Robot learning in the era of foundation models: A survey
X ** relies on high quality training data, which is hard to obtain: human data
is hard to transfer and synthetic data relies on simplifying assumptions that reduce grasp …
is hard to transfer and synthetic data relies on simplifying assumptions that reduce grasp …
Discriminative active learning for robotic gras** in cluttered scene
Robotic gras** is a challenging task due to the diversity of object shapes. A sufficiently
labeled dataset is essential for the grasp pose detection methods based on deep learning …
labeled dataset is essential for the grasp pose detection methods based on deep learning …
[HTML][HTML] Review of Machine Learning in Robotic Gras** Control in Space Application
This article presents a comprehensive survey of the integration of machine learning
techniques into robotic gras**, with a special emphasis on the challenges and …
techniques into robotic gras**, with a special emphasis on the challenges and …
Robotic System for Post Office Package Handling
Parcel sorting is becoming a significant challenge for delivery distribution centers and is
mostly automated by using high-throughput sorting machinery, but manual work is still used …
mostly automated by using high-throughput sorting machinery, but manual work is still used …
Domain randomization for sim2real transfer of automatically generated gras** datasets
J Huber, F Hélénon, H Watrelot… - … on Robotics and …, 2024 - ieeexplore.ieee.org
Robotic gras** refers to making a robotic system pick an object by applying forces and
torques on its surface. Many recent studies use data-driven approaches to address …
torques on its surface. Many recent studies use data-driven approaches to address …
A survey of embodied learning for object-centric robotic manipulation
Robot Grasp Planning: A Learning from Demonstration-Based Approach
Robot gras** constitutes an essential capability in fulfilling the complexities of advanced
industrial operations. This field has been extensively investigated to address a range of …
industrial operations. This field has been extensively investigated to address a range of …
Quality Diversity under Sparse Reward and Sparse Interaction: Application to Gras** in Robotics
Quality-Diversity (QD) methods are algorithms that aim to generate a set of diverse and high-
performing solutions to a given problem. Originally developed for evolutionary robotics, most …
performing solutions to a given problem. Originally developed for evolutionary robotics, most …
3D Whole-body Grasp Synthesis with Directional Controllability
Synthesizing 3D whole-bodies that realistically grasp objects is useful for animation, mixed
reality, and robotics. This is challenging, because the hands and body need to look natural …
reality, and robotics. This is challenging, because the hands and body need to look natural …