![UT-Austin Robot Perception and Learning Lab](/img/default-banner.jpg)
- 34
- 16 493
UT-Austin Robot Perception and Learning Lab
United States
Приєднався 22 чер 2021
Welcome to the Robot Perception and Learning (RPL) Lab at the University of Texas at Austin! Our research focuses on two intimately connected research threads: Robotics and Embodied AI. We investigate the synergistic relations of perception and action in embodied agents and build intelligent algorithms that give rise to general-purpose robot autonomy.
Model-Based Runtime Monitoring with Interactive Imitation Learning
Model-Based Runtime Monitoring with Interactive Imitation Learning. Huihan Liu, Shivin Dass, Roberto Martín-Martín, Yuke Zhu. International Conference on Robotics and Automation (ICRA), 2024.
Paper: arxiv.org/abs/2310.17552
Project: ut-austin-rpl.github.io/sirius-runtime-monitor/
Paper: arxiv.org/abs/2310.17552
Project: ut-austin-rpl.github.io/sirius-runtime-monitor/
Переглядів: 167
Відео
LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery
Переглядів 1892 місяці тому
LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery. Weikang Wan, Yifeng Zhu*, Rutav Shah*, Yuke Zhu. International Conference on Robotics and Automation (ICRA), 2024 Paper link: arxiv.org/abs/2311.02058 Project link: ut-austin-rpl.github.io/Lotus/ Github: github.com/UT-Austin-RPL/Lotus
Doduo: Dense Visual Correspondence from Unsupervised Semantic-Aware Flow
Переглядів 1342 місяці тому
Doduo: Dense Visual Correspondence from Unsupervised Semantic-Aware Flow. Zhenyu Jiang, Hanwen Jiang, Yuke Zhu. IEEE International Conference on Robotics and Automation (ICRA), May 2024. Paper link: arxiv.org/abs/2309.15110 Project link: ut-austin-rpl.github.io/Doduo/ Github: github.com/UT-Austin-RPL/Doduo
FORGE: Few-view Object Reconstruction with Unknown Categories and Camera Poses
Переглядів 2675 місяців тому
International Conference on 3D Vision (3DV), 2024 Authors: Hanwen Jiang, Zhenyu Jiang, Kristen Grauman, Yuke Zhu Arxiv link: arxiv.org/abs/2210.11339 Project website: ut-austin-rpl.github.io/FORGE/ Code: github.com/UT-Austin-RPL/FORGE
Pathway to Generalist Robots: Scaling Law, Data Flywheel, and Humanlike Embodiment
Переглядів 1,4 тис.6 місяців тому
CoRL2023 Early Career Keynote - Yuke Zhu (November 8th, 2023) Title: Pathway to Generalist Robots: Scaling Law, Data Flywheel, and Humanlike Embodiment Abstract: We have witnessed remarkable advancements in developing generalist models in AI and Machine Learning. These models, such as OpenAI's ChatGPT, can be applied to various tasks in open domains. The creation of these generalist AI models p...
Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation
Переглядів 2,5 тис.8 місяців тому
Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation. Mingyo Seo, Steve Han, Kyutae Sim, Seung Hyeon Bang, Carlos Gonzalez, Luis Sentis, Yuke Zhu. IEEE-RAS International Conference on Humanoid Robots (Humanoids), Dec 2023 Paper link: arxiv.org/abs/2309.01952 Project link: ut-austin-rpl.github.io/TRILL Github: github.com/UT-Austin-RPL/TRILL
Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment.
Переглядів 2209 місяців тому
Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment. Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao, Yuke Zhu. Robotics: Science and Systems (RSS), 2023 Paper link: arxiv.org/abs/2211.08416 Project link: ut-austin-rpl.github.io/sirius/ Github: github.com/UT-Austin-RPL/sirius
MUTEX: Learning Unified Policies from Multimodal Task Specifications
Переглядів 7710 місяців тому
CoRL 2023 Spotlight Video MUTEX: Learning Unified Policies from Multimodal Task Specifications. Rutav Shah, Roberto Martín-Martín, Yuke Zhu. 7th Annual Conference on Robot Learning (CoRL), Nov 2023. Project: ut-austin-rpl.github.io/MUTEX Paper: arxiv.org/abs/2309.14320 Codebase: github.com/UT-Austin-RPL/mutex
GROOT: Learning Generalizable Manipulation Policies with Object-Centric 3D Representations
Переглядів 61610 місяців тому
CoRL 2023 spotlight video. Learning Generalizable Manipulation Policies with Object-Centric 3D Representations. Yifeng Zhu, Zhenyu Jiang, Peter Stone, Yuke Zhu. 7th Annual Conference on Robot Learning (CoRL), Nov 2023. Project: ut-austin-rpl.github.io/GROOT/ Paper: arxiv.org/abs/2310.14386 Code: github.com/UT-Austin-RPL/GROOT
3DVR @ CVPR 2023 - Xiaolong Wang
Переглядів 427Рік тому
Talk: Geometric Robot Learning for Generalizable Dexterous Manipulation Speaker: Xiaolong Wang, University of California San Diego
3DVR @ CVPR 2023 - Angel Xuan Chang
Переглядів 375Рік тому
Talk: Towards Intelligent Home Robots Speaker: Angel Xuan Chang, Simon Fraser University
3DVR @ CVPR 2023 - Andrew Davison
Переглядів 864Рік тому
Talk: Real-Time 3D Scene Representation for Robotics Speaker: Andrew Davison, Imperial College London
3DVR @ CVPR 2023 - Saurabh Gupta
Переглядів 386Рік тому
Talk: Understanding and Articulating Articulated Objects Speaker: Saurabh Gupta, University of Illinois Urbana-Champaign
3DVR @ CVPR 2023 - Georgia Gkioxari
Переглядів 740Рік тому
Talk: Towards 3D Object Detection in the Wild Speaker: Georgia Gkioxari, California Institute of Technology
3DVR @ CVPR 2023 - Cewu Lu
Переглядів 327Рік тому
Talk: General Robotic Grasping with Human-like Capability ad High Learning Efficiency Speaker: Cewu Lu, Shanghai Jiao Tong University
DRACO’s Cooking Show - Humanoid VR Teleoperation Demo
Переглядів 176Рік тому
DRACO’s Cooking Show - Humanoid VR Teleoperation Demo
Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments
Переглядів 129Рік тому
Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
Переглядів 233Рік тому
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
Ditto: Building Digital Twins of Articulated Objects from Interaction
Переглядів 1 тис.Рік тому
Ditto: Building Digital Twins of Articulated Objects from Interaction
Coopernaut: End-to-End Driving with Cooperative Perception for Networked Vehicles
Переглядів 1732 роки тому
Coopernaut: End-to-End Driving with Cooperative Perception for Networked Vehicles
MAPLE: Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Переглядів 4492 роки тому
MAPLE: Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
Переглядів 2602 роки тому
Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation
Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
Переглядів 4303 роки тому
Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
cool
Wow, this is so amazing! Thanks for uploading it to youtube.