Yang Liu

Harbin Institute of Technology

収録論文 85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

• EATR-Stereo: 身体性を考慮したステレオ証拠のルーティングによるヒューマノイド視覚言語行動制御
  VLA/ヒューマノイド2026/8/18

  頭部搭載ステレオカメラを持つヒューマノイドのVLA制御において、主視点のトークンを保持しつつ補助視点の情報を身体状態に応じて選択的に統合するフレームワークを提案し、実機で高い成功率を達成した。

• GraphThink: グラフ強化LLM思考による長期的身体性タスク計画
  タスク計画2026/8/8

  LLMベースの身体性エージェントの計画における幻覚や長期タスクへの汎化不足を解決するため、タスクグラフとシーングラフを統合したフレームワークを提案。ALFREDベンチマークで最先端性能を達成した。

• GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
  2026/8/1
• Bridge-WA: Predicting Where and How the World Changes for Robotic Action
  2026/7/1
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
  2026/7/1
• HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation
  2026/7/1
• Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio
  2026/7/1
• Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Fields in Passive Object-State World Models
  2026/6/1
• RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
  2026/6/1
• VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis
  2026/6/1
• ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation
  2026/6/1
• In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
  2026/6/1
• Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation
  2026/6/1
• STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
  2026/5/1
• RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
  2026/5/1
• Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
  2026/4/1
• BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
  2026/4/1
• AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
  2026/3/19
• ACCURATE: Arbitrary-shaped Continuum Reconstruction Under Robust Adaptive Two-view Estimation
  2026/3/1
• ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation
  2026/3/1
• TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
  2026/3/1
• MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
  2026/3/1
• OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras
  2026/3/1
• Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
  2026/2/1
• DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
  2026/2/1
• Eva-Tracker: ESDF-update-free, Visibility-aware Planning with Target Reacquisition for Robust Aerial Tracking
  2026/2/1
• FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
  2026/2/1
• PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
  2026/1/1
• Preparation and Motion Study of Magnetically Driven Micro Soft Robot Mimicking the Cownose Ray
  2026/1/1
• Detecting Non-Optimal Decisions of Embodied Agents via Diversity-Guided Metamorphic Testing
  2025/12/1
• HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
  2025/12/1
• An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
  2025/12/1
• Phase-Based Multi-Gait Learning for a Salamander-Like Robot
  2025/11/1
• HDCNet: A Hybrid Depth Completion Network for Grasping Transparent and Reflective Objects
  2025/11/1
• Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents
  2025/11/1
• RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model
  2025/10/1
• Learning to Throw-Flip
  2025/10/1
• Bridging Perception and Planning: Towards End-to-End Planning for Signal Temporal Logic Tasks
  2025/9/1
• Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generation
  2025/9/1
• Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
  2025/8/1
• Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
  2025/8/1
• AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning
  2025/8/1
• ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation
  2025/7/1
• Vibration-aware Lidar-Inertial Odometry based on Point-wise Post-Undistortion Uncertainty
  2025/7/1
• GFM-Planner: Perception-Aware Trajectory Planning with Geometric Feature Metric
  2025/7/1
• AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
  2025/7/1
• Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration
  2025/6/1
• DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
  2025/6/1
• Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage
  2025/6/1
• OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
  2025/5/1
• Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms
  2025/3/1
• Learning Perceptive Humanoid Locomotion over Challenging Terrain
  2025/3/1
• Learning Humanoid Locomotion with World Model Reconstruction
  2025/2/1
• Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning
  2024/12/1
• InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction
  2024/12/1
• Depth-PC: A Visual Servo Framework Integrated with Cross-Modality Fusion for Sim2Real Transfer
  2024/11/1
• Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
  2024/7/1
• SuperVINS: A Real-Time Visual-Inertial SLAM Framework for Challenging Imaging Conditions
  2024/7/1
• Human-centered In-building Embodied Delivery Benchmark
  2024/6/1
• MAS-SAM: Segment Any Marine Animal with Aggregated Features
  2024/4/1
• NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting
  2024/3/1
• Bringing Robots Home: The Rise of AI Robots in Consumer Electronics
  2024/3/1
• R$\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training
  2024/1/1
• GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow
  2024/1/1
• Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
  2023/11/1
• Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
  2023/8/1
• NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain
  2023/8/1
• A reproducible approach to merging behavior analysis based on High Definition Map
  2023/3/1
• Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation
  2023/3/1
• FLYOVER: A Model-Driven Method to Generate Diverse Highway Interchanges for Autonomous Vehicle Testing
  2023/1/1
• The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning
  2022/10/1
• OA-Bug: An Olfactory-Auditory Augmented Bug Algorithm for Swarm Robots in a Denied Environment
  2022/9/1
• Research on Stable Obstacle Avoidance Control Strategy for Tracked Intelligent Transportation Vehicles in Non-structural Environment Based on Deep Learning
  2022/8/1
• A Solution to Adaptive Mobile Manipulator Throwing
  2022/7/1
• Design and experimental investigation of a vibro-impact self-propelled capsule robot with orientation control
  2022/2/1
• A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation
  2021/12/1
• The Unified Mathematical Framework for IMU Preintegration in Inertial-Aided Navigation System
  2021/11/1
• VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator
  2021/5/1
• The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
  2020/4/1
• Predicting Unobserved Space For Planning via Depth Map Augmentation
  2019/11/1
• Federated Transfer Reinforcement Learning for Autonomous Driving
  2019/10/1
• DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features
  2019/1/1
• Characterization of a RS-LiDAR for 3D Perception
  2017/9/1
• A Control Performance Index for Multicopters Under Off-nominal Conditions
  2017/5/1
• Motion Imitation Based on Sparsely Sampled Correspondence
  2016/7/1