4 papers · 1 filter
Generative Scenario Rollouts for End-to-End Autonomous Driving
Rajeev Yasarla, Deepti Hegde, Shizhong Han +10
Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation lear…
Distilling Multi-modal Large Language Models for Autonomous Driving
Deepti Hegde, Rajeev Yasarla, Hong Cai +7
Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as…
Multimodal 3D Object Detection on Unseen Domains
Deepti Hegde, Suhas Lohit, Kuan-Chuan Peng +2
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and eva…
Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection
Deepti Hegde, Suhas Lohit, Kuan-Chuan Peng +2
Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmen…