Zobrazeno 1 - 10
of 553
pro vyhledávání: '"James, Stephen P."'
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 for visuomotor control? We present GENIMA, a behavior-cloning agent that
Externí odkaz:
http://arxiv.org/abs/2407.07875
Generalising vision-based manipulation policies to novel environments remains a challenging area with limited exploration. Current practices involve collecting data in one location, training imitation learning or reinforcement learning policies with
Externí odkaz:
http://arxiv.org/abs/2407.07868
We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture
Externí odkaz:
http://arxiv.org/abs/2407.07788
Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present Coarse-to-fine
Externí odkaz:
http://arxiv.org/abs/2407.07787
Joint space and task space control are the two dominant action modes for controlling robot arms within the robot learning literature. Actions in joint space provide precise control over the robot's pose, but tend to suffer from inefficient training;
Externí odkaz:
http://arxiv.org/abs/2406.04144
In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with limited amounts
Externí odkaz:
http://arxiv.org/abs/2405.18196
This paper introduces Hierarchical Diffusion Policy (HDP), a hierarchical agent for multi-task robotic manipulation. HDP factorises a manipulation policy into a hierarchical structure: a high-level task-planning agent which predicts a distant next-be
Externí odkaz:
http://arxiv.org/abs/2403.03890
Autor:
Wang, Jiangliu, Jiao, Jianbo, Song, Yibing, James, Stephen, Tong, Zhan, Ge, Chongjian, Abbeel, Pieter, Liu, Yun-hui
This work aims to improve unsupervised audio-visual pre-training. Inspired by the efficacy of data augmentation in visual contrastive learning, we propose a novel speed co-augmentation method that randomly changes the playback speeds of both audio an
Externí odkaz:
http://arxiv.org/abs/2309.13942
Autor:
Fawz Kazzazi, Danny Kazzazi, Dilip Gosall, Diana Kazzazi, Thomas Hedley Newman, James Stephen Arthur Green, Nicola Bystrzonowski, Gurjinderpal Pahal
Publikováno v:
JPRAS Open, Vol 41, Iss , Pp 428-442 (2024)
Objective: This study aimed to examine the trends in gender, ethnicity and less-than-full-time (LTFT) training in reconstructive plastic surgery from 2009 to 2020 in the UK by comparing them to overall surgical specialties. Methods: We analysed NHS D
Externí odkaz:
https://doaj.org/article/9482a9f161fb4bfa8bc98ee9c8e0630b
Contact is at the core of robotic manipulation. At times, it is desired (e.g. manipulation and grasping), and at times, it is harmful (e.g. when avoiding obstacles). However, traditional path planning algorithms focus solely on collision-free paths,
Externí odkaz:
http://arxiv.org/abs/2308.16893