检索结果-内蒙古大学图书馆

BOOTSTRAPPING SEMANTIC SEGMENTATION WITH REGIONAL CONTRAST 10

学校读者我要写书评

暂无评论

BOOTSTRAPPING SEMANTIC SEGMENTATION WITH REGIONAL CONTRAST

10th International Conference on learning Representations, ICLR 2022

作者： Liu, Shikun Zhi, Shuaifeng Johns, Edward Davison, Andrew J. Dyson Robotics Lab Imperial College London United Kingdom Robot Learning Lab Imperial College London United Kingdom

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance, achieving more accurate segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high quality semantic segmentation model, requiring only 5 examples of each semantic class. © 2022 ICLR 2022 - 10th International Conference on learning Representationss. All rights reserved.

关键词： Semantics

Action Augmentation of Tactile Perception for Soft-Body Palpation

学校读者我要写书评

暂无评论

SOFT robotICS 2022年第2期9卷 280-292页

作者： Scimeca, Luca Hughes, Josie Maiolino, Perla He, Liang Nanayakkara, Thrishantha Iida, Fumiya Univ Cambridge Dept Engn Bioinspired Robot Lab Trumpington St Cambridge CB2 1PZ England Univ Oxford Oxford Robot Inst Oxford England Imperial Coll London Dyson Sch Design Engn Morphol Computat & Learning Lab London England

Medical palpation is a diagnostic technique in which physicians use the sense of touch to manipulate the soft human tissue. This can be done to enable the diagnosis of possibly life-threatening conditions, such as cancer. Palpation is still poorly understood because of the complex interaction dynamics between the practitioners' hands and the soft human body. To understand this complex of soft body interactions, we explore robotic palpation for the purpose of diagnosing the presence of abnormal inclusions, or tumors. Using a Bayesian framework for training and classification, we show that the exploration of soft bodies requires complex, multi-axis, palpation trajectories. We also find that this probabilistic approach is capable of rapidly searching the large action space of the robot. This work progresses "robotic" palpation, and it provides frameworks for understanding and exploiting soft body interactions.

关键词： soft tissue palpation soft haptics soft tactile perception

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xiao Patidar, Sumit Haughton, Iain James, Stephen Dyson Robot Learning Lab

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-best end-effector pose (NBP), and a low-level goal-conditioned diffusion policy which generates optimal motion trajectories. The factorised policy representation allows HDP to tackle both long-horizon task planning while generating fine-grained low-level actions. To generate context-aware motion trajectories while satisfying robot kinematics constraints, we present a novel kinematics-aware goal-conditioned control agent, robot Kinematics Diffuser (RK-Diffuser). Specifically, RK-Diffuser learns to generate both the end-effector pose and joint position trajectories, and distill the accurate but kinematics-unaware end-effector pose diffuser to the kinematics-aware but less accurate joint position diffuser via differentiable kinematics. Empirically, we show that HDP achieves a significantly higher success rate than the state-of-the-art methods in both simulation and real-world.1 © 2024, CC BY.

关键词： Kinematics

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task robotic Manipulation

学校读者我要写书评

暂无评论

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Tas...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiao Ma Sumit Patidar Iain Haughton Stephen James Dyson Robot Learning Lab

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

关键词： Accuracy robot kinematics Kinematics Multitasking End effectors Robustness Trajectory

BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chernyadev, Nikita Backshall, Nicholas Ma, Xiao Lu, Yunfan Seo, Younggyo James, Stephen Dyson Robot Learning Lab

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 the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities. Project website: https://***/bigym/ Copyright © 2024, The Authors. All rights reserved.

关键词： learning algorithms

Vision Foundation Model Enables Generalizable Object Pose Estimation 38

学校读者我要写书评

暂无评论

Vision Foundation Model Enables Generalizable Object Pose Es...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Kai Ma, Yiyao Lin, Xingyu James, Stephen Zhou, Jianshu Liu, Yun-Hui Abbeel, Pieter Dou, Qi The Chinese University of Hong Kong Hong Kong UC Berkeley United States Dyson Robot Learning Lab United Kingdom

Object pose estimation plays a crucial role in robotic manipulation, however, its practical applicability still suffers from limited generalizability. This paper addresses the challenge of generalizable object pose estimation, particularly focusing on category-level object pose estimation for unseen object categories. Current methods either require impractical instance-level training or are confined to predefined categories, limiting their applicability. We propose VFM-6D, a novel framework that explores harnessing existing vision and language models, to elaborate object pose estimation into two stages: category-level object viewpoint estimation and object coordinate map estimation. Based on the two-stage framework, we introduce a 2D-to-3D feature lifting module and a shape-matching module, both of which leverage pre-trained vision foundation models to improve object representation and matching accuracy. VFM-6D is trained on cost-effective synthetic data and exhibits superior generalization capabilities. It can be applied to both instance-level unseen object pose estimation and category-level object pose estimation for novel categories. Evaluations on benchmark datasets demonstrate the effectiveness and versatility of VFM-6D in various real-world scenarios. Project website: ***/. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

Accelerating Reinforcement learning with Value-Conditional State Entropy Exploration 37

学校读者我要写书评

暂无评论

Accelerating Reinforcement Learning with Value-Conditional S...

37th Conference on Neural Information Processing Systems (NeurIPS)

作者： Kim, Dongyoung Shin, Jinwoo Abbeel, Pieter Seo, Younggyo Korea Adv Inst Sci & Technol Daejeon South Korea Univ Calif Berkeley Berkeley CA USA Dyson Robot Learning Lab London England

ISBN: (纸本)9781713899921

A promising technique for exploration is to maximize the entropy of visited state distribution, i.e., state entropy, by encouraging uniform coverage of visited state space. While it has been effective for an unsupervised setup, it tends to struggle in a supervised setup with a task reward, where an agent prefers to visit high-value states to exploit the task reward. Such a preference can cause an imbalance between the distributions of high-value states and low-value states, which biases exploration towards low-value state regions as a result of the state entropy increasing when the distribution becomes more uniform. This issue is exacerbated when high-value states are narrowly distributed within the state space, making it difficult for the agent to complete the tasks. In this paper, we present a novel exploration technique that maximizes the value-conditional state entropy, which separately estimates the state entropies that are conditioned on the value estimates of each state, then maximizes their average. By only considering the visited states with similar value estimates for computing the intrinsic bonus, our method prevents the distribution of low-value states from affecting exploration around high-value states, and vice versa. We demonstrate that the proposed alternative to the state entropy baseline significantly accelerates various reinforcement learning algorithms across a variety of tasks within MiniGrid, DeepMind Control Suite, and Meta-World benchmarks. Source code is available at https://***/view/rl-vcse.

关键词： Reinforcement learning

Green Screen Augmentation Enables Scene Generalisation in robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Teoh, Eugene Patidar, Sumit Ma, Xiao James, Stephen Dyson Robot Learning Lab United Kingdom

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 this data, and deploying the policy in the same location. However, this approach lacks scalability as it necessitates data collection in multiple locations for each task. This paper proposes a novel approach where data is collected in a location predominantly featuring green screens. We introduce Greenscreen Augmentation (GreenAug), employing a chroma key algorithm to overlay background textures onto a green screen. Through extensive real-world empirical studies with over 850 training demonstrations and 8.2k evaluation episodes, we demonstrate that GreenAug surpasses no augmentation, standard computer vision augmentation, and prior generative augmentation methods in performance. While no algorithmic novelties are claimed, our paper advocates for a fundamental shift in data collection practices. We propose that real-world demonstrations in future research should utilise green screens, followed by the application of GreenAug. We believe GreenAug unlocks policy generalisation to visually distinct novel locations, addressing the current scene generalisation limitations in robot learning. © 2024, CC BY.

关键词： Reinforcement learning

Generative Image as Action Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shridhar, Mohit Lo, Yat Long James, Stephen Dyson Robot Learning Lab United Kingdom

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 fine-tunes Stable Diffusion to "draw joint-actions" as targets on RGB images. These images are fed into a controller that maps the visual targets into a sequence of joint-positions. We study GENIMA on 25 RLBench and 9 real-world manipulation tasks. We find that, by lifting actions into image-space, internet pre-trained diffusion models can generate policies that outperform state-of-the-art visuomotor approaches, especially in robustness to scene perturbations and generalizing to novel objects. Our method is also competitive with 3D agents, despite lacking priors such as depth, keypoints, or motion-planners. © 2024, CC BY.

关键词： Clone cells