Papers with Code · CC BY-SA 4.0

Autonomous Vehicles

769 평가 기록 63 datasets

Autonomous vehicles is the task of making a vehicle that can guide itself without human conduction.

Many of the state-of-the-art results can be found at more general task pages such as 3D Object Detection and Semantic Segmentation.

<span style="color:grey; opacity: 0.6">( Image credit: GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision )</span>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode

Argoverse CVPR 2020

SEPT

MR (K=6): 0.1032minADE (K=1): 1.4412minFDE (K=1): 3.1777MR (K=1): 0.5154

- -

CULane

DLNet

F1 score: 81.23

논문 코드

TuSimple

SCNN_UNet_Attention_PL*

Accuracy: 98.38

논문 -

Bench2Drive

HiP-AD

Driving Score: 86.77

논문 코드

Caltech

LSFM

Reasonable Miss Rate: 0.87Heavy MR^-2: 19.5

논문 -

OpenScene

DriveSuprim

PDMS: 93.5

- -

CityPersons

DIW Loss

Reasonable MR^-2: 6.23Heavy MR^-2: 28.37Small MR^-2: 7.36

논문 -

OpenLane

GLane3D(Swin-B)

F1 (all): 66.0Up & Down: 61.7Curve: 72.7Extreme Weather: 63.8

논문 -

CurveLanes

CondLSTR (ResNet-101)

F1 score: 88.47

논문 코드

CARLA Leaderboard

ReasonNet

Driving Score: 79.95Route Completion: 89.89Infraction penalty: 0.89

논문 -

LLVIP

MMPedestron

AP: 0.726

논문 코드

PA-100K

PATH (Partial FT)

Accuracy: 90.8

논문 코드

데이터셋

63개

Argoverse CVPR 2020 CULane TuSimple Bench2Drive Caltech OpenScene CityPersons OpenLane CurveLanes CARLA Leaderboard LLVIP PA-100K

논문

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

2104.09224 2021-04-19 이 페이지의 평가 4건

RC: 86.91

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

2007.13124 2020-07-26 이 페이지의 평가 2건

A3DP: 20.21

BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling

2023-01-01 이 페이지의 평가 1건

A3DP: 22.85

Hidden Biases of End-to-End Driving Models

2306.07957 2023-06-13 이 페이지의 평가 1건

Driving Score: 66.32Route Completion: 78.57Infraction penalty: 0.84

Learning from All Vehicles

2203.11934 2022-03-22 이 페이지의 평가 1건

Driving Score: 61.846Route Completion: 94.459Infraction penalty: 0.640

ReasonNet: End-to-End Driving with Temporal and Global Reasoning

2305.10507 2023-05-17 이 페이지의 평가 1건

Driving Score: 79.95Route Completion: 89.89Infraction penalty: 0.89

Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

2207.14024 2022-07-28 이 페이지의 평가 1건

Driving Score: 76.18Route Completion: 88.23Infraction penalty: 0.84

Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline

2206.08129 2022-06-16 이 페이지의 평가 1건

Driving Score: 75.14Route Completion: 85.63Infraction penalty: 0.87

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/autonomousvision/transfuser 1 논문

github.com/Kin-Zhang/mmfn 1 논문

github.com/lkeab/gsnet 1 논문

github.com/autonomousvision/carla_garage 1 논문

github.com/dotchen/LAV 1 논문

github.com/gywns6287/baam 1 논문

github.com/opendilab/InterFuser 1 논문

github.com/OpenPerceptionX/TCP 1 논문

하위 태스크

AD Autonomous Driving 12 데이터셋 · 407 rows LD Lane Detection 17 데이터셋 · 201 rows PD Pedestrian Detection 10 데이터셋 · 94 rows PA Pedestrian Attribute Recognition 8 데이터셋 · 30 rows TS Traffic Sign Recognition 10 데이터셋 · 26 rows CL CARLA Leaderboard 2.0 1 데이터셋 · 4 rows 3C 3D Car Instance Understanding 1 데이터셋 · 2 rows SL Simultaneous Localization and Mapping 2 데이터셋 · 2 rows AN Autonomous Navigation 1 데이터셋 · 1 rows DA Driver Attention Monitoring 0 데이터셋 · 0 rows FV Fast Vehicle Detection 0 데이터셋 · 0 rows LC Loop Closure Detection 0 데이터셋 · 0 rows