paper-with-me

홈 › Papers

Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories

2024-04-20 · Hamidreza Mirkhani, Behzad Khamidehi, Kasra Rezaee

Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. However, imitating trajectories that inadequately represent the original expert data can result in undesirable behaviors, particularly in safety-critical scenarios. We propose a trajectory augmentation method designed to maintain similarity with expert trajectory data. To accomplish this, we first cluster trajectories to identify minority yet safety-critical groups. Then, we combine the trajectories within the same cluster through geometrical transformation to create new trajectories. These trajectories are then added to the training dataset, provided that they meet our specified safety-related criteria. Our experiments exhibit that training an imitation learning model using these augmented trajectories can significantly improve closed-loop performance.

📄 PDF Abstract BibTeX arXiv:2404.13347

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests

2025-02-28 · Yukuan Yang, Xucheng Lu, Zhili Zhang, Zepeng Wu 외

Generating adversarial safety-critical scenarios is a pivotal method for testing autonomous driving systems, as it identifies potential weaknesses and enhances system robustness and reliability. However, existing approac…

Autonomous Driving

Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios

2025-03-31 · Jingzheng Li, Xianglong Liu, Shikui Wei, Zhijun Chen 외

Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception task and the development of end-to-end autonomous driving systems. However, the safety and …

Adversarial AttackAutonomous DrivingBenchmarking

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

2025-02-04 · Yuan Gao, Mattia Piccinini, Korbinian Moller, Amr Alanwar 외

Ensuring the safety of autonomous vehicles requires virtual scenario-based testing, which depends on the robust evaluation and generation of safety-critical scenarios. So far, researchers have used scenario-based testing…

Autonomous DrivingAutonomous VehiclesMotion PlanningPrompt Engineering

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

2024-04-11 · William Ljungbergh, Adam Tonderski, Joakim Johnander, Holger Caesar 외

We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios. The simula…

Autonomous DrivingNeRF

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models

2025-02-21 · Zihao Sheng, Zilin Huang, Yansong Qu, Yue Leng 외

Ensuring safety in autonomous driving systems remains a critical challenge, particularly in handling rare but potentially catastrophic safety-critical scenarios. While existing research has explored generating safety-cri…

Autonomous Driving