Sushant Veer

NVIDIA

収録論文 33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

• ペアシステムを用いた障害発見のためのカバレッジ考慮型能動評価
  能動学習/障害発見2026/8/13

  限られたテスト予算で実世界の障害を効率的に発見するため、プロキシシステムの情報を活用しつつ、実システムの評価結果と組み合わせて障害が起きそうなシナリオを適応的に選択する手法を提案した。

• X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
  2026/6/1
• StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
  2026/6/1
• Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World
  2026/2/1
• The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving
  2025/9/1
• Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set Estimators
  2025/7/1
• Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
  2025/6/1
• RealDrive: Retrieval-Augmented Driving with Diffusion Models
  2025/5/1
• Online Aggregation of Trajectory Predictors
  2025/2/1
• Surprise Potential as a Measure of Interactivity in Driving Scenarios
  2025/2/1
• LoRD: Adapting Differentiable Driving Policies to Distribution Shifts
  2024/10/1
• System-Level Safety Monitoring and Recovery for Perception Failures in Autonomous Vehicles
  2024/9/1
• RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts
  2024/5/1
• HT-LIP Model based Robust Control of Quadrupedal Robot Locomotion under Unknown Vertical Ground Motion
  2024/3/1
• Driving Everywhere with Large Language Model Policy Adaptation
  2024/2/1
• Interactive Joint Planning for Autonomous Vehicles
  2023/10/1
• Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors
  2023/7/1
• Task-Aware Risk Estimation of Perception Failures for Autonomous Vehicles
  2023/5/1
• Reactive Gait Composition with Stability: Dynamic Walking amidst Static and Moving Obstacles
  2023/3/1
• Real-Time Walking Pattern Generation of Quadrupedal Dynamic-Surface Locomotion based on a Linear Time-Varying Pendulum Model
  2023/1/1
• Receding Horizon Planning with Rule Hierarchies for Autonomous Vehicles
  2022/12/1
• Guided Conditional Diffusion for Controllable Traffic Simulation
  2022/10/1
• Learning Autonomous Vehicle Safety Concepts from Demonstrations
  2022/10/1
• Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles
  2022/7/1
• DRS-LIP: Linear Inverted Pendulum Model for Legged Locomotion on Dynamic Rigid Surfaces
  2022/2/1
• Learning Provably Robust Motion Planners Using Funnel Libraries
  2021/11/1
• Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data
  2021/11/1
• Interactive Dynamic Walking: Learning Gait Switching Policies with Generalization Guarantees
  2021/9/1
• Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning
  2021/6/1
• Generalization Guarantees for Imitation Learning
  2020/8/1
• CoNES: Convex Natural Evolutionary Strategies
  2020/7/1
• Probably Approximately Correct Vision-Based Planning using Motion Primitives
  2020/2/1
• Safe Adaptive Switching among Dynamical Movement Primitives: Application to 3D Limit-Cycle Walkers
  2018/10/1