Junjie Wang

The Chinese University of Hong Kong, Shenzhen

収録論文 13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

• 意図と軌道の分離：世界行動モデルのための表現演繹フレームワーク
  VLA2026/8/7

  世界行動モデルにおける高レベルの物理状態遷移と低レベルの行動軌道生成の表現が絡み合う問題を解決するため、思考連鎖ガイダンスを統合した表現演繹フレームワークPILOTを提案し、複雑なロボット操作タスクでの成功率と一般化を向上させた。

• Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models
  2026/8/1
• Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA
  2026/7/1
• Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learning
  2026/6/1
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
  2026/3/1
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms
  2026/3/1
• A Precise Real-Time Force-Aware Grasping System for Robust Aerial Manipulation
  2026/2/1
• Shape-Adaptive Planning and Control for a Deformable Quadrotor
  2025/5/1
• Safe and Agile Transportation of Cable-Suspended Payload via Multiple Aerial Robots
  2025/1/1
• Decictor: Towards Evaluating the Robustness of Decision-Making in Autonomous Driving Systems
  2024/2/1
• Multi-agent Coordination Under Temporal Logic Tasks and Team-Wise Intermittent Communication
  2023/8/1
• Hierarchical Motion Planning under Probabilistic Temporal Tasks and Safe-Return Constraints
  2023/2/1
• Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints
  2019/4/1