Guardado en:
Detalles Bibliográficos
Autores principales: Jing, Pengfei, Huang, Victor Shea-Jay, Lu, Hengtong, Dai, Jifeng, Xie, Yan, Zhu, Benjin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.12622
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911685412913152
author Jing, Pengfei
Huang, Victor Shea-Jay
Lu, Hengtong
Dai, Jifeng
Xie, Yan
Zhu, Benjin
author_facet Jing, Pengfei
Huang, Victor Shea-Jay
Lu, Hengtong
Dai, Jifeng
Xie, Yan
Zhu, Benjin
contents We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appropriate, and safety-compliant actions in arbitrary, long-tail traffic scenes through scene-conditioned reasoning rather than retrieval or interpolation of learned scene-action mappings. We show that previous paradigms cannot deliver action emergence: autoregressive trajectory decoders collapse the inherently multimodal future into a single averaged output, while diffusion and flow-matching generators express multimodality but are not steerable by reasoned intent. We propose Streaming Intent as a concrete way to approach action emergence: a mechanism that makes driving intent (i) semantically streamed through a continuous chain-of-thought that causally derives the intent from scene understanding, and (ii) temporally streamed across clips so that intent commitments remain coherent along the driving horizon. We realize Streaming Intent in a VLA model we call SI (Streaming Intent). SI autoregressively decodes a four-step chain-of-thought and emits an intent token; the decoded intent then drives classifier-free guidance (CFG) on a flow-matching action head, requiring only two denoising steps to generate the final trajectory. On the Waymo End-to-End benchmark, SI achieves competitive aggregate performance, with an RFS score of 7.96 on the validation set and 7.74 on the test set. Beyond aggregate metrics, the model demonstrates -- to our knowledge for the first time in a fully end-to-end VLA -- intent-faithful controllability: for a fixed scene, varying the intent class at inference yields qualitatively distinct yet consistently high-quality plans, arising purely from data-driven learning without any pre-built trajectory bank or hand-coded post-hoc selector.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12622
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Action Emergence from Streaming Intent
Jing, Pengfei
Huang, Victor Shea-Jay
Lu, Hengtong
Dai, Jifeng
Xie, Yan
Zhu, Benjin
Robotics
Computer Vision and Pattern Recognition
We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appropriate, and safety-compliant actions in arbitrary, long-tail traffic scenes through scene-conditioned reasoning rather than retrieval or interpolation of learned scene-action mappings. We show that previous paradigms cannot deliver action emergence: autoregressive trajectory decoders collapse the inherently multimodal future into a single averaged output, while diffusion and flow-matching generators express multimodality but are not steerable by reasoned intent. We propose Streaming Intent as a concrete way to approach action emergence: a mechanism that makes driving intent (i) semantically streamed through a continuous chain-of-thought that causally derives the intent from scene understanding, and (ii) temporally streamed across clips so that intent commitments remain coherent along the driving horizon. We realize Streaming Intent in a VLA model we call SI (Streaming Intent). SI autoregressively decodes a four-step chain-of-thought and emits an intent token; the decoded intent then drives classifier-free guidance (CFG) on a flow-matching action head, requiring only two denoising steps to generate the final trajectory. On the Waymo End-to-End benchmark, SI achieves competitive aggregate performance, with an RFS score of 7.96 on the validation set and 7.74 on the test set. Beyond aggregate metrics, the model demonstrates -- to our knowledge for the first time in a fully end-to-end VLA -- intent-faithful controllability: for a fixed scene, varying the intent class at inference yields qualitatively distinct yet consistently high-quality plans, arising purely from data-driven learning without any pre-built trajectory bank or hand-coded post-hoc selector.
title Action Emergence from Streaming Intent
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12622