InfoQ Homepage autonomous vehicles Content on InfoQ
-
Waymo Publishes Report Showing Lower Crash Rates Than Human Drivers
Alphabet's autonomous taxi company Waymo recently published a report showing its autonomous driver software outperforms human drivers on several benchmarks. The analysis covers over seven million miles of driving with no human behind the wheel, with Waymo cars having a 85% reduction in crashes involving an injury.
-
Ai4 2023: Generative AI Testing Lessons from Hussein Mehanna of Cruise
The recent Ai4 conference featured a talk by Hussein Mehanna of Cruise titled "How Autonomous Vehicles Will Inform and Improve AI Model Testing." Some key takeaways are that systems should handle the "long tail," developers should measure model output quality, and developers should push their systems to fail.
-
Waymo Developed Collision Avoid Test to Evaluate Its Autonomous Driver
Waymo developed a testing framework called Collision Avoidance Test (CAT) to evaluate the ability to avoid crush or potential hazard situations of its Waymo Driver, compared to a human driver.
-
Testing Advanced Driver Assistance Systems
Advanced driver assistance systems can have a huge number of test cases. Cutting the elephant into smaller pieces can ensure every bit and piece is tested. A good test environment is essential to be efficient, fast and flexible to cover all required tests to ensure quality. Testers should be involved in the project right from the beginning to avoid task-forces, quality- or delivery problems.
-
Wayve's End-to-End Deep Learning Model for Self-Driving Cars
Wayve released a state-of-the-art end-to-end model for learning a world model and vehicular driving policy based on simulation data from CARLA, allowing autonomy to cars without HD maps. Wayve’s new Model-based Imitation Learning (MILE) is a machine-learning model, specifically a reinforcement learning architecture, that learns a model of the world and a driving policy during offline training.
-
Implementing Remote Software Verification and Validation Using a Real Vehicle
Bosch is doing automated regression testing and user testing using a real car instead of a simulated one. Their aim is to test the software as quickly as possible, both from the test engineer's and user's perspectives. The car can be accessed remotely, and team members can work without being in the car.
-
TensorFlow 3D: Deep Learning for Autonomous Cars’ 3D Perception
Google has released TensorFlow 3D, a library that adds 3D deep-learning capabilities to the TensorFlow machine-learning framework. The new library brings tools and resources that allow researchers to develop and deploy 3D scene understanding models.
-
Waymo Publishes Autonomous Vehicle Safety Report
Waymo has published a report analyzing collisions involving their self-driving vehicles. The data was collected during more than 6 million miles of driving and includes 18 actual collisions as well as 29 simulated collisions.
-
Tesla Releases Full Self-Driving Mode Beta Update
Tesla has enabled new full-self driving features for certain customers. The new features include the ability to automatically steer the vehicle while on city streets, and Tesla plans to increase the price of the package by $2,000 in the near future.
-
MIT and Toyota Release Autonomous Driving Dataset DriveSeg
Toyota's Collaborative Safety Research Center (CSRC) and MIT's AgeLab have released DriveSeg, a dataset for autonomous driving research. DriveSeg contains over 25,000 frames of high-resolution video with each pixel labelled with one of 12 classes of road object. DriveSeg is available free of charge for non-commercial use.
-
Audi Releases Autonomous Driving Dataset
Researchers at Audi have released the Audi Autonomous Driving Dataset (A2D2) for developing self-driving cars. The dataset includes camera images, lidar point clouds, and vehicle control information, and over 40,000 frames have been segmented and labelled for use in supervised learning. The dataset can be used for commercial purposes.
-
Waymo Shares Autonomous Vehicle Dataset for Machine Learning
Waymo, the self-driving technology company, released a dataset containing sensor data collected by their autonomous vehicles during more than five hours of driving. The set contains high-resolution data from lidar and camera sensors collected in several urban and suburban environments in a wide variety of driving conditions and includes labels for vehicles, pedestrians, cyclists, and signage.
-
NVIDIA Announces RAPIDS, Medical Image Application, and a Driving Simulator for Autonomous Vehicles.
Today Jensen Huang, CEO of NVIDIA, gave a keynote at the GPU Technology Conference 2018 in Munich. He announced RAPIDS, an open-source CUDA accelerated toolkit that can help data scientists to faster process their data. They announced a partnership to work on medical imaging. They announced a self-driving car simulator that car manufacturers can use for verification of autonomous vehicles.
-
Major Automakers Aim to Bring Blockchain to Cars
Launched by four of some of the major automakers worldwide and a number of other companies, the Mobility Open Blockchain Initiative (MOBI) focuses on speeding up Blockchain adoption for mobility applications, from payments to ride-sharing and autonomous vehicles.
-
Baidu Release Huge Dataset "ApolloScape" for Autonomous Vehicle Research
Baidu, the Chinese internet giant, has released ApolloScape, a massive data-set for autonomous vehicle simulation and research. ApolloScape is an order of magnitude more complex than similar open data-sets. It is part of Apollo, Baidu's vehicle simulation and hardware platform. With this release, Baidu strengthens its position in the automated driving sector.