Zuxin Liu

収録論文 19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

• 環境との対話によるLLMエージェントのテスト時適応
  VLA2025/11/6

  LLMエージェントが未知の環境に適応するため、オンライン構文整合と展開時の動力学接地という2つの手法を提案し、関数呼び出しやWebナビゲーションで有効性を示した。

• EXTRACT: オフラインデータから転移可能なロボットスキルを抽出する効率的な方策学習
  スキルベース強化学習2024/6/1

  事前学習済み視覚言語モデルを用いてオフラインデータから意味のあるスキルを連続パラメータ付きで抽出し、新しいロボット操作タスクを効率的に学習する手法を提案。

• Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving
  2023/11/1
• Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization
  2023/10/1
• TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
  2023/10/1
• Influence of Camera-LiDAR Configuration on 3D Object Detection for Autonomous Driving
  2023/10/1
• Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
  2023/9/1
• Datasets and Benchmarks for Offline Safe Reinforcement Learning
  2023/6/1
• Constrained Decision Transformer for Offline Safe Reinforcement Learning
  2023/2/1
• Robustness Certification of Visual Perception Models via Camera Motion Smoothing
  2022/10/1
• SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles
  2022/6/1
• On the Robustness of Safe Reinforcement Learning under Observational Perturbations
  2022/5/1
• Constrained Variational Policy Optimization for Safe Reinforcement Learning
  2022/1/1
• Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
  2021/5/1
• Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method
  2020/10/1
• MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments
  2020/7/1
• Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
  2020/6/1
• DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
  2018/9/1
• Where Should We Place LiDARs on the Autonomous Vehicle? - An Optimal Design Approach
  2018/9/1