Research KB

SRC-1812.03079 Source

以模仿学习训练驾驶策略(Bansal et al., RSS 2019):学最佳示范、合成最坏失败。

id SRC-1812.03079
type source
kind paper
title ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
authors Mayank Bansal, A. Krizhevsky, A. Ogale
venue RSS 2019
arxiv 1812.03079
doi 10.15607/RSS.2019.XV.031
tier 0
lifecycle EXTRACTED
epistemic n/a
ingested 2026-09-03
version arXiv:1812.03079
source-hash sha256:0000000000000000000000000000000000000000000000000000000000000000
source-role g2dp-citation-neighbor
g2dp-anchor SRC-2606.26017
g2dp-relation CITED_BY_G2DP | G2DP 引用本工作作模仿学习训练的参照(Bansal et al., RSS 2019):『学最佳示范、合成最坏失败』的数据配方。
citation-count-s2 886

以模仿学习训练驾驶策略(Bansal, Krizhevsky & Ogale, RSS 2019):只模仿表现最好的人类示范,并合成最差失败情形扩充训练数据。

与 G2DP 的关系(SRC-2606.26017:G2DP 引用本工作作模仿学习训练的参照(Bansal et al., RSS 2019):『学最佳示范、合成最坏失败』的数据配方。

引用(1)

  • SRC-2606.26017 G2DP:时空占据栅格+路线进度融合为可微 cost volume,去噪末段注入引导,nuPlan 纯模仿 SOTA;本引用簇中心。