Unfolding the literature: A review of robotic cloth manipulation
The realm of textiles spans clothing, households, healthcare, sports, and industrial
applications. The deformable nature of these objects poses unique challenges that prior …
applications. The deformable nature of these objects poses unique challenges that prior …
Data scaling laws in imitation learning for robotic manipulation
Data scaling has revolutionized fields like natural language processing and computer vision,
providing models with remarkable generalization capabilities. In this paper, we investigate …
providing models with remarkable generalization capabilities. In this paper, we investigate …
Learning to manipulate anywhere: A visual generalizable framework for reinforcement learning
Can we endow visuomotor robots with generalization capabilities to operate in diverse open-
world scenarios? In this paper, we propose\textbf {Maniwhere}, a generalizable framework …
world scenarios? In this paper, we propose\textbf {Maniwhere}, a generalizable framework …
Green screen augmentation enables scene generalisation in robotic manipulation
Generalising vision-based manipulation policies to novel environments remains a
challenging area with limited exploration. Current practices involve collecting data in one …
challenging area with limited exploration. Current practices involve collecting data in one …
Aha: A vision-language-model for detecting and reasoning over failures in robotic manipulation
Robotic manipulation in open-world settings requires not only task execution but also the
ability to detect and learn from failures. While recent advances in vision-language models …
ability to detect and learn from failures. While recent advances in vision-language models …
Generative image as action models
M Shridhar, YL Lo, S James - arXiv preprint arXiv:2407.07875, 2024 - arxiv.org
Image-generation diffusion models have been fine-tuned to unlock new capabilities such as
image-editing and novel view synthesis. Can we similarly unlock image-generation models …
image-editing and novel view synthesis. Can we similarly unlock image-generation models …
3d-mvp: 3d multiview pretraining for robotic manipulation
Recent works have shown that visual pretraining on egocentric datasets using masked
autoencoders (MAE) can improve generalization for downstream robotics tasks. However …
autoencoders (MAE) can improve generalization for downstream robotics tasks. However …
Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies
J Qian, A Panagopoulos, D Jayaraman - arXiv preprint arXiv:2405.15916, 2024 - arxiv.org
Generic re-usable pre-trained image representation encoders have become a standard
component of methods for many computer vision tasks. As visual representations for robots …
component of methods for many computer vision tasks. As visual representations for robots …
Position: scaling simulation is neither necessary nor sufficient for in-the-wild robot manipulation
H Bharadhwaj - Forty-first International Conference on Machine …, 2024 - openreview.net
In this paper, we develop a structured critique of robotic simulations for real-world
manipulation, by arguing that scaling simulators is neither necessary nor sufficient for …
manipulation, by arguing that scaling simulators is neither necessary nor sufficient for …
Investigating the role of instruction variety and task difficulty in robotic manipulation tasks
Evaluating the generalisation capabilities of multimodal models based solely on their
performance on out-of-distribution data fails to capture their true robustness. This work …
performance on out-of-distribution data fails to capture their true robustness. This work …