{"list":"other","total":67,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2303.00905","title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","created":"2023-03-02","cited_by_count":156},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145},{"id":"2311.01977","title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","created":"2023-11-03","cited_by_count":133},{"id":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121},{"id":"2403.08248","title":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","created":"2024-03-13","cited_by_count":99},{"id":"2202.05481","title":"Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion","created":"2022-02-11","cited_by_count":88},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83},{"id":"2407.10353","title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","created":"2024-07-14","cited_by_count":75},{"id":"2110.05457","title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","created":"2021-10-11","cited_by_count":71},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62},{"id":"2209.12827","title":"Advanced Skills by Learning Locomotion and Local Navigation End-to-End","created":"2022-09-26","cited_by_count":52},{"id":"2310.13065","title":"Creative Robot Tool Use with Large Language Models","created":"2023-10-19","cited_by_count":43},{"id":"2304.00410","title":"ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation","created":"2023-04-01","cited_by_count":42},{"id":"2306.07580","title":"SayTap: Language to Quadrupedal Locomotion","created":"2023-06-13","cited_by_count":41},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41},{"id":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","cited_by_count":39},{"id":"2201.03871","title":"Combining Learning-based Locomotion Policy with Model-based Manipulation for Legged Mobile Manipulators","created":"2022-01-11","cited_by_count":37},{"id":"2310.03191","title":"Sim-to-Real Learning for Humanoid Box Loco-Manipulation","created":"2023-10-04","cited_by_count":36},{"id":"2104.09025","title":"The MIT Humanoid Robot: Design, Motion Planning, and Control For Acrobatic Behaviors","created":"2021-04-19","cited_by_count":32},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","cited_by_count":27},{"id":"2305.17842","title":"RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion","created":"2023-05-29","cited_by_count":26},{"id":"2308.16820","title":"Learning Whole-body Manipulation for Quadrupedal Robot","created":"2023-08-31","cited_by_count":25},{"id":"2405.01402","title":"Learning Force Control for Legged Manipulation","created":"2024-05-02","cited_by_count":21},{"id":"2403.20328","title":"Learning Visual Quadrupedal Loco-Manipulation from Demonstrations","created":"2024-03-29","cited_by_count":20},{"id":"2203.01446","title":"RoLoMa: Robust Loco-Manipulation for Quadruped Robots with Arms","created":"2022-03-02","cited_by_count":16},{"id":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15},{"id":"2204.01147","title":"Continuous Jumping for Legged Robots on Stepping Stones via Trajectory Optimization and Model Predictive Control","created":"2022-04-03","cited_by_count":10},{"id":"2209.07654","title":"Cerberus: Low-Drift Visual-Inertial-Leg Odometry For Agile Locomotion","created":"2022-09-16","cited_by_count":10},{"id":"2403.18197","title":"LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators","created":"2024-03-27","cited_by_count":10},{"id":"2408.16567","title":"Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigation","created":"2024-08-29","cited_by_count":10},{"id":"2304.08663","title":"Continuous Versatile Jumping Using Learned Action Residuals","created":"2023-04-17","cited_by_count":8},{"id":"2401.09388","title":"CognitiveDog: Large Multimodal Model Based System to Translate Vision and Language into Action of Quadruped Robot","created":"2024-01-17","cited_by_count":7}],"next_cursor":null}