世界模型 - arXivDaily 专题

2310.17552 2024-03-11 cs.RO cs.AI cs.LG 50%

Model-Based Runtime Monitoring with Interactive Imitation Learning

Huihan Liu, Shivin Dass, Roberto Martín-Martín, Yuke Zhu

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2308.14947 2024-03-01 cs.RO cs.LG cs.MA 50%

Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation

Adam Sigal, Hsiu-Chin Lin, AJung Moon

专题命中具身与机器人：分类 cs.LG、cs.RO、cs.MA；dynamics model(abstract)

Comments NeurIPS 2023 Workshop on Generalization in Planning, 2023

2210.01426 2024-02-08 cs.AI cs.LG cs.RO 50%

Continuous Monte Carlo Graph Search

Kalle Kujanpää, Amin Babadi, Yi Zhao, Juho Kannala, Alexander Ilin, Joni Pajarinen

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments Accepted at AAMAS 2024 (full paper & oral)

2312.01473 2023-12-05 cs.LG 50%

Regularity as Intrinsic Reward for Free Play

Cansu Sancaktar, Justus Piater, Georg Martius

专题命中具身与机器人：model-based reinforcement learning(abstract)；分类 cs.LG

Comments NeurIPS 2023 camera-ready version. Project webpage at http://sites.google.com/view/rair-project

2307.14272 2023-07-27 cs.RO 50%

Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing

Max Yang, Yijiong Lin, Alex Church, John Lloyd, Dandan Zhang, David A. W. Barton, Nathan F. Lepora

专题命中具身与机器人：model-based RL(abstract)；分类 cs.RO

Comments Accepted by IEEE Robotics and Automation Letters (RA-L)

2303.03675 2023-07-27 cs.RO 50%

End-to-End Learning of Deep Visuomotor Policy for Needle Picking

Hongbin Lin, Bin Li, Xiangyu Chu, Qi Dou, Yunhui Liu, Kwok Wai Samuel Au

专题命中具身与机器人：model-based reinforcement learning(abstract)；分类 cs.RO

Comments Accepted by IROS 2023

2306.16700 2023-07-03 cs.RO cs.CV cs.LG 50%

Dynamic-Resolution Model Learning for Object Pile Manipulation

Yixuan Wang, Yunzhu Li, Katherine Driggs-Campbell, Li Fei-Fei, Jiajun Wu

专题命中具身与机器人：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments Accepted to Robotics: Science and Systems (RSS) 2023. The first two authors contributed equally. Project Page: https://robopil.github.io/dyn-res-pile-manip

2306.14601 2023-06-27 cs.RO cs.CV cs.LG 50%

Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception

Junwon Seo, Jungwi Mun, Taekyung Kim

专题命中具身与机器人：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments RSS 2023 Workshop on Inference and Decision Making for Autonomous Vehicles (IDMAV)

2306.08815 2023-06-16 cs.RO cs.AI cs.MA 50%

Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization

Rohan Chandra, Rahul Menon, Zayne Sprague, Arya Anantula, Joydeep Biswas

专题命中具身与机器人：分类 cs.AI、cs.RO、cs.MA；simulation model(abstract)

Comments Submitted to IROS 2023

2205.01927 2023-05-22 cs.LG cs.AI cs.RO 50%

Probabilistic Symmetry for Multi-Agent Dynamics

Sophia Sun, Robin Walters, Jinxi Li, Rose Yu

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2303.02234 2023-03-10 cs.RO cs.AI cs.LG cs.NE 50%

Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning

Simon Guist, Jan Schneider, Alexander Dittrich, Vincent Berenz, Bernhard Schölkopf, Dieter Büchler

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2302.13378 2023-02-28 cs.RO cs.AI cs.LG 50%

Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive

Milad Shafiee, Guillaume Bellegarda, Auke Ijspeert

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments Accepted for IEEE International Conference on Robotics and Automation (ICRA) 2023

2210.11287 2022-10-21 cs.LG cs.AI cs.RO 50%

MoCoDA: Model-based Counterfactual Data Augmentation

Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda

2209.14041 2022-09-29 cs.RO 50%

Towards Adaptive Planning of Assistive-care Robot Tasks

Jordan Hamilton, Ioannis Stefanakos, Radu Calinescu, Javier Cámara

专题命中具身与机器人：environment model(abstract)；分类 cs.RO

Comments In Proceedings FMAS2022 ASYDE2022, arXiv:2209.13181

Journal ref EPTCS 371, 2022, pp. 175-183

2209.03207 2022-09-08 cs.LG 50%

Concept-modulated model-based offline reinforcement learning for rapid generalization

Nicholas A. Ketz, Praveen K. Pilly

专题命中具身与机器人：model-based reinforcement learning(abstract)；分类 cs.LG

2203.06856 2022-08-09 cs.CV cs.AI cs.RO 50%

ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation

Bokui Shen, Zhenyu Jiang, Christopher Choy, Leonidas J. Guibas, Silvio Savarese, Anima Anandkumar, Yuke Zhu

专题命中具身与机器人：分类 cs.AI、cs.CV、cs.RO；dynamics model(abstract)

Comments RSS 2022 Best Student Paper Award Finalist. Please check out more details at https://b0ku1.github.io/acid/

Journal ref Robotics: Science and Systems (RSS), 2022

2106.08531 2022-08-09 cs.RO 50%

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Taisuke Kobayashi, Shingo Murata, Tetsunari Inamura

专题命中具身与机器人：latent dynamics(abstract)；分类 cs.RO

Comments 10 pages, 10 figures

Journal ref IEEE Transactions on Human-Machine Systems, 2022

2109.08522 2022-07-21 cs.LG cs.AI cs.NE cs.RO 50%

Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires

Bryan Lim, Luca Grillotti, Lorenzo Bernasconi, Antoine Cully

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2203.00551 2022-06-02 cs.RO cs.AI cs.LG math.OC 50%

Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty

Rel Guzman, Rafael Oliveira, Fabio Ramos

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments To appear in the 2022 IEEE International Conference on Robotics and Automation (ICRA), Philadelphia (PA), USA

2203.06783 2022-04-07 cs.RO cs.AI cs.LG cs.SY eess.SY 50%

Adaptive Model Predictive Control by Learning Classifiers

Rel Guzman, Rafael Oliveira, Fabio Ramos

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments To appear in the 4th Annual Learning for Dynamics & Control Conference (L4DC) 2022

2107.08981 2022-03-11 cs.LG cs.AI cs.RO 50%

Hierarchical Few-Shot Imitation with Skill Transition Models

Kourosh Hakhamaneshi, Ruihan Zhao, Albert Zhan, Pieter Abbeel, Michael Laskin

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2201.05830 2022-01-19 cs.RO math.DS stat.ML 50%

Physical Derivatives: Computing policy gradients by physical forward-propagation

Arash Mehrjou, Ashkan Soleymani, Stefan Bauer, Bernhard Schölkopf

专题命中具身与机器人：model-based reinforcement learning(abstract)；分类 cs.RO

2105.10396 2021-12-23 cs.RO cs.CL 50%

Language Understanding for Field and Service Robots in a Priori Unknown Environments

Matthew R. Walter, Siddharth Patki, Andrea F. Daniele, Ethan Fahnestock, Felix Duvallet, Sachithra Hemachandra, Jean Oh, Anthony Stentz, Nicholas Roy, Thomas M. Howard

专题命中具身与机器人：environment model(abstract)；分类 cs.RO

Comments Field Robotics (accepted, to appear)

2107.00306 2021-11-30 cs.LG cs.AI cs.RO 50%

MHER: Model-based Hindsight Experience Replay

Rui Yang, Meng Fang, Lei Han, Yali Du, Feng Luo, Xiu Li

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

Comments NeurIPS 2021 Workshop DeepRL

2107.04004 2021-11-15 cs.RO cs.CV cs.LG 50%

3D Neural Scene Representations for Visuomotor Control

Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba

专题命中具身与机器人：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments Accepted to Conference on Robot Learning (CoRL 2021) as Oral Presentation. The first two authors contributed equally. Project Page: https://3d-representation-learning.github.io/nerf-dy/

2111.05986 2021-11-12 stat.ML cs.LG 50%

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision

Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev

专题命中具身与机器人：latent dynamics(abstract)；分类 cs.LG

2008.02066 2021-11-12 cs.LG cs.AI cs.RO stat.ML 50%

Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals

Ozsel Kilinc, Giovanni Montana

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；predictive model(abstract)

Comments To appear in Deep Reinforcement Learning Workshop, NeurIPS 2021

2107.09996 2021-11-09 cs.RO cs.AI cs.LG 50%

MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments

Dimitrios I. Koutras, Athanasios Ch. Kapoutsis, Angelos A. Amanatiadis, Elias B. Kosmatopoulos

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；simulation model(abstract)

2106.13280 2021-11-08 cs.RO cs.AI cs.LG 50%

Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots

Katie Kang, Gregory Kahn, Sergey Levine

专题命中具身与机器人：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2104.02213 2021-09-14 eess.SY cs.RO cs.SY 50%

Particle MPC for Uncertain and Learning-Based Control

Robert Dyro, James Harrison, Apoorva Sharma, Marco Pavone

专题命中具身与机器人：model-based reinforcement learning(abstract)；分类 cs.RO

Comments Accepted to International Conference on Intelligent Robots and Systems (IROS) 2021

1. 具身与机器人 504 篇

Model-Based Runtime Monitoring with Interactive Imitation Learning

Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation

Continuous Monte Carlo Graph Search

Regularity as Intrinsic Reward for Free Play

Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing

End-to-End Learning of Deep Visuomotor Policy for Needle Picking

Dynamic-Resolution Model Learning for Object Pile Manipulation

Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception

Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization

Probabilistic Symmetry for Multi-Agent Dynamics

Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning

Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive

MoCoDA: Model-based Counterfactual Data Augmentation

Towards Adaptive Planning of Assistive-care Robot Tasks

Concept-modulated model-based offline reinforcement learning for rapid generalization

ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires

Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty

Adaptive Model Predictive Control by Learning Classifiers

Hierarchical Few-Shot Imitation with Skill Transition Models

Physical Derivatives: Computing policy gradients by physical forward-propagation

Language Understanding for Field and Service Robots in a Priori Unknown Environments

MHER: Model-based Hindsight Experience Replay

3D Neural Scene Representations for Visuomotor Control

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision

Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals

MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments

Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots

Particle MPC for Uncertain and Learning-Based Control