检索结果-内蒙古大学图书馆

12th International Conference on learning Representations, ICLR 2024

作者： Lo, Yat Long Sengupta, Biswa Foerster, Jakob Noukhovitch, Michael Dyson Robot Learning Lab United Kingdom Imperial College London United Kingdom FLAIR University of Oxford United Kingdom Mila Université de Montréal Canada

Communication is a powerful tool for coordination in multi-agent RL. But inducing an effective, common language is a difficult challenge, particularly in the decentralized setting. In this work, we introduce an alternative perspective where communicative messages sent between agents are considered as different incomplete views of the environment state. By examining the relationship between messages sent and received, we propose to learn to communicate using contrastive learning to maximize the mutual information between messages of a given trajectory. In communication-essential environments, our method outperforms previous work in both performance and learning speed. Using qualitative metrics and representation probing, we show that our method induces more symmetric communication and captures global state information from the environment. Overall, we show the power of contrastive learning and the importance of leveraging messages as encodings for effective communication. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning

arXiv

引用

arXiv 2024年

作者： Vosylius, Vitalis Seo, Younggyo Uruç, Jafar James, Stephen Dyson Robot Learning Lab Imperial College London United Kingdom

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 of data. In this work, we introduce Render and Diffuse (R&D) a method that unifies low-level robot actions and RGB observations within the image space using virtual renders of the 3D model of the robot. Using this joint observation-action representation it computes low-level robot actions using a learnt diffusion process that iteratively updates the virtual renders of the robot. This space unification simplifies the learning problem and introduces inductive biases that are crucial for sample efficiency and spatial generalisation. We thoroughly evaluate several variants of R&D in simulation and showcase their applicability on six everyday tasks in the real world. Our results show that R&D exhibits strong spatial generalisation capabilities and is more sample efficient than more common image-to-action methods. © 2024, CC BY.

关键词： robots

来源：评论

学校读者我要写书评

暂无评论

Visual representation learning with stochastic frame prediction 24

Visual representation learning with stochastic frame predict...

引用

Proceedings of the 41st International Conference on Machine learning

作者： Huiwon Jang Dongyoung Kim Junsu Kim Jinwoo Shin Pieter Abbeel Younggyo Seo KAIST UC Berkeley KAIST and Dyson Robot Learning Lab.

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise from a single current frame. To tackle this challenge, in this paper, we revisit the idea of stochastic video generation that learns to capture uncertainty in frame prediction and explore its effectiveness for representation learning. Specifically, we design a framework that trains a stochastic frame prediction model to learn temporal information between frames. Moreover, to learn dense information within each frame, we introduce an auxiliary masked image modeling objective along with a shared decoder architecture. We find this architecture allows for combining both objectives in a synergistic and compute-efficient manner. We demonstrate the effectiveness of our framework on a variety of tasks from video label propagation and vision-based robot learning domains, such as video segmentation, pose tracking, vision-based robotic locomotion, and manipulation tasks. Code is available on the project webpage: https://***/view/2024rsp.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BOOTSTRAPPING SEMANTIC SEGMENTATION WITH REGIONAL CONTRAST 10

BOOTSTRAPPING SEMANTIC SEGMENTATION WITH REGIONAL CONTRAST

引用

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

来源：评论

学校读者我要写书评

暂无评论

Action Augmentation of Tactile Perception for Soft-Body Palpation

引用

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

来源：评论

学校读者我要写书评

暂无评论

StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS

StereoPose: Category-Level 6D Transparent Object Pose Estima...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Chen, Kai James, Stephen Sui, Congying Liu, Yun-Hui Abbeel, Pieter Dou, Qi Chinese Univ Hong Kong Hong Kong Peoples R China Univ Calif Berkeley Berkeley CA 94720 USA Dyson Robot Learning Lab London England Hong Kong Ctr Logist Robot Hong Kong Peoples R China

ISBN: (纸本)9798350323658

Most existing methods for category-level pose estimation rely on object point clouds. However, when considering transparent objects, depth cameras are usually not able to capture high-quality data, resulting in point clouds with severe artifacts. Without a complete point cloud, existing methods are not applicable to challenging transparent objects. To tackle this problem, we present StereoPose, a novel stereo image based framework for category-level object pose estimation, ideally suited for transparent objects. For a robust estimation from pure stereo images, we develop a pipeline that decouples category-level pose estimation into object size estimation, initial pose estimation, and pose refinement. StereoPose then estimates object pose based on representation in the normalized object coordinate space (NOCS). To address the issue of image content aliasing, we further define a back-view NOCS map for the transparent object. The back-view NOCS aims to reduce the network learning ambiguity caused by content aliasing, and leverage informative cues on the back of the transparent object for more accurate pose estimation. To further improve the performance of the stereo framework, StereoPose is equipped with a parallax attention module for stereo feature fusion and an epipolar loss for improving the stereo-view consistency of network predictions. Extensive experiments on the public TOD dataset demonstrate the superiority of the proposed StereoPose framework for category-level 6D transparent object pose estimation. Code and demos will be available on the project homepage: ***/(similar to)kaichen/***.

关键词： Geometrical optics

来源：评论

学校读者我要写书评

暂无评论

CHEAP TALK DISCOVERY AND UTILIZATION IN MULTI-AGENT REINFORCEMENT learning 11

CHEAP TALK DISCOVERY AND UTILIZATION IN MULTI-AGENT REINFORC...

引用

11th International Conference on learning Representations, ICLR 2023

作者： Lo, Yat Long de Witt, Christian Schroeder Sokota, Samuel Foerster, Jakob Whiteson, Shimon University of Oxford Dyson Robot Learning Lab United Kingdom FLAIR University of Oxford United Kingdom Carnegie Mellon University United States University of Oxford United Kingdom

By enabling agents to communicate, recent cooperative multi-agent reinforcement learning (MARL) methods have demonstrated better task performance and more coordinated behavior. Most existing approaches facilitate inter-agent communication by allowing agents to send messages to each other through free communication channels, i.e., cheap talk channels. Current methods require these channels to be constantly accessible and known to the agents a priori. In this work, we lift these requirements such that the agents must discover the cheap talk channels and learn how to use them. Hence, the problem has two main parts: cheap talk discovery (CTD) and cheap talk utilization (CTU). We introduce a novel conceptual framework for both parts and develop a new algorithm based on mutual information maximization that outperforms existing algorithms in CTD/CTU settings. We also release a novel benchmark suite to stimulate future research in CTD/CTU. © 2023 11th International Conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating reinforcement learning with value-conditional state entropy exploration 23

Accelerating reinforcement learning with value-conditional s...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dongyoung Kim Jinwoo Shin Pieter Abbeel Younggyo Seo KAIST UC Berkeley KAIST and Dyson Robot Learning Lab.

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：

来源：评论

学校读者我要写书评

暂无评论

Language-Conditioned Path Planning

arXiv

引用

arXiv 2023年

作者： Xie, Amber Lee, Youngwoon Abbeel, Pieter James, Stephen University of California Berkeley United States Dyson Robot Learning Lab Poland

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, limiting their applicability in contact-rich tasks. To address this limitation, we propose the domain of Language-Conditioned Path Planning, where contact-awareness is incorporated into the path planning problem. As a first step in this domain, we propose Language-Conditioned Collision Functions (LACO), a novel approach that learns a collision function using only a single-view image, language prompt, and robot configuration. LACO predicts collisions between the robot and the environment, enabling flexible, conditional path planning without the need for manual object annotations, point cloud data, or ground-truth object meshes. In both simulation and the real world, we demonstrate that LACO can facilitate complex, nuanced path plans that allow for interaction with objects that are safe to collide, rather than prohibiting any collision. © 2023, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

InsActor: instruction-driven physics-based characters 23

InsActor: instruction-driven physics-based characters

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jiawei Ren Mingyuan Zhang Cunjun Yu Xiao Ma Liang Pan Ziwei Liu S-Lab Nanyang Technological University National University of Singapore Dyson Robot Learning Lab

Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications. However, generating physically simulated animations that reflect high-level human instructions remains a difficult problem due to the complexity of physical environments and the richness of human language. In this paper, we present InsActor, a principled generative framework that leverages recent advancements in diffusion-based human motion models to produce instruction-driven animations of physics-based characters. Our framework empowers InsActor to capture complex relationships between high-level human instructions and character motions by employing diffusion policies for flexibly conditioned motion planning. To overcome invalid states and infeasible state transitions in planned motions, InsActor discovers low-level skills and maps plans to latent skill sequences in a compact latent space. Extensive experiments demonstrate that InsActor achieves state-of-the-art results on various tasks, including instruction-driven motion generation and instruction-driven waypoint heading. Notably, the ability of InsActor to generate physically simulated animations using high-level human instructions makes it a valuable tool, particularly in executing long-horizon tasks with a rich set of instructions. Our project page is available at ***/projects/insactor/***

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：