Jiahang Cao

The Hong Kong University of Science and Technology

収録論文 35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

• Tac4Loco: ヒューマノイド歩行のための時空間足底圧表現の学習
  歩行2026/8/16

  ヒューマノイドロボットの歩行制御において、足底圧力の空間的トポロジーを保持した表現を学習し、シミュレーションと実機のセンサ信号を共通の観測空間にマッピングすることで、不整地での適応的な歩行を実現するフレームワークを提案した。

• Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
  2026/7/1
• FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation
  2026/6/1
• GeoSem-WAM: Geometry- and Semantic-Aware World Action Models
  2026/6/1
• GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training
  2026/6/1
• AttenA+: Rectifying Action Inequality in Robotic Foundation Models
  2026/5/1
• Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
  2026/5/1
• MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
  2026/5/1
• Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control
  2026/3/1
• MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction
  2026/2/1
• Real-to-Sim for Highly Cluttered Environments via Physics-Consistent Inter-Object Reasoning
  2026/2/1
• Fast and Safe Trajectory Optimization for Mobile Manipulators With Neural Configuration Space Distance Field
  2026/1/1
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
  2025/10/1
• DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
  2025/10/1
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
  2025/10/1
• ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations
  2025/9/1
• Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
  2025/7/1
• LOVON: Legged Open-Vocabulary Object Navigator
  2025/7/1
• Occupancy World Model for Robots
  2025/5/1
• HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
  2025/3/1
• Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion
  2025/3/1
• Trinity: A Modular Humanoid Robot AI System
  2025/3/1
• ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
  2025/3/1
• Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
  2025/3/1
• EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
  2025/3/1
• LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
  2025/3/1
• PALo: Learning Posture-Aware Locomotion for Quadruped Robots
  2025/3/1
• RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation
  2025/3/1
• RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations
  2025/2/1
• E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework
  2024/10/1
• LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots
  2024/9/1
• World Model-based Perception for Visual Legged Locomotion
  2024/9/1
• Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models
  2024/9/1
• Fully Spiking Neural Network for Legged Robots
  2023/10/1
• Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera
  2023/9/1