Article "Self-driving cars are headed toward an AI roadblock"
Skeptics say full autonomy could be farther away than the industry admits
by Russell Brandom
July 3, 2018
Printable View
Article "Self-driving cars are headed toward an AI roadblock"
Skeptics say full autonomy could be farther away than the industry admits
by Russell Brandom
July 3, 2018
https://youtu.be/cECsj2Bznig
The collapsible crash test robot car
Published on Sep 10, 2018
Quote:
The Global Vehicle Target is the new standard for testing autonomous driving and crash test systems. To cameras and radar, it looks like a car: but if you hit it, it'll fly apart. So if your emergency braking doesn't quite work... well, this is what happens.
Thanks to everyone at Thatcham Research! You can find out more about them at https://www.thatcham.org
Airicist... u are amazing guy!
A big thanks to you for this links and videos!
______________________
Bump :rolleyes:
https://youtu.be/1imWlr_PiPA
Ford's sweaty robutt
Published on Jan 8, 2019
Quote:
For the sweat test, “Robutt” simulates a decade’s worth of car use in just three days as it sits, bounces and twists in the seat 7,500 times.
Based on the dimensions of a large man, the robotic bottom is heated to 36° C, and soaked with 450 millilitres of water.
Introduced in 2018 for Fiesta, the “Robutt” seat test is now being rolled out for all Ford vehicles in Europe
https://youtu.be/xZldmMNpIyk
Largest autonomous car parade - Guinness World Records
Published on Jan 14, 2019
https://youtu.be/NOHLENkL8oE
How machine learning helps identify potholes on Los Angeles roads
Published on Jan 16, 2019
Quote:
The streets of Los Angeles are peppered with potholes. To help identify and track them, three students at Loyola Marymount University developed a model using TensorFlow, Google’s open-source machine learning platform.
https://youtu.be/KqQyYOPPn7w
Helping autonomous vehicles to communicate with pedestrians
Published on Feb 6, 2019
Quote:
Hand gestures, head nods and thumbs-up signals all help to ensure drivers, pedestrians and cyclists know what each other is doing. But how will self driving vehicles, with no human driver, communicate with those around them?
https://youtu.be/gdbIDkQ0eCE
CES 2019 Trend: Vehicle technology
Published on Feb 6, 2019
Quote:
Vehicle technology at CES is larger than many stand-alone car shows, featuring the hottest cars and connected vehicles. Vehicle tech is growing at a rapid page, with a focus on self-driving cars and driver-assistance technology.
https://youtu.be/sRxaMDDMWQQ
MIT Self-Driving Cars: State of the Art (2019)
Published on Feb 1, 2019
Quote:
Introductory lecture of the MIT Self-Driving Cars series (6.S094) with an overview of the autonomous vehicle industry in 2018 and looking forward to 2019, including Waymo, Tesla, Cruise, Ford, GM, and out-of-the-box ideas of boring tunnels, flying cars, connected vehicles, and more. This covers the state of the art in terms of industry developments and not the perception and planning algorithm development. The latter will be covered in detail in future lectures. For more lecture videos on deep learning, reinforcement learning (RL), artificial intelligence (AI & AGI), and podcast conversations, visit our website or follow TensorFlow code tutorials on our GitHub repo.
Lex Fridman
INFO:
Website: deeplearning.mit.edu
GitHub: github.com/lexfridman/mit-deep-learning
Slides: dropbox.com/s/7in6e07mqiynvqi/self_driving_cars_state_of_the_art.pdf
Playlist: MIT Self-Driving Cars
OUTLINE:
0:00 - Introduction
1:53 - 2018 in review
4:49 - Fatalities
8:29 - Taxi services
10:54 - Predictions
16:55 - Human-centered autonomy
19:42 - Levels of autonomy and proliferation strategies
24:48 - Out-of-the-box ideas
27:28 - Who will be first?
29:26 - Historical context
31:05 - Underlying beliefs of the industry and public
32:32 - Driving is hard
35:32 - Humans are amazing
37:10 - Humans and automation don't mix well?
41:55 - Two approaches: Lidar vs Vision
49:54 - In the meantime… data
52:49 - The road ahead
https://youtu.be/YIB8IALSwmE
Predicting pedestrian movement in 3d for driverless cars
Published on Feb 15, 2019
Quote:
This research has immediate applications to driverless cars. Much of the machine learning used to bring autonomous technology to its current level has dealt with two dimensional images—still photos. A computer shown several million photos of a stop sign will eventually come to recognize stop signs in the real world and in real time.
But by utilizing video clips that run for several seconds, the U-M system can study the first half of the snippet to make its predictions, and then verify the accuracy with the second half.
“If a pedestrian is playing with their phone, you know they’re distracted,” said Ram Vasudevan, a U-M assistant professor of mechanical engineering. “Their pose and where they’re looking is telling you a lot about their level of attentiveness. It’s also telling you a lot about what they’re capable of doing next.”
The research was conducted out of the U-M Ford Center for Autonomous Vehicles (FCAV) by Xiaoxiao Du, a research engineer in FCAV, Matthew Johnson-Roberson, an associate professor of naval architecture and marine engineering, and Vasudevan.
https://fcav.engin.umich.edu
Read the paper: "Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Prediction" in IEEE Robotics and Automation Letters, 2019: https://doi.org/10.1109/LRA.2019.2895266
This video was produced by the FCAV lab, which acknowledges one of its former research engineers, Charles Barto, for his help in making this video, and also thanks Wonhui Kim and the rest of FCAV lab members who helped providing the PedX dataset used in this video.
https://www.engin.umich.edu