研究兴趣

论文共 31 篇作者统计合作学者相似作者

按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Suvir Mirchandani,Fei Xia, Pete Florence,Brian Ichter,Danny Driess, Montserrat Gonzalez Arenas,Kanishka Rao,Dorsa Sadigh, Andy Zeng
引用19浏览0EI引用
19
0
Abhishek Padalkar,Acorn Pooley, Ajinkya Jain,Alex Bewley, Alex Herzog, Alex Irpan, Alexander Khazatsky, Anant Rai,Anikait Singh, Anthony Brohan, Antonin Raffin,Ayzaan Wahid,
引用0浏览0引用
0
0
引用0浏览0引用
0
0
加载更多
作者统计
  • 合作者
  • 学生
  • 导师
暂无相似学者,你可以通过学者研究领域进行搜索筛选
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
s robustness and awareness of the task's feasibility through its own actions and gradual responses to different interferences. ","authors":[{"id":"63bbd181163be4f513f49660","name":"Jason Harris"},{"id":"53f43347dabfaec22ba61a68","name":"Danny Driess"},{"id":"53f5674adabfae6421f8045b","name":"Marc Toussaint"}],"citations":{"google_citation":0},"create_time":"2022-05-10T02:47:39.685Z","doi":"10.1109\u002FIROS47612.2022.9981758","hashs":{"h1":"f3fcc","h3":"c"},"id":"6279c9c65aee126c0fdae7c8","lang":"en","num_citation":0,"pages":{"end":"13776","start":"13769"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F8B\u002F93\u002F68\u002F8B93682717E2CE7EF6B4E8A9E2287E20.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.04362"],"title":"FC 3 : Feasibility-Based Control Chain Coordination.","update_times":{"u_a_t":"2023-01-23T02:55:49.89Z","u_c_t":"2023-10-13T09:55:05.809Z","u_v_t":"2023-03-18T09:36:23.995Z"},"urls":["https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04362","https:\u002F\u002Fdoi.org\u002F10.1109\u002FIROS47612.2022.9981758"],"venue":{"info":{"name":"IEEE\u002FRJS International Conference on Intelligent RObots and Systems (IROS)","name_s":"IROS"}},"venue_hhb_id":"5eba39c4edb6e7d53c0f3a9f","versions":[{"id":"6279c9c65aee126c0fdae7c8","sid":"2205.04362","src":"arxiv","year":2022},{"id":"63b6439690e50fcafd94c52c","sid":"conf\u002Firos\u002FHarrisDT22","src":"dblp","vsid":"conf\u002Firos","year":2022}],"year":2022},{"abstract":" A factored Nonlinear Program (Factored-NLP) explicitly models the dependencies between a set of continuous variables and nonlinear constraints, providing an expressive formulation for relevant robotics problems such as manipulation planning or simultaneous localization and mapping. When the problem is over-constrained or infeasible, a fundamental issue is to detect a minimal subset of variables and constraints that are infeasible.Previous approaches require solving several nonlinear programs, incrementally adding and removing constraints, and are thus computationally expensive. In this paper, we propose a graph neural architecture that predicts which variables and constraints are jointly infeasible. The model is trained with a dataset of labeled subgraphs of Factored-NLPs, and importantly, can make useful predictions on larger factored nonlinear programs than the ones seen during training. We evaluate our approach in robotic manipulation planning, where our model is able to generalize to longer manipulation sequences involving more objects and robots, and different geometric environments. The experiments show that the learned model accelerates general algorithms for conflict extraction (by a factor of 50) and heuristic algorithms that exploit expert knowledge (by a factor of 4). ","authors":[{"id":"63bbd181163be4f513f4963f","name":"Joaquim Ortiz-Haro"},{"id":"56315def45cedb3399daf0d9","name":"Jung-Su Ha"},{"id":"53f43347dabfaec22ba61a68","name":"Danny Driess"},{"id":"53f45395dabfaee1c0b2254c","name":"Erez Karpas"},{"id":"53f5674adabfae6421f8045b","name":"Marc Toussaint"}],"create_time":"2022-10-25T04:45:10.482Z","hashs":{"h1":"lffnp","h3":"rmp"},"id":"635753cb90e50fcafdddd99a","lang":"en","num_citation":1,"pages":{"end":"3735","start":"3729"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002FCC\u002FCB\u002F47\u002FCCCB47C93A182D0C206007A19944765E.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2210.12386"],"title":"Learning Feasibility of Factored Nonlinear Programs in Robotic\n Manipulation Planning","update_times":{"u_a_t":"2022-10-25T04:52:13.071Z","u_c_t":"2023-11-06T04:01:02.506Z"},"urls":["db\u002Fconf\u002Ficra\u002Ficra2023.html#HaroHDKT23","https:\u002F\u002Fdoi.org\u002F10.1109\u002FICRA48891.2023.10160887","https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.12386"],"versions":[{"id":"635753cb90e50fcafdddd99a","sid":"2210.12386","src":"arxiv","year":2022},{"id":"64f561633fda6d7f06f1bafc","sid":"conf\u002Ficra\u002FHaroHDKT23","src":"dblp","year":2023}],"year":2022},{"abstract":" Task and Motion Planning has made great progress in solving hard sequential manipulation problems. However, a gap between such planning formulations and control methods for reactive execution remains. In this paper we propose a model predictive control approach dedicated to robustly execute a single sequence of constraints, which corresponds to a discrete decision sequence of a TAMP plan. We decompose the overall control problem into three sub-problems (solving for sequential waypoints, their timing, and a short receding horizon path) that each is a non-linear program solved online in each MPC cycle. The resulting control strategy can account for long-term interdependencies of constraints and reactively plan for a timing-optimal transition through all constraints. We additionally propose phase backtracking when running constraints of the current phase cannot be fulfilled, leading to a fluent re-initiation behavior that is robust to perturbations and interferences by an experimenter. ","authors":[{"email":"toussaint@tu-berlin.de","id":"53f5674adabfae6421f8045b","name":"Marc Toussaint","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","TU Berlin, Sci Intelligence Excellence Cluster, Berlin, Germany"]},{"id":"63bbd181163be4f513f4964f","name":"Jason Harris","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany"]},{"id":"56315def45cedb3399daf0d9","name":"Jung-Su Ha","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany"]},{"id":"53f43347dabfaec22ba61a68","name":"Danny Driess","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","TU Berlin, Sci Intelligence Excellence Cluster, Berlin, Germany"]},{"id":"6176bc3a60a96541e9c9c2e6","name":"Wolfgang Hönig","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany"]}],"citations":{"google_citation":1},"create_time":"2022-03-11T13:45:28.086Z","doi":"10.1109\u002FIROS47612.2022.9982236","hashs":{"h1":"smrtc","h3":"sm"},"id":"622abdd05aee126c0f56bba3","issn":"2153-0858","lang":"en","num_citation":3,"pages":{"end":"13760","start":"13753"},"pdf":"https:\u002F\u002Fcz5waila03cyo0tux1owpyofgoryroob.aminer.cn\u002F61\u002FE2\u002FD1\u002F61E2D1570D9517F6007FC802783DA37A.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2203.05390"],"title":"Sequence-of-Constraints MPC: Reactive Timing-Optimal Control of Sequential Manipulation.","update_times":{"u_a_t":"2023-01-23T02:55:49.762Z","u_c_t":"2023-10-13T05:56:01.932Z","u_v_t":"2023-03-18T09:36:16.745Z"},"urls":["http:\u002F\u002Fwww.webofknowledge.com\u002F","https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.05390","https:\u002F\u002Fdoi.org\u002F10.1109\u002FIROS47612.2022.9982236"],"venue":{"info":{"name":"IEEE\u002FRJS International Conference on Intelligent RObots and Systems (IROS)","name_s":"IROS"}},"venue_hhb_id":"5eba39c4edb6e7d53c0f3a9f","versions":[{"id":"622abdd05aee126c0f56bba3","sid":"2203.05390","src":"arxiv","year":2022},{"id":"63b6439690e50fcafd94c52a","sid":"conf\u002Firos\u002FToussaintHHDH22","src":"dblp","vsid":"conf\u002Firos","year":2022},{"id":"64d5264c3fda6d7f065a926b","sid":"WOS:000909405304101","src":"wos","year":2022}],"year":2022},{"abstract":" It is a long-standing problem to find effective representations for training reinforcement learning (RL) agents. This paper demonstrates that learning state representations with supervision from Neural Radiance Fields (NeRFs) can improve the performance of RL compared to other learned representations or even low-dimensional, hand-engineered state information. Specifically, we propose to train an encoder that maps multiple image observations to a latent space describing the objects in the scene. The decoder built from a latent-conditioned NeRF serves as the supervision signal to learn the latent space. An RL algorithm then operates on the learned latent space as its state representation. We call this NeRF-RL. Our experiments indicate that NeRF as supervision leads to a latent space better suited for the downstream RL tasks involving robotic object manipulations like hanging mugs on hooks, pushing objects, or opening doors. Video: https:\u002F\u002Fdannydriess.github.io\u002Fnerf-rl ","authors":[{"id":"53f43347dabfaec22ba61a68","name":"Danny Driess","org":"TU Berlin","orgid":"5f71b2901c455f439fe3cbc2","orgs":["TU Berlin"]},{"id":"63725610ec88d95668cd0aae","name":"Ingmar Schubert","org":"Technische Universität Berlin \u002F Learning and Intelligent Systems Group","orgid":"5f71b2901c455f439fe3cbc2","orgs":["Technische Universität Berlin \u002F Learning and Intelligent Systems Group"]},{"id":"53f42b01dabfaec22b9f0b83","name":"Pete Florence","org":"Google","orgid":"5f71b2d21c455f439fe3e823","orgs":["Google"]},{"id":"53f3521adabfae4b3494c795","name":"Yunzhu Li","org":"Stanford University","orgid":"62331e330a6eb147dca8a6e8","orgs":["Stanford University"]},{"id":"53f5674adabfae6421f8045b","name":"Marc Toussaint","org":"TU Berlin","orgid":"5f71b2901c455f439fe3cbc2","orgs":["TU Berlin"]}],"citations":{"google_citation":6,"last_citation":6},"create_time":"2022-06-06T04:45:42.004Z","hashs":{"h1":"rlnrf"},"id":"629d70385aee126c0f302692","keywords":["RL","NeRF","Computer Vision","Representation Learning","Robotic Manipulation","Neural Implicit Representations"],"lang":"en","num_citation":32,"pdf":"https:\u002F\u002Fstatic.aminer.cn\u002Fupload\u002Fpdf\u002F1788\u002F1803\u002F815\u002F629d70385aee126c0f302692_0.pdf","pdf_src":["https:\u002F\u002Farxiv.org\u002Fpdf\u002F2206.01634","https:\u002F\u002Fapi.openreview.net\u002Fpdf\u002F5bcc9448dd1f37123b2007b2052a56a2cd569b30.pdf"],"title":"Reinforcement Learning with Neural Radiance Fields","update_times":{"u_a_t":"2022-06-06T05:24:42.693Z","u_c_t":"2023-11-07T10:11:13.496Z","u_v_t":"2023-11-09T16:02:08.843Z"},"urls":["db\u002Fconf\u002Fnips\u002Fneurips2022.html#DriessSFLT22","http:\u002F\u002Fpapers.nips.cc\u002Fpaper_files\u002Fpaper\u002F2022\u002Fhash\u002F6c294f059e3d77d58dbb8fe48f21fe00-Abstract-Conference.html","https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.01634","https:\u002F\u002Fopenreview.net\u002Fforum?id=3SLW-YIw7tX"],"venue":{"info":{"name":"NeurIPS 2022"}},"venue_hhb_id":"5ea1e340edb6e7d53c011a4c","versions":[{"id":"629d70385aee126c0f302692","sid":"2206.01634","src":"arxiv","year":2022},{"id":"63a413f690e50fcafd6d1b30","sid":"neurips2022#147828","src":"conf_neurips","year":2022},{"id":"6479e3acd68f896efa4e5c4a","sid":"conf\u002Fnips\u002FDriessSFLT22","src":"dblp","year":2022}],"year":2022},{"abstract":"Hierarchical coordination of controllers often uses symbolic state representations that fully abstract their underlying low-level controllers, treating them as \"black boxes\" to the symbolic action abstraction. This paper proposes a framework to realize robust behavior, which we call Feasibility-based Control Chain Coordination (FC3). Our controllers expose the geometric features and constraints they operate on. Based on this, FC3 can reason over the controllers' feasibility and their sequence feasibility. For a given task, FC3 first automatically constructs a library of potential controller chains using a symbolic action tree, which is then used to coordinate controllers in a chain, evaluate task feasibility, as well as switching between controller chains if necessary. In several real-world experiments we demonstrate FC3's robustness and awareness of the task's feasibility through its own actions and gradual responses to different interferences.","authors":[{"email":"harris.e.jason@gmail.com","id":"63bbd181163be4f513f49660","name":"Jason Harris","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany"]},{"id":"53f43347dabfaec22ba61a68","name":"Danny Driess","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","TU Berlin, Sci Intelligence Excellence Cluster, Berlin, Germany"]},{"id":"53f5674adabfae6421f8045b","name":"Marc Toussaint","org":"TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","orgs":["TU Berlin, Learning & Intelligent Syst Lab, Berlin, Germany","TU Berlin, Sci Intelligence Excellence Cluster, Berlin, Germany"]}],"create_time":"2023-10-27T09:19:49.755Z","hashs":{"h1":"ffccc"},"id":"64d5264a3fda6d7f065a8be5","issn":"2153-0858","num_citation":0,"pages":{"end":"13776","start":"13769"},"title":"FC3: Feasibility-Based Control Chain Coordination","urls":["http:\u002F\u002Fwww.webofknowledge.com\u002F"],"venue":{"info":{"name":"2022 IEEE\u002FRSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)"}},"versions":[{"id":"64d5264a3fda6d7f065a8be5","sid":"WOS:000909405304103","src":"wos","year":2022}],"year":2022}],"profilePubsTotal":31,"profilePatentsPage":0,"profilePatents":null,"profilePatentsTotal":null,"profilePatentsEnd":false,"profileProjectsPage":1,"profileProjects":{"success":true,"msg":"","data":null,"log_id":"2Ynemrgc731vFITObNQT0IkjUtp"},"profileProjectsTotal":0,"newInfo":null,"checkDelPubs":[]}};