Learning and Local Replanning

Tian, Hao; Wang, Changbo; Manocha, Dinesh; Zhang, Xinyu

doi:10.1109/icra.2019.8793796

Cited by 22 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scene-oriented approaches pursue an understanding of the whole scene [16]. This kind of method can be generalized to new objects and environments, and dynamically reacts to the environment [17][18][19][20].…”

Section: Scene Orientedmentioning

confidence: 99%

GraspVDN: scene-oriented grasp estimation by learning vector representations of grasps

Dong

Tian

Bao

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Grasp estimation is a fundamental technique crucial for robot manipulation tasks. In this work, we present a scene-oriented grasp estimation scheme taking constraints of the grasp pose imposed by the environment into consideration and training on samples satisfying the constraints. We formulate valid grasps for a parallel-jaw gripper as vectors in a two-dimensional (2D) image and detect them with a fully convolutional network that simultaneously estimates the vectors’ origins and directions. The detected vectors are then converted to 6 degree-of-freedom (6-DOF) grasps with a tailored strategy. As such, the network is able to detect multiple grasp candidates from a cluttered scene in one shot using only an RGB image as input. We evaluate our approach on the GraspNet-1Billion dataset and archived comparable performance as state-of-the-art while being efficient in runtime.

show abstract

Section: Scene Orientedmentioning

confidence: 99%

GraspVDN: scene-oriented grasp estimation by learning vector representations of grasps

Dong

Tian

Bao

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…This method first segmented the target into parts with different grasp labels and semantic information according to the geometric shape and category, and then used the grasp transformation measurement method to evaluate the probability that grasp tags can be successfully implemented, and finally output the grasp tag with the highest probability. Tian et al 11 first segmented the target in 3D according to the geometric shape and semantic features, and then established the corresponding relationship between the current target and the various parts of the sample, and finally selected the current target's grasp position by the grasp results calculated on the sample. Empirical methods can often generate reliable grasp configurations with a higher success rate when the object type is fixed in the scene, but the generalization performance is poor when facing unknown objects.…”

Section: Related Workmentioning

confidence: 99%

Grasp detection via visual rotation object detection and point cloud spatial feature scoring

Wang

2021

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Accurately detecting the appropriate grasp configurations is the central task for the robot to grasp an object. Existing grasp detection methods usually overlook the depth image or only regard it as a two-dimensional distance image, which makes it difficult to capture the three-dimensional structural characteristics of target object. In this article, we transform the depth image to point cloud and propose a two-stage grasp detection method based on candidate grasp detection from RGB image and spatial feature rescoring from point cloud. Specifically, we first adopt the recently proposed high-performance rotation object detection method for aerial images, named R3Det, to grasp detection task, obtaining the candidate grasp boxes and their appearance scores. Then, point clouds within each candidate grasp box are normalized and evaluated to get the point cloud quality scores, which are fused with the established point cloud quantity scoring model to obtain spatial scores. Finally, appearance scores and their corresponding spatial scores are combined to output high-quality grasp detection results. The proposed method effectively fuses three types of grasp scoring modules, thus is called Score Fusion Grasp Net. Besides, we propose and adopt top-k grasp metric to effectively reflect the success rate of algorithm in actual grasp execution. Score Fusion Grasp Net obtains 98.5% image-wise accuracy and 98.1% object-wise accuracy on Cornell Grasp Dataset, which exceeds the performances of state-of-the-art methods. We also use the robotic arm to conduct physical grasp experiments on 15 kinds of household objects and 11 kinds of adversarial objects. The results show that the proposed method still has a high success rate when facing new objects.

show abstract

“…for each specific object. Tian et al [32] present bijective contact mapping for transferring grasp contact points from an example object to a novel object.…”

Section: Related Workmentioning

confidence: 99%

Multi-Fingered Active Grasp Learning

Merwe

Hermans

2020

Preprint

View full text Add to dashboard Cite

Learning-based approaches to grasp planning are preferred over analytical methods due to their ability to better generalize to new, partially observed objects. However, data collection remains one of the biggest bottlenecks for grasp learning methods, particularly for multi-fingered hands. The relatively high dimensional configuration space of the hands coupled with the diversity of objects common in daily life requires a significant number of samples to produce robust and confident grasp success classifiers. In this paper, we present the first active learning approach to grasping that searches over the grasp configuration space and classifier confidence in a unified manner. Our real-robot grasping experiment shows our active grasp planner using less training data achieves comparable success rates with a passive supervised planner trained with geometrical grasping data. We also compute the differential entropy to demonstrate our active learner generates grasps with larger diversity than passive supervised learning using more heuristic data. We base our approach on recent success in planning multi-fingered grasps as probabilistic inference with a learned neural network likelihood function. We embed this within a multi-armed bandit formulation of sample selection. We show that our active grasp learning approach uses fewer training samples to produce grasp success rates comparable with the passive supervised learning method trained with grasping data generated by an analytical planner.

show abstract

Transferring Grasp Configurations using Active Learning and Local Replanning

Cited by 22 publications

References 41 publications

GraspVDN: scene-oriented grasp estimation by learning vector representations of grasps

GraspVDN: scene-oriented grasp estimation by learning vector representations of grasps

Grasp detection via visual rotation object detection and point cloud spatial feature scoring

Multi-Fingered Active Grasp Learning

Contact Info

Product

Resources

About