Andy Zeng

収録論文 45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

• ロボットナビゲーションと操作のためのマルチモーダル空間言語マップ
  VLA2025/6/1

  視覚・言語・音声の特徴を3D環境再構成に融合した空間マップを構築し、LLMと組み合わせて自然言語指示やマルチモーダルな目標を地図上に定位してロボットのナビゲーションと操作を可能にする手法を提案。

• 二本腕の身体性AI：ゼロショット学習、安全性、モジュール性
  マニピュレーション2024/4/1

  自然言語指示に基づき二本腕ロボットが協調して長期的タスクをゼロショットで実行するモジュール型身体性AIシステムを提案。安全性とモジュール性を重視し、実世界データなしで動作する。

• 基盤モデルの実世界ロボット応用：レビュー
  基盤モデル応用2024/2/1

  LLMやVLMなどの基盤モデルを実ロボットシステムの知覚・運動計画・制御にどう組み込むかを、入出力関係の観点から整理したレビュー。

• 言語モデル予測制御による人間フィードバックからの高速学習
  VLA2024/2/1

  人間との対話履歴を遷移モデルとしてLLMに微調整し、モデル予測制御と組み合わせることで、ロボットの教示効率と成功率を向上させるフレームワークLMPCを提案。

• PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
  2024/2/1
• Generative Expressive Robot Behaviors using Large Language Models
  2024/1/1
• Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
  2023/12/1
• Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
  2023/11/1
• Video Language Planning
  2023/10/1
• Large Language Models as General Pattern Machines
  2023/7/1
• Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
  2023/7/1
• Rearrangement Planning for General Part Assembly
  2023/7/1
• Language to Rewards for Robotic Skill Synthesis
  2023/6/1
• TidyBot: Personalized Robot Assistance with Large Language Models
  2023/5/1
• RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning
  2023/4/1
• Audio Visual Language Maps for Robot Navigation
  2023/3/1
• Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents
  2023/3/1
• PaLM-E: An Embodied Multimodal Language Model
  2023/3/1
• MIRA: Mental Imagery for Robotic Affordances
  2022/12/1
• VIRDO++: Real-World, Visuo-tactile Dynamics and Perception of Deformable Objects
  2022/10/1
• Visual Language Maps for Robot Navigation
  2022/10/1
• Code as Policies: Language Model Programs for Embodied Control
  2022/9/1
• Inner Monologue: Embodied Reasoning through Planning with Language Models
  2022/7/1
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
  2022/4/1
• Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower
  2022/4/1
• Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research
  2022/4/1
• Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot Learning
  2022/3/1
• Multiscale Sensor Fusion and Continuous Control with Neural CDEs
  2022/3/1
• VIRDO: Visio-tactile Implicit Representations of Deformable Objects
  2022/2/1
• Multi-Task Learning with Sequence-Conditioned Transporter Networks
  2021/9/1
• Implicit Behavioral Cloning
  2021/9/1
• Learning to See before Learning to Act: Visual Pre-training for Manipulation
  2021/7/1
• XIRL: Cross-embodiment Inverse Reinforcement Learning
  2021/6/1
• Spatial Intention Maps for Multi-Agent Mobile Manipulation
  2021/3/1
• Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks
  2020/12/1
• Transporter Networks: Rearranging the Visual World for Robotic Manipulation
  2020/10/1
• Spatial Action Maps for Mobile Manipulation
  2020/4/1
• Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
  2019/12/1
• ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
  2019/10/1
• Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
  2019/10/1
• DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
  2019/6/1
• TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
  2019/3/1
• Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
  2018/3/1
• Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
  2017/10/1
• Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge
  2016/9/1