Learning Goal-Oriented Non-Prehensile Pushing in Cluttered Scenes

Dengler, Nils; Grobklaus, David; Bennewitz, Maren

doi:10.1109/iros47612.2022.9981873

Cited by 11 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al developed a hybrid analytical/data-driven approach that approximated the limit surface for different objects using a parametrised model (Zhou et al (2018)). Other researchers have used deep learning to model the forward or inverse dynamics of pushed object motion (Agrawal et al (2016); Byravan and Fox (2017); Li et al (2018)), or to learn end-to-end control policies for pushing (Clavera et al (2017); Dengler et al (2022)). In general, analytical approaches are more computationally efficient and transparent in their operation than data-driven approaches, but may not perform well if their underlying assumptions and approximations do not hold in practice (Yu et al (2016)).…”

Section: Background and Related Workmentioning

confidence: 99%

Pose-and-shear-based tactile servoing

Lloyd,

Lepora

2024

The International Journal of Robotics Research

View full text Add to dashboard Cite

Tactile servoing is an important technique because it enables robots to manipulate objects with precision and accuracy while adapting to changes in their environments in real-time. One approach for tactile servo control with high-resolution soft tactile sensors is to estimate the contact pose relative to an object surface using a convolutional neural network (CNN) for use as a feedback signal. In this paper, we investigate how the surface pose estimation model can be extended to include shear, and utilise these combined pose-and-shear models to develop a tactile robotic system that can be programmed for diverse non-prehensile manipulation tasks, such as object tracking, surface-following, single-arm object pushing and dual-arm object pushing. In doing this, two technical challenges had to be overcome. Firstly, the use of tactile data that includes shear-induced slippage can lead to error-prone estimates unsuitable for accurate control, and so we modified the CNN into a Gaussian-density neural network and used a discriminative Bayesian filter to improve the predictions with a state dynamics model that utilises the robot kinematics. Secondly, to achieve smooth robot motion in 3D space while interacting with objects, we used SE(3) velocity-based servo control, which required re-deriving the Bayesian filter update equations using Lie group theory, as many standard assumptions do not hold for state variables defined on non-Euclidean manifolds. In future, we believe that pose-and-shear-based tactile servoing will enable many object manipulation tasks and the fully-dexterous utilisation of multi-fingered tactile robot hands.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Pose-and-shear-based tactile servoing

Lloyd,

Lepora

2024

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…Pushing is a fundamental operation of robots to manipulate objects in the workspace. Pushing can separate stacked objects and increase the operating space for subsequent operations, such as object classification, object arrangement, obstacle removal, repositioning and reorientating objects [29,30]. Push-Net [31] used deep recurrent neural networks to push objects for solving the problem of repositioning and reorientating objects.…”

Section: Pushingmentioning

confidence: 99%

Position‐aware pushing and grasping synergy with deep reinforcement learning in clutter

Zhao

Zuo

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in clutter. To effectively perform grasping and pushing manipulations, robots need to perceive the position information of objects, including the coordinates and spatial relationship between objects (e.g., proximity, adjacency). The authors propose an end‐to‐end position‐aware deep Q‐learning framework to achieve efficient collaborative pushing and grasping in clutter. Specifically, a pair of conjugate pushing and grasping attention modules are proposed to capture the position information of objects and generate high‐quality affordance maps of operating positions with features of pushing and grasping operations. In addition, the authors propose an object isolation metric and clutter metric based on instance segmentation to measure the spatial relationships between objects in cluttered environments. To further enhance the perception capacity of position information of the objects, the authors associate the change in the object isolation metric and clutter metric in cluttered environment before and after performing the action with reward function. A series of experiments are carried out in simulation and real‐world which indicate that the method improves sample efficiency, task completion rate, grasping success rate and action efficiency compared to state‐of‐the‐art end‐to‐end methods. Noted that the authors’ system can be robustly applied to real‐world use and extended to novel objects. Supplementary material is available at https://youtu.be/NhG\_k5v3NnM}{https://youtu.be/NhG\_k5v3NnM.

show abstract

“…Contact force information plays a critical role in pushing tasks, as it provides valuable cues about the interaction dynamics and the effectiveness of the applied forces. Surprisingly, contact force information has been underutilized in previous reinforcement learning-based pushing tasks (Dengler et al, 2022 ), especially in the reward design phase.…”

Section: Introductionmentioning

confidence: 99%

Learning adaptive reaching and pushing skills using contact information

Wang,

Sun,

Zha

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

In this paper, we propose a deep reinforcement learning-based framework that enables adaptive and continuous control of a robot to push unseen objects from random positions to the target position. Our approach takes into account contact information in the design of the reward function, resulting in improved success rates, generalization for unseen objects, and task efficiency compared to policies that do not consider contact information. Through reinforcement learning using only one object in simulation, we obtain a learned policy for manipulating a single object, which demonstrates good generalization when applied to the task of pushing unseen objects. Finally, we validate the effectiveness of our approach in real-world scenarios.

show abstract

Learning Goal-Oriented Non-Prehensile Pushing in Cluttered Scenes

Cited by 11 publications

References 22 publications

Pose-and-shear-based tactile servoing

Pose-and-shear-based tactile servoing

Position‐aware pushing and grasping synergy with deep reinforcement learning in clutter

Learning adaptive reaching and pushing skills using contact information

Contact Info

Product

Resources

About