Pulkit Agrawal
収録論文 65本 ・ フィジカルAI/ロボット学習
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- Learning More from Less: Reinforcement Learning from Hindsight2026/7/10
- Prompt-Driven Exploration2026/7/9
- What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?2026/6/1
- KaRMA: A Kinematic Metric for Fine Manipulation Ability in Robotic Hands2026/5/1
- Tune to Learn: How Controller Gains Shape Robot Policy Learning2026/4/1
- Agile asymmetric multi-legged locomotion: contact planning via geometric mechanics and spin model duality2026/2/1
- SoftMimic: Learning Compliant Whole-body Control from Examples2025/10/1
- DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation2025/9/1
- DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation2025/7/1
- Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning2025/2/1
- Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation2025/2/1
- Robot Learning with Super-Linear Scaling2024/12/1
- Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning2024/12/1
- DexHub and DART: Towards Internet Scale Robot Data Collection2024/11/1
- Embodied Red Teaming for Auditing Robotic Foundation Models2024/11/1
- Few-Shot Task Learning through Inverse Generative Modeling2024/11/1
- Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck2024/11/1
- ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization2024/10/1
- Diffusion Policy Policy Optimization2024/9/1
- EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation2024/8/1
- Everyday Finger: A Robotic Finger that Meets the Needs of Everyday Interactive Manipulation2024/8/1
- Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation2024/7/1
- From Imitation to Refinement -- Residual RL for Precise Assembly2024/7/1
- ROER: Regularized Optimal Experience Replay2024/7/1
- Automatic Environment Shaping is the Next Frontier in RL2024/7/1
- Learning Force Control for Legged Manipulation2024/5/1
- JUICER: Data-Efficient Imitation Learning for Robotic Assembly2024/4/1
- Rank2Reward: Learning Shaped Reward Functions from Passive Video2024/4/1
- Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation2024/3/1
- Learning to See Physical Properties with Active Sensing Motor Policies2023/11/1
- Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback2023/10/1
- Compositional Foundation Models for Hierarchical Planning2023/9/1
- Lifelong Robot Learning with Human Assisted Language Planners2023/9/1
- Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement2023/7/1
- Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building2023/7/1
- Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation2023/7/1
- Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback2023/7/1
- Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation2023/7/1
- DribbleBot: Dynamic Legged Manipulation in the Wild2023/4/1
- TactoFind: A Tactile Only System for Object Retrieval2023/3/1
- Aligning Robot and Human Representations2023/2/1
- Geometry of contact: contact planning for multi-legged robots via spin models duality2023/2/1
- Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior2022/12/1
- Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes2022/11/1
- Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning2022/11/1
- SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields2022/11/1
- Stable Object Reorientation using Contact Plane Registration2022/8/1
- Rapid Locomotion via Reinforcement Learning2022/5/1
- An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators2022/4/1
- Stubborn: A Strong Baseline for Indoor Object Navigation2022/3/1
- Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation2021/12/1
- A System for General In-Hand Object Re-Orientation2021/11/1
- Learning to Jump from Pixels2021/10/1
- An End-to-End Differentiable Framework for Contact-Aware Robot Design2021/7/1
- 3D Neural Scene Representations for Visuomotor Control2021/7/1
- Learning Task Informed Abstractions2021/6/1
- Residual Model Learning for Microrobot Control2021/4/1
- A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects2020/11/1
- Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning2019/12/1
- Learning Instance Segmentation by Interaction2018/6/1
- Zero-Shot Visual Imitation2018/4/1
- Curiosity-driven Exploration by Self-supervised Prediction2017/5/1
- Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation2017/3/1
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics2016/6/1
- Learning to See by Moving2015/5/1