How artificial intelligence could impact the car industry
Stéphane Canu
asi.insa-rouen.fr/enseignants/~scanu scanu@insa-rouen.fr
« APPC, ASI »
Road map
1 A very brief history of autonomous vehicles
2 Autonomous vehicles today
3 How has this happened? (Deep Learninng)
4 How Artificial Intelligence will change the Automotive Industry
5 Conclusion
Artificial intelligence and autonomous vehicles
Artificial intelligence is about doing things better than human
→ It can do a lot of things better than a human driver
NavLab: the autonomous vehicle of the 80s
1 M $ , 10 km/h
http://www.rediscoverthe80s.com/2016/11/navlab- the- selfdriving- car- of- the- 80s.html/
DARPA Grand Challenge 2004
for American autonomous vehicles only 1 million $
140 miles (225km) from Barstow, California to Primm, Neveda
DARPA Grand Challenge 2005
2 million $ – 132 miles (213 km) in the desert, Primm, Neveda.
Stanford vs Carnegie Mellon
212.7 km at an average speed of 30.7 km/h Key issue
"The specific transfer function emulates human driving characteristics, and is learned from data gathered through human driving."
CMU autonomous vehicles
Road map
1 A very brief history of autonomous vehicles
2 Autonomous vehicles today
3 How has this happened? (Deep Learninng)
4 How Artificial Intelligence will change the Automotive Industry
5 Conclusion
Level 2/3 Autonomous vehicles for sale
100 000 $
Tesla Model X vs. Audi A8
Motivations Today:
I driver comfort (10 000e→0 because of openpilot) Tomorrow
I save lives (safety)
I environmental issues
Comparaison des systèmes d’aide à la conduite (see
openpilot)
Level 4 experences in Rouen, Phoenix, 13 cities in China...
Waymo’s cars (Google) hit the 10 million-mile milestone on public roads New uses
public transportation (last kilometer) isolated people
autonomous ride services (taxi) . . .
pole- moveo.org/actualites/rouen- normandy- autonomous- lab- la- metropole- rouen- normandie- teste- un- service- de- mobilite- autonome/
Autonomous vehicle performance ranking
In total, 48 companies reported driving 2 million miles in autonomous mode on California roads and highways 2018
Advanced Driver Assistance Systems ADAS Ratings
Consumer Reports’ for major Advanced Driver Assistance Systems (nov 2020)
Safety Ratings
Safety Assist, which evaluated driver-assistance and crash-avoidance technologies.
Accidents: 8 lethal since 2015 (+7 processing)
https://www.republicanmatters.com/police- release- footage- of- fatal- uber- self- driving- car- accident/
What autonomy level?
→ Levels for AI ?
https://en.wikipedia.org/wiki/List_of_self- driving_car_fatalities
The 3 IA Levels
What do you see ? (is it a cat?) specific intelligence
Why is it a cat? general intelligence
Is she going up or down? super intelligence
Specific, General and Super Intelligence
What do you see ? (is it a cat?) specific intelligence
Why is it a cat? general intelligence
Is she going up or down? super intelligence
When do we see super intelligence?
Autonomy and Artificial Intelligence Levels
Level 3 autonomy specific intelligence
Level 4 autonomy general intelligence
Level 5 autonomy super intelligence
Road map
1 A very brief history of autonomous vehicles
2 Autonomous vehicles today
3 How has this happened? (Deep Learninng)
4 How Artificial Intelligence will change the Automotive Industry
Reconnaissance d’objets : caltech 101 database (2004)
101 classes,
30 images par catégorie ...and the winner is NOT a deep network
I pas assez d’images
in What is the Best Multi-Stage Architecture for Object Recognition? Jarrett et al, 2009
The image net database (Deng et al., 2012)
ImageNet = 15 million labeled high-resolution images of 22,000 categories.
Large-Scale Visual Recognition Challenge (a subset of ImageNet) 1000 categories.
1.2 million training images, 50,000 validation images,
A new fashion in image processing
shallow approaches deep learning
Y. LeCun StatLearn tutorial
Deep architecture and the image net (15%)
The Alex Net architecture [Krizhevsky, Sutskever, Hinton, 2012]
Convolution + Recitification (ReLU) + Normalization + Pooling 60 million parameters
using 2 GPU – 6 days regularization
ImageNet results
2012 Alex Net 2013 ZFNet 2014 VGG
2015 GoogLeNet / Inception 2016 Residual Network 2018 NAS Network
2020 EfficientNet (Transformers)
Reconnaissance d’objets par apprentissage
2020: GPT-3 contains 175 billion parameters Pour résoudre des problèmes spécifiques :
traitement d’image
reconnaissance de la parole, traduction automatique le texte : répondre à des questions, assistants, (GPT-3) planifier : Alpha GO
Big Models
GPT-3 requiert au moins 175 Go de mémoire vive
Detection, tracking and recognition of traffic signs (2011-13)
Recognition German Traffic Sign Recognition Benchmark (GTSRB) data set, containing 51839 labelled images of real-world traffic signs.
Detection The German Traffic Sign Detection Benchmark is a single-image detection
assessment 900 images (600 for training and 300 for test) and the winner is
Object recognition for autonomous vehicles
https://www.nvidia.com/en- au/self- driving- cars/drive- px/
https://pjreddie.com/darknet/yolo/
Two components are needed detection
recognition (characterization)
Perception is scene understanding
Scene understanding is
Multi-task learning
Components of self driving cars software (1)
Components of self driving cars software
AI inside: uses data
(Deep) learning based programming
Decision making is an imitation model
Imitation model is
Multi-Task and multi objective learning
Mayank Bansal , ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst, ICML 2019
Machine learning issues in self driving
multi task multi objective
architecture design issues
the never ending learning (long tails events) under budget
HydraNet: Tesla Autopilot Neural network architecture
in 2020 : 48 networks, 1,000 outputs, 70,000 GPU h to train Multi task learning
Sharing feature over space, cameras and time
HydraNet: Tesla Autopilot Neural network architecture
Multi task learning
Sharing feature over space, cameras and time
Tesla Neural Network
backbone ResNet50 (2020), RegNet (2021) (a Facebook 2020 paper) feature fusion : EfficientDet (from a Google 2019 paper)
decision module (multi task fine tuning)
I head
I trunk
I terminal
Tesla car crash
1916 Tesla’s car crash was due to a confusion between white side of trailer with brightly lit sky
Managing the confidence
Data: the long tail of situations
Rare driving situations
Drago Anguelov (Waymo) - MIT Self-Driving Cars lectures https://medium.com/waymo/how- do- we- prepare- for- rare- and- odd- situations- on- the- road- by- following- these- 3- steps- 1abd73d93e15
Tesla improving: iterative process
data
multi task learning fleet learing
testing = shadow mode for more training data
Tesla’s point of view on data
Gathering process
I 221 triggering situations manual labelling (1000 people)
I 2d -> 3d
I reconstruction labelling auto labelling
I use specificly trained networks
I human to clean simulation
I rare event
I sensor robustness
I adversarial exemples
Tesla’s release and validation
Waymo’s point of view
uses autoML (NAS cells)
Drago Anguelov (Waymo) - MIT Self-Driving Cars lectures
Waymo’s AutoML
Proxy end-to-end search: Explore thousands of architecture on a scaled-down proxy task, apply the 100 best ones to the original task,
validate and deploy the best of the best architectures on the car.
Drago Anguelov (Waymo) - MIT Self-Driving Cars lectures https://medium.com/waymo/automl- automating- the- design- of- machine- learning- models- for- autonomous- driving- 141a5583ec2a
Waymo’s AutoML (mobil eye is missing)
1) The first graph shows about 4,000 architectures discovered with a random search on a simple set of architectures. Each point is an architecture that was trained and evaluated. The solid line
marks the best architectures at different inference time constraints. The red dot shows the latency and performance of the net built with transfer learning. In this random search, the nets were not as good as the one from transfer learning. 2) In the second graph, the yellow and blue points show the results of two other search algorithms. The yellow one was a random search on a refined set of architectures. The blue one used reinforcement learning as in [1] and explored
Tesla vs. Waymo (vs. Openpilot, MobilEye, Appolo. . . )
Tesla Waymo
Autonomy Diver assist Self driving
objective Hands on the wheel no driver
Sensors Camera Lidar + Camera
Autopilot on highway Taxi in a known area
Data from the Fleet Simulation
3 millions miles per day 16 billions simulated miles AI multi task deep learning
semi supervised
hybrid deep learning reinforcement & Auto ML Running
by now 1 000 000 100
Project
2014/2016 2010
Open Pilot: 1000 $
Openpilot : l’étiquetage des données par crowd sourcing
Openpilot : surveillance du conducteur
EfficentNet inside
https://github.com/commaai/openpilot
Road map
1 A very brief history of autonomous vehicles
2 Autonomous vehicles today
3 How has this happened? (Deep Learninng)
4 How Artificial Intelligence will change the Automotive Industry
5 Conclusion
Programmation par l’exemple : le pari de Tesla & Waymo
Tesla is collecting “just over 3 million miles [of data] per day.”
Waymo train the car with 6 million miles driven on public roads and 5 billion driven in simulation
Learn agent for driving situation simulations
Massive open data sets
and simulators (Carla, google & microsoft)
Les 5 composants d’un système de conduite autonome
https://devblogs.nvidia.com/parallelforall/deep- learning- self- driving- cars https://medium.com/udacity/how- self- driving- cars- work- f77c49dca47e
Les données de ApolloScape
Des compétitions académiques
Des plateformes de développement ouvertes
Open source code, written by hundreds of students from across the globe!
Autoware (japon), NVIDIA’s DriveWorks and others
https://www.udacity.com/self- driving- car
Data for self driving cars: CNN
Tesla Project Dojo
L’IA dans l’automobile au delà du véhicule autonome
Assistance à la conduite (AI copilote)
Maintenance prédictive
Production : usine 2.0
Pour quoi faire ?
Accepter les voitures autonomes Une histoire de confiance
Nous voulons comprendre les enjeux conduite du changement
Pour quoi faire ?
self driving trucks and tractors
Road map (done)
1 A very brief history of autonomous vehicles
2 Autonomous vehicles today
3 How has this happened? (Deep Learninng)
4 How Artificial Intelligence will change the Automotive Industry
5 Conclusion
Future of AI in Automotive Industry
The value of your data (IA fuel) big data
Robustness (degraded conditions) deep learning theory Level 4 Autonomous driving common sense (cf Y. LeCun) unsupervised learning Predictive Maintenance data + prior knowledge
Acceptability (safety) Ethic
Interpretable AI
Questions?
http://asi.insa-rouen.fr/enseignants/~scanu/