자율주행 소프트웨어 테스팅을 위한 디지털 형제 활용: 단일 시뮬레이터 접근의 한계 극복
시뮬레이션 기반 테스팅은 자율주행 소프트웨어의 신뢰성을 보장하는 중요한 단계이지만, 일반 목적 시뮬레이터를 사용할 경우 실제 자율주행 차량 동작과의 괴리가 발생할 수 있다. 이 연구는 다중 시뮬레이터 접근법인 '디지털 형제' 방식을 제안하여 이러한 한계를 극복하고자 한다.
Ensuring Safe Autonomy: Navigating the Challenges of Autonomous Vehicle Development
Autonomous vehicles require robust safety assurance to overcome the challenges of complex situations and unreliable perception, which traditional approaches often fail to address. Integrating dynamic risk management into behavior-based systems can provide a promising solution.
InsMapper: Vectorized HD Mapping with Inner-Instance Information
InsMapper effectively utilizes inner-instance information to improve vectorized HD map detection.
Nigel - Mechatronic Design and Robust Sim2Real Control of an Over-Actuated Autonomous Vehicle
Developing a robust sim2real control framework for autonomous vehicles with unconventional architectures.
Addressing Data Annotation Challenges in Multiple Sensors: A Solution for Scania Collected Datasets
Addressing challenges in annotating data from multiple sensors in autonomous vehicles, focusing on motion compensation and object tracking.
LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models
Utilizing Large Language Models for lane change prediction enhances accuracy and interpretability.
Cooperative Motion Prediction with Multi-Agent Communication
Advancing cooperative capabilities in CAVs through integrated perception and prediction.
Optimizing LiDAR Placements for Robust Driving Perception in Adverse Conditions
Place3D framework optimizes LiDAR placements for robust driving perception under adverse conditions.
CurbNet: Advanced Curb Detection Framework Based on LiDAR Point Cloud Segmentation
Advanced framework for curb detection using LiDAR point cloud segmentation.
Analyzing Online Map Uncertainty in Trajectory Prediction
Incorporating uncertainty in online map estimation improves trajectory prediction performance significantly.
© 2024 by Linnk AI