Tianyi Zhang
Shanghai Jiao Tong University
収録論文 49本 ・ フィジカルAI/ロボット学習
SLAM強化学習/ヒューマノイド
※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
- Scalix: 不確実性を考慮したスケール一貫性のある単眼SLAMSLAM2026/8/18
単眼SLAMのスケール曖昧性を解決するため、学習された深度情報を確率的因子グラフに統合し、ピクセル単位とフレーム単位の不確実性を考慮してメートルスケールの状態推定を実現するフレームワークを提案した。
- RoboStriker: 自律型ヒューマノイドボクシングのための潜在空間戦略ゲーム強化学習/ヒューマノイド2026/8/17
ヒューマノイドボクシングを2プレイヤーの潜在空間ゼロサムマルコフゲームとして定式化し、戦略的探索と物理的実現性の矛盾を解決する階層的フレームワークを提案した。
- OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation2026/8/1
- NeoMap: Training-free Novel-View Synthesis from Single Images and Videos2026/7/1
- RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model2026/7/1
- HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation2026/7/1
- ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI2026/7/1
- Natural Gradient Bayesian Filtering: Geometry-Aware Filter for Dynamical Systems2026/5/1
- Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT2026/5/1
- Natural Gradient Gaussian Approximation Filter on Lie Groups for Robot State Estimation2026/4/1
- Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving2026/3/1
- RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing2026/1/1
- Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation2025/9/1
- A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning2025/9/1
- Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy2025/8/1
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces2025/6/1
- Bi-Manual Joint Camera Calibration and Scene Representation2025/5/1
- Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios2025/5/1
- From Single Images to Motion Policies via Video-Generation Environment Representations2025/5/1
- GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction2025/4/1
- NANO-SLAM : Natural Gradient Gaussian Approximation for Vehicle SLAM2025/4/1
- Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models2025/3/1
- Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity2025/3/1
- Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy2025/3/1
- SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis2025/3/1
- Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video2025/1/1
- Robust State Estimation for Legged Robots with Dual Beta Kalman Filter2024/11/1
- MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking2024/11/1
- PhotoReg: Photometrically Registering 3D Gaussian Splatting Models2024/10/1
- Diffusion Transformer Policy2024/10/1
- SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting2024/10/1
- ModCube: Modular, Self-Assembling Cubic Underwater Robot2024/9/1
- Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation2024/9/1
- 3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects2024/7/1
- From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking2024/6/1
- Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception2024/5/1
- Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models2024/4/1
- DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark2024/3/1
- Teaching Robots Where To Go And How To Act With Human Sketches via Spatial Diagrammatic Instructions2024/3/1
- Customizable Perturbation Synthesis for Robust SLAM Benchmarking2024/2/1
- Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis2023/12/1
- Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching2023/9/1
- Learning Orbitally Stable Systems for Diagrammatically Teaching2023/9/1
- Reasoning about the Unseen for Efficient Outdoor Object Navigation2023/9/1
- Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery2023/4/1
- Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization2021/9/1
- Generative Adversarial Network based Heuristics for Sampling-based Path Planning2020/12/1
- Design Paradigms Based on Spring Agonists for Underactuated Robot Hands: Concepts and Application2020/11/1
- Exploring home robot capabilities by medium fidelity prototyping2017/10/1