Efficient Data Collection for Robotic Manipulation via Compositional Generalization
Data collection has become an increasingly important problem in robotic manipulation, yet
there still lacks much understanding of how to effectively collect data to facilitate broad …
there still lacks much understanding of how to effectively collect data to facilitate broad …
Poco: Policy composition from and for heterogeneous robot learning
Training general robotic policies from heterogeneous data for different tasks is a significant
challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile …
challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile …
Data augmentation for manipulation
P Mitrano, D Berenson - arXiv preprint arXiv:2205.02886, 2022 - arxiv.org
The success of deep learning depends heavily on the availability of large datasets, but in
robotic manipulation there are many learning problems for which such datasets do not exist …
robotic manipulation there are many learning problems for which such datasets do not exist …
Large-Scale Scenario Generation for Robotic Manipulation via Conditioned Generative Models
Data-driven robotic manipulation has been gaining traction. However, creating synthetic
large-scale datasets for training, validation and benchmarks often relies on random …
large-scale datasets for training, validation and benchmarks often relies on random …
Learning to Design and Use Tools for Robotic Manipulation
When limited by their own morphologies, humans and some species of animals have the
remarkable ability to use objects from the environment toward accomplishing otherwise …
remarkable ability to use objects from the environment toward accomplishing otherwise …
Environment prediction from sparse samples for robotic information gathering
JA Caley, GA Hollinger - 2020 IEEE International Conference …, 2020 - ieeexplore.ieee.org
Robots often require a model of their environment to make informed decisions. In unknown
environments, the ability to infer the value of a data field from a limited number of samples is …
environments, the ability to infer the value of a data field from a limited number of samples is …
ASID: Active Exploration for System Identification in Robotic Manipulation
Model-free control strategies such as reinforcement learning have shown the ability to learn
control strategies without requiring an accurate model or simulator of the world. While this is …
control strategies without requiring an accurate model or simulator of the world. While this is …
Cacti: A framework for scalable multi-task multi-scene visual imitation learning
Large-scale training have propelled significant progress in various sub-fields of AI such as
computer vision and natural language processing. However, building robot learning systems …
computer vision and natural language processing. However, building robot learning systems …
Droid: A large-scale in-the-wild robot manipulation dataset
A Khazatsky, K Pertsch, S Nair, A Balakrishna… - arXiv preprint arXiv …, 2024 - arxiv.org
The creation of large, diverse, high-quality robot manipulation datasets is an important
stepping stone on the path toward more capable and robust robotic manipulation policies …
stepping stone on the path toward more capable and robust robotic manipulation policies …
Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation
Given the high cost of collecting robotic data in the real world, sample efficiency is a
consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation …
consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation …