Autonomous driving

OpenPilot ↗ looks interesting, would love to try it out on a real car some day.

Notes#

• Tesla’s autopilot program shuts off less than a second before impact so the company can deny it was the cause of the impact. ↗

Links#

• Self Driving Cars [S1E2: ALVINN] (2019) ↗
• Elon Musk: Tesla Autopilot (2019) ↗
• Apollo ↗ - Open autonomous driving platform.
• OpenPilot ↗ - Open source driving agent.
• CARLA Simulator ↗ - Open-source simulator for autonomous driving research.
• Deep Reinforcement Learning for Autonomous Driving: A Survey (2020) ↗
• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving ↗
• highway-env ↗ - Environment for autonomous driving decision-making.
• Cruise ↗ - Self-driving vehicle service.
• Aurora ↗ - Delivering the benefits of self-driving technology safely, quickly, and broadly.
• Zoox ↗ - Driving autonomously in ways that no one else has shown. (HN ↗)
• Mobileye ↗ - Autonomous Driving & ADAS (Advanced Driver Assistance Systems).
• Einride ↗ - Making autonomous electric transport possible today. (GitHub ↗)
• Going Driverless: How we developed a CAN library for Go (2020) ↗
• SelfDriving.fyi ↗ - Comprehensive database of companies working on autonomous vehicles and related technologies.
• panda ↗ - Universal car interface.
• AirSim ↗ - Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research. (Docs ↗)
• Tesla Autopilot AI ↗
• George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets (2020) ↗
• Luminar ↗ - Making autonomous transportation safe with long-range, high resolution lidar and perception.
• comma.ai ↗ - Open source driving agent that runs on most cars. (Discord ↗)
• comma10k ↗ - 10k crowdsourced images for training segnets.
• 75 Minutes of Autonomous Driving with Kyle Vogt and Sam Altman (2020) ↗
• Oxbotica ↗ - Autonomous vehicle software company located in Oxford, UK.
• Why Tesla’s Full Self-Driving Is Such A Big Deal: 4D Data Continuity & Trajectory Projection (2020) ↗
• LIO-SAM ↗ - Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping.
• Neural Network Cars and Genetic Algorithms (2020) ↗
• Scalability in Autonomus Driving Workshop - Andrej Karpathy (2020) ↗
• Social Driving ↗ - Design multi-agent environments and simple reward functions such that social driving behavior emerges.
• FAST-LIO ↗ - Computationally efficient and robust LiDAR-inertial odometry (LIO) package.
• Awesome Lane Detection ↗
• SMARTS ↗ - Scalable Multi-Agent RL Training School for Autonomous Driving.
• Duckietown ↗ - Self-driving car simulator for the Duckietown universe. (Code ↗)
• R2LIVE ↗ - Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping.
• Five ↗ - AV development and safety assurance.
• Transitioning to Tesla Vision (2021) ↗ (HN ↗)
• Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles (2021) ↗ (HN ↗) (Summary ↗)
• XVIZ ↗ - Protocol for real-time transfer and visualization of autonomy data.
• SemanticKITTI ↗ - Dataset for LiDAR-based Semantic Scene Understanding.
• SemanticKITTI API ↗ - Helper scripts to open, visualize, process, and evaluate results for point clouds and labels from the SemanticKITTI dataset.
• Tesla Safety Score ↗ - Assessment of your driving behavior based on five metrics called Safety Factors.
• Self-Parking Car in 500 Lines of Code (2021) ↗ (Lobsters ↗) (HN ↗)
• Self-Parking Car Evolution ↗ - Training the car to do self-parking using genetic algorithm. (Code ↗)
• Samples for TensorRT/Deepstream for Tesla & Jetson ↗
• Gym environments and agents for autonomous driving ↗
• OATomobile ↗ - Research framework for autonomous driving.
• Learn-to-Race ↗ - Open-source autonomous racing.
• R3LIVE: Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package ↗
• Cruise Under The Hood 2021 - YouTube ↗
• HN: Cruise is opening driverless cars to the public in San Francisco (2022) ↗
• CT-ICP: Elastic SLAM for LiDAR sensors ↗
• You don’t ever own an electric vehicle (2022) ↗ (HN ↗)
• Cam2BEV ↗ - TensorFlow Implementation for Computing a Semantically Segmented Bird’s Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.
• Quatro ↗ - Fast and robust global registration for terrestrial robots.
• Awesome CARLA ↗ - CARLA has been developed from the ground up to support development, training, and validation of autonomous driving systems.
• CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation (2022) ↗ (Code ↗)
• YOLOP: You Only Look Once for Panoptic Driving Perception (2022) ↗ (Code ↗)
• Learning from All Vehicles (2022) ↗ (Code ↗)
• OpenCDA ↗ - Generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.
• BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (2022) ↗ (Code ↗)
• Dataset Governance Policy (DGP) ↗ - ML Dataset Governance Policy for Autonomous Vehicle Datasets.
• HelixNet Toolbox ↗ - Dataset presented in the “Online Segmentation of LiDAR Sequences: Dataset and Algorithm” paper.
• Nocturne ↗ - 2D driving simulator, built in C++ for speed and exported as a Python library.
• Autonomous Driving Data Framework (ADDF) ↗
• Autoware ↗ - Open-source software stack for self-driving vehicles, built on the Robot Operating System (ROS).