Argoverse: 3D Tracking and Forecasting with Rich Maps
arXiv:1911.02620
Abstract
We present Argoverse -- two datasets designed to support autonomous vehicle machine learning tasks such as 3D tracking and motion forecasting. Argoverse was collected by a fleet of autonomous vehicles in Pittsburgh and Miami. The Argoverse 3D Tracking dataset includes 360 degree images from 7 cameras with overlapping fields of view, 3D point clouds from long range LiDAR, 6-DOF pose, and 3D track annotations. Notably, it is the only modern AV dataset that provides forward-facing stereo imagery. The Argoverse Motion Forecasting dataset includes more than 300,000 5-second tracked scenarios with a particular vehicle identified for trajectory forecasting. Argoverse is the first autonomous vehicle dataset to include "HD maps" with 290 km of mapped lanes with geometric and semantic metadata. All data is released under a Creative Commons license at www.argoverse.org. In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting. Our tracking and forecasting experiments represent only an initial exploration of the use of rich maps in robotic perception. We hope that Argoverse will enable the research community to explore these problems in greater depth.
CVPR 2019
References in corpus (11)
- Sequence to Sequence Learning with Neural Networks
- MOT16: A Benchmark for Multi-Object Tracking
- Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
- CARLA: An Open Urban Driving Simulator
- IntentNet: Learning to Predict Intention from Raw Sensor Data
- HDNET: Exploiting HD Maps for 3D Object Detection
- DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
- FlowNet3D: Learning Scene Flow in 3D Point Clouds
- A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment
- End-to-End Deep Structured Models for Drawing Crosswalks
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Cited by in corpus (81)
- Monocular Depth Estimation Based On Deep Learning: An Overview
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset
- Stepwise Goal-Driven Networks for Trajectory Prediction
- TNT: Target-driveN Trajectory Prediction
- One Thousand and One Hours: Self-driving Motion Prediction Dataset
- One Million Scenes for Autonomous Driving: ONCE Dataset
- Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
- PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
- Learning to Predict Vehicle Trajectories with Model-based Planning
- THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling
- Joint Monocular 3D Vehicle Detection and Tracking
- Dynamic Occupancy Grid Mapping with Recurrent Neural Networks
- Probabilistic 3D Multi-Object Tracking for Autonomous Driving
- Wasserstein Distances for Stereo Disparity Estimation
- VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
- Learning Lane Graph Representations for Motion Forecasting
- From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
- Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
- The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
- Overview of Tools Supporting Planning for Automated Driving
- A Survey on Trajectory Data Management, Analytics, and Learning
- Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
- What-If Motion Prediction for Autonomous Driving
- Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
- Multimodal Motion Prediction with Stacked Transformers
- DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning
- Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving
- DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
- PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving
- Driving Style Recognition Using Interval Type-2 Fuzzy Inference System and Multiple Experts Decision Making
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
- SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
- CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps
- Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene
- Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction
- The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
- TPNet: Trajectory Proposal Network for Motion Prediction
- A Fleet Learning Architecture for Enhanced Behavior Predictions during Challenging External Conditions
- Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
- MODISSA: a multipurpose platform for the prototypical realization of vehicle-related applications using optical sensors
- UrbanLoco: A Full Sensor Suite Dataset for Mapping and Localization in Urban Scenes
- Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
- Scene Transformer: A unified architecture for predicting multiple agent trajectories
- LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents
- End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
- STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
- 3D for Free: Crossmodal Transfer Learning using HD Maps
- TPCN: Temporal Point Cloud Networks for Motion Forecasting
- CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
- Reimagining an autonomous vehicle
- SiamMOT: Siamese Multi-Object Tracking
- Trajectory Prediction using Equivariant Continuous Convolution
- DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling
- Joint Pose and Shape Estimation of Vehicles from LiDAR Data
- Lane Attention: Predicting Vehicles' Moving Trajectories by Learning Their Attention over Lanes
- Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study
- MoNet: Motion-based Point Cloud Prediction Network
- Crowd Density Forecasting by Modeling Patch-based Dynamics
- baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents
- Vehicle Telematics Via Exteroceptive Sensors: A Survey
- Universal Embeddings for Spatio-Temporal Tagging of Self-Driving Logs
- CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
- EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
- Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures
- Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
- AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points
- PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Information
- Radar-Camera Pixel Depth Association for Depth Completion
- Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data
- Learning Calibratable Policies using Programmatic Style-Consistency
- Iterative Imitation Policy Improvement for Interactive Autonomous Driving
- UrbanNet: Leveraging Urban Maps for Long Range 3D Object Detection
- Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
- Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes
- 3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset
- On complementing end-to-end human behavior predictors with planning
- Multi-Object Tracking using Poisson Multi-Bernoulli Mixture Filtering for Autonomous Vehicles
- Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
- CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles
- Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction
- PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction