CARLA: An Open Urban Driving Simulator
arXiv:1711.03938
Abstract
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end-to-end model trained via reinforcement learning. The approaches are evaluated in controlled scenarios of increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform's utility for autonomous driving research. The supplementary video can be viewed at https://youtu.be/Hp8Dz-Zek2E
Published at the 1st Conference on Robot Learning (CoRL)
References in corpus (1)
Cited by in corpus (57)
- Multi-modal Sensor Fusion-Based Deep Neural Network for End-to-end Autonomous Driving with Scene Understanding
- Argoverse: 3D Tracking and Forecasting with Rich Maps
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
- SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
- The StreetLearn Environment and Dataset
- SceML - A Graphical Modeling Framework for Scenario-based Testing of Autonomous Vehicles
- Unsupervised Domain Adaptation in Semantic Segmentation: a Review
- Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
- A Game Theory Based Ramp Merging Strategy for Connected and Automated Vehicles in the Mixed Traffic: A Unity-SUMO Integrated Platform
- Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments
- The State of Modeling, Simulation, and Data Utilization within Industry: An Autonomous Vehicles Perspective
- CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
- 3DB: A Framework for Debugging Computer Vision Models
- SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
- Learning Latent Representations to Influence Multi-Agent Interaction
- DSDNet: Deep Structured self-Driving Network
- Cooperative Perception with Deep Reinforcement Learning for Connected Vehicles
- Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
- Affordance Learning In Direct Perception for Autonomous Driving
- DeepRacing: Parameterized Trajectories for Autonomous Racing
- Feature Sharing and Integration for Cooperative Cognition and Perception with Volumetric Sensors
- Learning hierarchical behavior and motion planning for autonomous driving
- Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving
- Domain-invariant Stereo Matching Networks
- Recovering and Simulating Pedestrians in the Wild
- Shadow Transfer: Single Image Relighting For Urban Road Scenes
- Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments
- Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars
- SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
- Augmented Reality-Based Advanced Driver-Assistance System for Connected Vehicles
- Safe Deep Q-Network for Autonomous Vehicles at Unsignalized Intersection
- Learning to simulate complex scenes
- WAD: A Deep Reinforcement Learning Agent for Urban Autonomous Driving
- A Survey on Simulators for Testing Self-Driving Cars
- Simulating Autonomous Driving in Massive Mixed Urban Traffic
- Unsupervised Metric Relocalization Using Transform Consistency Loss
- GLADAS: Gesture Learning for Advanced Driver Assistance Systems
- Digital Twins Are Not Monozygotic -- Cross-Replicating ADAS Testing in Two Industry-Grade Automotive Simulators
- Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks
- Reinforcement Learning with Latent Flow
- Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry
- Multiple criteria decision-making for lane-change model
- Addressing crash-imminent situations caused by human driven vehicle errors in a mixed traffic stream: a model-based reinforcement learning approach for CAV
- A gamified simulator and physical platform for self-driving algorithm training and validation
- Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data
- Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
- Parallel and Multi-Objective Falsification with Scenic and VerifAI
- Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving
- Watch out for the risky actors: Assessing risk in dynamic environments for safe driving
- Self Training Autonomous Driving Agent
- 3D Surfel Map-Aided Visual Relocalization with Learned Descriptors
- Risk-Aware Lane Selection on Highway with Dynamic Obstacles
- Monocular Direct Sparse Localization in a Prior 3D Surfel Map
- Building Mental Models through Preview of Autopilot Behaviors
- KIT Bus: A Shuttle Model for CARLA Simulator
- DASC: Towards A Road Damage-Aware Social-Media-Driven Car Sensing Framework for Disaster Response Applications
- Manual-Label Free 3D Detection via An Open-Source Simulator