Tong Li

Xidian University

収録論文 11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

• 賢く記憶する：ロボット記憶のための視覚履歴圧縮と双曲経験空間
  VLA/記憶2026/8/15

  長期的なロボットポリシーのために、視覚履歴を圧縮し、経験を双曲空間で階層的に保存・活用するプラグインモジュールを提案。pi0に適用し、LIBERO-Plusで成功率を向上させた。

• Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization
  2026/4/1
• VitaTouch: Property-Aware Vision-Tactile-Language Model for Robotic Quality Inspection in Manufacturing
  2026/4/1
• VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing
  2026/2/1
• CSMapping: Scalable Crowdsourced Semantic Mapping and Topology Inference for Autonomous Driving
  2025/12/1
• Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
  2025/9/1
• Integrated Decision Making and Trajectory Planning for Autonomous Driving Under Multimodal Uncertainties: A Bayesian Game Approach
  2024/9/1
• Multi-modal Integrated Prediction and Decision-making with Adaptive Interaction Modality Explorations
  2024/8/1
• Theoretical Modeling and Bio-inspired Trajectory Optimization of A Multiple-locomotion Origami Robot
  2024/3/1
• MARC: Multipolicy and Risk-aware Contingency Planning for Autonomous Driving
  2023/8/1
• An Efficient Spatial-Temporal Trajectory Planner for Autonomous Vehicles in Unstructured Environments
  2022/8/1