Conference on Robot Learning最新文献_第5页

Learning Visualization Policies of Augmented Reality for Human-Robot Collaboration 面向人机协作的增强现实学习可视化策略

Conference on Robot Learning Pub Date : 2022-11-13 DOI: 10.48550/arXiv.2211.07028

Kishan Chandan, Jack Albertson, Shiqi Zhang

{"title":"Learning Visualization Policies of Augmented Reality for Human-Robot Collaboration","authors":"Kishan Chandan, Jack Albertson, Shiqi Zhang","doi":"10.48550/arXiv.2211.07028","DOIUrl":"https://doi.org/10.48550/arXiv.2211.07028","url":null,"abstract":"In human-robot collaboration domains, augmented reality (AR) technologies have enabled people to visualize the state of robots. Current AR-based visualization policies are designed manually, which requires a lot of human efforts and domain knowledge. When too little information is visualized, human users find the AR interface not useful; when too much information is visualized, they find it difficult to process the visualized information. In this paper, we develop a framework, called VARIL, that enables AR agents to learn visualization policies (what to visualize, when, and how) from demonstrations. We created a Unity-based platform for simulating warehouse environments where human-robot teammates collaborate on delivery tasks. We have collected a dataset that includes demonstrations of visualizing robots' current and planned behaviors. Results from experiments with real human participants show that, compared with competitive baselines from the literature, our learned visualization strategies significantly increase the efficiency of human-robot teams, while reducing the distraction level of human users. VARIL has been demonstrated in a built-in-lab mock warehouse.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121889522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Learning Riemannian Stable Dynamical Systems via Diffeomorphisms 通过微分同态学习黎曼稳定动力系统

Conference on Robot Learning Pub Date : 2022-11-06 DOI: 10.48550/arXiv.2211.03169

Jiechao Zhang, H. Mohammadi, L. Rozo

引用次数: 2

Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics 剩余技能策略:学习一个可适应的基于技能的机器人强化学习行动空间

Conference on Robot Learning Pub Date : 2022-11-04 DOI: 10.48550/arXiv.2211.02231

Krishan Rana, Ming Xu, Brendan Tidd, Michael Milford, N. Sunderhauf

{"title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","authors":"Krishan Rana, Ming Xu, Brendan Tidd, Michael Milford, N. Sunderhauf","doi":"10.48550/arXiv.2211.02231","DOIUrl":"https://doi.org/10.48550/arXiv.2211.02231","url":null,"abstract":"Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration in the skill space using state-conditioned generative models to directly bias the high-level agent towards only sampling skills relevant to a given state based on prior experience. Next, we propose a low-level residual policy for fine-grained skill adaptation enabling downstream RL agents to adapt to unseen task variations. Finally, we validate our approach across four challenging manipulation tasks that differ from those used to build the skill space, demonstrating our ability to learn across task variations while significantly accelerating exploration, outperforming prior works. Code and videos are available on our project website: https://krishanrana.github.io/reskill.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131522907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Leveraging Fully Observable Policies for Learning under Partial Observability 利用完全可观察策略进行部分可观察学习

Conference on Robot Learning Pub Date : 2022-11-03 DOI: 10.48550/arXiv.2211.01991

Hai V. Nguyen, Andrea Baisero, Dian Wang, Chris Amato, Robert W. Platt

{"title":"Leveraging Fully Observable Policies for Learning under Partial Observability","authors":"Hai V. Nguyen, Andrea Baisero, Dian Wang, Chris Amato, Robert W. Platt","doi":"10.48550/arXiv.2211.01991","DOIUrl":"https://doi.org/10.48550/arXiv.2211.01991","url":null,"abstract":"Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that uses a fully observable policy (which we call a state expert) during offline training to improve online performance. Based on Soft Actor-Critic (SAC), our agent balances performing actions similar to the state expert and getting high returns under partial observability. Our approach can leverage the fully-observable policy for exploration and parts of the domain that are fully observable while still being able to learn under partial observability. On six robotics domains, our method outperforms pure imitation, pure reinforcement learning, the sequential or parallel combination of both types, and a recent state-of-the-art method in the same setting. A successful policy transfer to a physical robot in a manipulation task from pixels shows our approach's practicality in learning interesting policies under partial observability.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125436143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Learning to Grasp the Ungraspable with Emergent Extrinsic Dexterity 学会用突发的外在灵活性掌握不可掌握的东西

Conference on Robot Learning Pub Date : 2022-11-02 DOI: 10.48550/arXiv.2211.01500

Wen-Min Zhou, David Held

{"title":"Learning to Grasp the Ungraspable with Emergent Extrinsic Dexterity","authors":"Wen-Min Zhou, David Held","doi":"10.48550/arXiv.2211.01500","DOIUrl":"https://doi.org/10.48550/arXiv.2211.01500","url":null,"abstract":"A simple gripper can solve more complex manipulation tasks if it can utilize the external environment such as pushing the object against the table or a vertical wall, known as\"Extrinsic Dexterity.\"Previous work in extrinsic dexterity usually has careful assumptions about contacts which impose restrictions on robot design, robot motions, and the variations of the physical parameters. In this work, we develop a system based on reinforcement learning (RL) to address these limitations. We study the task of\"Occluded Grasping\"which aims to grasp the object in configurations that are initially occluded; the robot needs to move the object into a configuration from which these grasps can be achieved. We present a system with model-free RL that successfully achieves this task using a simple gripper with extrinsic dexterity. The policy learns emergent behaviors of pushing the object against the wall to rotate and then grasp it without additional reward terms on extrinsic dexterity. We discuss important components of the system including the design of the RL problem, multi-grasp training and selection, and policy generalization with automatic curriculum. Most importantly, the policy trained in simulation is zero-shot transferred to a physical robot. It demonstrates dynamic and contact-rich motions with a simple gripper that generalizes across objects with various size, density, surface friction, and shape with a 78% success rate. Videos can be found at https://sites.google.com/view/grasp-ungraspable/.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133922816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 21

Real-time Mapping of Physical Scene Properties with an Autonomous Robot Experimenter

Conference on Robot Learning Pub Date : 2022-10-31 DOI: 10.48550/arXiv.2210.17325

I. Haughton, Edgar Sucar, A. Mouton, Edward Johns, A. Davison

引用次数: 1

Adapting Neural Models with Sequential Monte Carlo Dropout 时序蒙特卡罗Dropout神经模型的自适应

Conference on Robot Learning Pub Date : 2022-10-27 DOI: 10.48550/arXiv.2210.15779

Pamela Carreno-Medrano, Dana Kuli'c, Michael Burke

引用次数: 0

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation 面向可变形对象操作的点云时空抽象规划

Conference on Robot Learning Pub Date : 2022-10-27 DOI: 10.48550/arXiv.2210.15751

Xingyu Lin, Carl Qi, Yunchu Zhang, Zhiao Huang, Katerina Fragkiadaki, Yunzhu Li, Chuang Gan, David Held

引用次数: 16

Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data 通过模拟到真实:端到端无真实数据的越野自动驾驶

Conference on Robot Learning Pub Date : 2022-10-25 DOI: 10.48550/arXiv.2210.14721

John So, Amber Xie, Sunggoo Jung, J. Edlund, Rohan Thakker, Ali-akbar Agha-mohammadi, P. Abbeel, Stephen James

{"title":"Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data","authors":"John So, Amber Xie, Sunggoo Jung, J. Edlund, Rohan Thakker, Ali-akbar Agha-mohammadi, P. Abbeel, Stephen James","doi":"10.48550/arXiv.2210.14721","DOIUrl":"https://doi.org/10.48550/arXiv.2210.14721","url":null,"abstract":"Autonomous driving is complex, requiring sophisticated 3D scene understanding, localization, mapping, and control. Rather than explicitly modelling and fusing each of these components, we instead consider an end-to-end approach via reinforcement learning (RL). However, collecting exploration driving data in the real world is impractical and dangerous. While training in simulation and deploying visual sim-to-real techniques has worked well for robot manipulation, deploying beyond controlled workspace viewpoints remains a challenge. In this paper, we address this challenge by presenting Sim2Seg, a re-imagining of RCAN that crosses the visual reality gap for off-road autonomous driving, without using any real-world data. This is done by learning to translate randomized simulation images into simulated segmentation and depth maps, subsequently enabling real-world images to also be translated. This allows us to train an end-to-end RL policy in simulation, and directly deploy in the real-world. Our approach, which can be trained in 48 hours on 1 GPU, can perform equally as well as a classical perception and control stack that took thousands of engineering hours over several months to build. We hope this work motivates future end-to-end autonomous driving research.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115072129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

MidasTouch: Monte-Carlo inference over distributions across sliding touch MidasTouch:滑动触摸分布的蒙特卡罗推断

Conference on Robot Learning Pub Date : 2022-10-25 DOI: 10.48550/arXiv.2210.14210

Sudharshan Suresh, Zilin Si, Stuart Anderson, M. Kaess, Mustafa Mukadam

{"title":"MidasTouch: Monte-Carlo inference over distributions across sliding touch","authors":"Sudharshan Suresh, Zilin Si, Stuart Anderson, M. Kaess, Mustafa Mukadam","doi":"10.48550/arXiv.2210.14210","DOIUrl":"https://doi.org/10.48550/arXiv.2210.14210","url":null,"abstract":"We present MidasTouch, a tactile perception system for online global localization of a vision-based touch sensor sliding on an object surface. This framework takes in posed tactile images over time, and outputs an evolving distribution of sensor pose on the object's surface, without the need for visual priors. Our key insight is to estimate local surface geometry with tactile sensing, learn a compact representation for it, and disambiguate these signals over a long time horizon. The backbone of MidasTouch is a Monte-Carlo particle filter, with a measurement model based on a tactile code network learned from tactile simulation. This network, inspired by LIDAR place recognition, compactly summarizes local surface geometries. These generated codes are efficiently compared against a precomputed tactile codebook per-object, to update the pose distribution. We further release the YCB-Slide dataset of real-world and simulated forceful sliding interactions between a vision-based tactile sensor and standard YCB objects. While single-touch localization can be inherently ambiguous, we can quickly localize our sensor by traversing salient surface geometries. Project page: https://suddhu.github.io/midastouch-tactile/","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130776340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 19