Kyle Stachowicz

UC Berkeley

収録論文 21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

• 行動チャンキングがロボット制御における行動クローニングの性能を向上させる理由
  ロボット制御2026/8/3

  行動チャンキングの性能向上の理由を実験的に検証し、既存の仮説が不十分であることを示し、遅延ポリシーや暗黙のアンサンブル効果が重要であることを明らかにした。

• Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?
  2026/8/1
• ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
  2026/4/1
• MEM: Multi-Scale Embodied Memory for Vision Language Action Models
  2026/3/1
• SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios
  2026/2/1
• $π^{*}_{0.6}$: a VLA That Learns From Experience
  2025/11/18
• $\pi^{*}_{0.6}$: a VLA That Learns From Experience
  2025/11/1
• Learning to Drive Anywhere with Model-Based Reannotation
  2025/5/1
• $π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
  2025/4/22
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
  2025/4/1
• FAST: Efficient Action Tokenization for Vision-Language-Action Models
  2025/1/16
• FAST: Efficient Action Tokenization for Vision-Language-Action Models
  2025/1/1
• Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
  2025/1/1
• Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
  2024/10/1
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes
  2024/5/1
• SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation
  2024/3/1
• ViNT: A Foundation Model for Visual Navigation
  2023/6/1
• FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
  2023/4/1
• Multimodal Maximum Entropy Dynamic Games
  2022/1/1
• Optimal-Horizon Model-Predictive Control with Differential Dynamic Programming
  2021/11/1
• Safety Embedded Differential Dynamic Programming Using Discrete Barrier States
  2021/5/1