Stefan Schaal

収録論文 70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

• 軌道バンドル法：逐次凸計画とサンプリングベース軌道最適化の統合
  軌道最適化2025/9/1

  微分不要のサンプリングにより凸近似を構築し、逐次凸計画とMPPIなどのサンプリングベース軌道最適化を統合するフレームワークを提案。

• RoboBallet: グラフニューラルネットワークと強化学習によるマルチロボット到達計画
  マルチロボット計画2025/9/1

  強化学習とグラフニューラルネットワークを用いて、障害物の多い共有空間で複数ロボットのタスク割り当て・スケジューリング・動作計画を同時に解くフレームワークを提案し、8台のロボットによる40の到達タスクでゼロショット汎化を実証した。

• 双腕マニピュレーションのための模倣学習アルゴリズム比較
  マニピュレーション2024/8/1

  高精度な双腕マニピュレーションタスクにおいて、代表的な模倣学習アルゴリズムを比較し、ハイパーパラメータ感度やデータ効率、性能などの特性を実験的に評価した。

• GenCHiP: 高精度・接触リッチなマニピュレーションタスクのためのロボットポリシーコード生成
  マニピュレーション2024/4/1

  LLMによるロボットポリシーコード生成を、接触力や剛性の制約を考慮した行動空間の再パラメータ化により高精度・接触リッチなタスクへ拡張し、FMBやNISTタスクボードで成功率を大幅に改善した。

• RT-Sketch: 手描きスケッチによる目標条件付き模倣学習
  模倣学習2024/3/1

  手描きスケッチを目標指定に用いる操作ポリシーを提案し、言語や画像条件よりも曖昧さや視覚的妨害に頑健であることを示した。

• SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
  2024/1/1
• Efficient Online Learning of Contact Force Models for Connector Insertion
  2023/12/1
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
  2023/10/1
• Multi-Stage Cable Routing through Hierarchical Imitation Learning
  2023/7/1
• Prim-LAfD: A Framework to Learn and Adapt Primitive-Based Skills from Demonstrations for Insertion Tasks
  2022/12/1
• Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
  2022/10/1
• A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies
  2022/8/1
• Detection and Physical Interaction with Deformable Linear Objects
  2022/5/1
• Symbolic State Estimation with Predicates for Contact-Rich Manipulation Tasks
  2022/3/1
• Efficient Spatial Representation and Routing of Deformable One-Dimensional Objects for Manipulation
  2022/2/1
• You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration
  2022/1/1
• Deformable One-Dimensional Object Detection for Routing and Manipulation
  2022/1/1
• Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
  2021/12/1
• Offline Meta-Reinforcement Learning for Industrial Insertion
  2021/10/1
• From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
  2021/10/1
• Multi-Task Learning with Sequence-Conditioned Transporter Networks
  2021/9/1
• CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation
  2021/9/1
• A Robustness Analysis of Inverse Optimal Control of Bipedal Walking
  2021/4/1
• Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study
  2021/3/1
• Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks
  2021/3/1
• Learning Dense Rewards for Contact-Rich Manipulation Tasks
  2020/11/1
• Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation
  2020/8/1
• Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed
  2020/7/1
• An Interior Point Method Solving Motion Planning Problems with Narrow Passages
  2020/7/1
• Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing
  2018/10/1
• Scaling simulation-to-real transfer by learning composable robot skills
  2018/9/1
• Learning Task-Specific Dynamics to Improve Whole-Body Control
  2018/3/1
• An MPC Walking Framework With External Contact Forces
  2017/12/1
• A New Data Source for Inverse Dynamics Learning
  2017/10/1
• Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networks
  2017/10/1
• Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data
  2017/10/1
• On Time Optimization of Centroidal Momentum Dynamics
  2017/9/1
• Unsupervised Contact Learning for Humanoid Estimation and Control
  2017/9/1
• Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
  2017/5/1
• Time-Contrastive Networks: Self-Supervised Learning from Video
  2017/4/1
• Real-time Perception meets Reactive Motion Generation
  2017/3/1
• Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
  2017/3/1
• Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
  2017/3/1
• Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
  2017/3/1
• Balancing and Walking Using Full Dynamics LQR Control With Contact Constraints
  2017/1/1
• A Probabilistic Representation for Dynamic Movement Primitives
  2016/12/1
• Probabilistic Articulated Real-Time Tracking for Robot Manipulation
  2016/10/1
• Path Integral Guided Policy Search
  2016/10/1
• Learning Feedback Terms for Reactive Planning and Control
  2016/10/1
• Stepping Stabilization Using a Combination of DCM Tracking and Step Adjustment
  2016/9/1
• DOOMED: Direct Online Optimization of Modeling Errors in Dynamics
  2016/8/1
• A Convex Model of Momentum Dynamics for Multi-Contact Motion Generation
  2016/7/1
• Structured contact force optimization for kino-dynamic motion generation
  2016/5/1
• On the Fundamental Importance of Gauss-Newton in Motion Optimization
  2016/5/1
• Automatic LQR Tuning Based on Gaussian Process Global Optimization
  2016/5/1
• On the Effects of Measurement Uncertainty in Optimal Control of Contact Interactions
  2016/5/1
• Interactive Perception: Leveraging Action in Perception and Perception in Action
  2016/4/1
• Depth-Based Object Tracking Using a Robust Gaussian Filter
  2016/2/1
• Inertial Sensor-Based Humanoid Joint State Estimation
  2016/2/1
• Trajectory generation for multi-contact momentum-control
  2015/7/1
• Humanoid Momentum Estimation Using Sensed Contact Wrenches
  2015/7/1
• The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems
  2015/5/1
• Probabilistic Object Tracking using a Range Camera
  2015/5/1
• A New Perspective and Extension of the Gaussian Filter
  2015/4/1
• Probabilistic Depth Image Registration incorporating Nonvisual Information
  2015/4/1
• Policy Learning with Hypothesis based Local Action Selection
  2015/3/1
• Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid
  2014/10/1
• State Estimation for a Humanoid Robot
  2014/2/1
• Local Gaussian Regression
  2014/2/1
• Balancing experiments on a torque-controlled humanoid with hierarchical inverse dynamics
  2013/5/1