Apoorva Sharma

NVIDIA

収録論文 18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
• Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
  2025/12/1
• 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
• Online Aggregation of Trajectory Predictors
  2025/2/1
• 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
• Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors
  2023/7/1
• A System-Level View on Out-of-Distribution Data in Robotics
  2022/12/1
• On the Problem of Reformulating Systems with Uncertain Dynamics as a Stochastic Differential Equation
  2021/11/1
• Particle MPC for Uncertain and Learning-Based Control
  2021/4/1
• Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework
  2020/8/1
• Network Offloading Policies for Cloud Robotics: a Learning-based Approach
  2019/2/1
• Meta-Learning Priors for Efficient Online Bayesian Regression
  2018/7/1
• BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning
  2018/6/1