Xin Wang

Shanghai AI Laboratory

収録論文 29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

• 見えにくい攻撃：拡散モデルによる視覚言語行動モデルへの無制限ロボット攻撃
  VLA/敵対的攻撃2026/8/11

  拡散モデルを用いて視覚的に自然な敵対的パッチを生成し、VLAモデルのロボット制御を攻撃する手法を提案。ホワイトボックスとブラックボックスの両設定で有効性を実証した。

• 音響駆動ミリメートル螺旋ロボット：閉鎖流体環境における超音波協調操作
  群制御2026/8/6

  音響放射力と音響流の相乗効果を利用し、ミリメートルサイズの螺旋ロボットを制御・推進する手法を提案。シミュレーションと実験で平面移動や傾斜登攀、垂直運動を実証し、生体血管内での往復運動も確認した。

• Acoustic-driven millimetric helical robot: ultrasonic synergistic manipulation in confined fluidic environment
  2026/8/1
• Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models
  2026/8/1
• Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
  2026/7/1
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
  2026/5/1
• LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios
  2026/4/1
• Shape-Interpretable Visual Self-Modeling Enables Geometry-Aware Continuum Robot Control
  2026/3/1
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
  2025/12/1
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
  2025/12/1
• Embodied AI: From LLMs to World Models
  2025/9/1
• U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks
  2025/9/1
• EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
  2025/2/1
• Universal Online Temporal Calibration for Optimization-based Visual-Inertial Navigation Systems
  2025/1/1
• U2UData: A Large-scale Cooperative Perception Dataset for Swarm UAVs Autonomous Flight
  2024/8/1
• A Generic Stochastic Hybrid Car-following Model Based on Approximate Bayesian Computation
  2023/12/1
• 3D Pose Estimation of Tomato Peduncle Nodes using Deep Keypoint Detection and Point Cloud
  2023/11/1
• On-the-Fly SfM: What you capture is What you get
  2023/9/1
• Semantics-Aware Next-best-view Planning for Efficient Search and Detection of Task-relevant Plant Parts
  2023/6/1
• RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
  2022/10/1
• Instance-Aware Predictive Navigation in Multi-Agent Environments
  2021/1/1
• Deep Visual Odometry with Adaptive Memory
  2020/8/1
• Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
  2019/8/1
• Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
  2019/8/1
• Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
  2018/11/1
• Guided Feature Selection for Deep Visual Odometry
  2018/11/1
• PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
  2018/7/1
• Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
  2018/3/1
• An Efficient Volumetric Mesh Representation for Real-time Scene Reconstruction using Spatial Hashing
  2018/3/1