Title page
Copyright page
Preface
Acknowledgments
1 The Robotic Chauffeur
2 A Driverless World
3 The Ultimate Mobility Device
4 A Mind of Its Own
5 Creating Artificial Perception
6 First There Were Electronic Highways
7 Build Smart Cars, not Smart Highways
8 Rise of the Robots
9 Anatomy of a Driverless Car
10 Deep Learning: The Final Piece of the Puzzle
11 Fueled by Data
12 The Ripple Effects
Afterword: The Cambrian Explosion
Index

List of Tables

Table 2.1 In the U.S., the average commute to work is roughly half an hour.

List of Illustrations

Figure 2.1 A depiction of customized autonomous mobile office pods (concept). Source: Courtesy of IDEO
Figure 2.2 A depiction of a revitalized city where autonomous taxis have brought an end to traffic jams. Source: Granstudio
Figure 4.1 The “electric dog” (circa 1912). Source: Scientific American, supp. 2267, June 14, 1919, pp. 376–377.
Figure 5.1 Time-lapse image of Shakey in action (circa 1970). Source: SRI International
Figure 5.2 An occupancy grid of an intersection with recognized objects; the grid overlays sensor data onto stored data from a high-definition map. Source: Google, Inc.
Figure 6.1 As fairgoers listened, the Futurama’s narrative read, “The world we are now seeing is a vision, an artistic conception, which may undergo many changes as it develops into the great realities of tomorrow.” New York World’s Fair, “Futurama: Highways & Horizons,” 1939. Source: General Motors
Figure 6.2 “Electricity may be the driver.” Driverless Car of the Future, advertisement for “America’s Electric Light and Power Companies,” Saturday Evening Post, 1950s. Source: The Everett Collection
Figure 6.3 The electronic highway in action. Source: Radio Corporation of America (RCA), courtesy the David Sarnoff Library
Figure 6.4 The “Turbine-Powered” GM Firebird concept car entering an autopilot lane. This techno-utopian fantasy was set in 1976 but created in 1956 for GM’s Motorama Exhibit. Source: General Motors
Figure 6.5 The History of Driverless Cars: Key milestones in the evolution of autonomous vehicles.
Figure 8.1 An infamous stretch of road in the DARPA Grand Challenge of 2005 called Beer Bottle Pass, approximately seven miles from the finish line, featured over twenty twists and turns. Source: U.S. Federal Government (DARPA); Wikipedia
Figure 8.2 AI techniques used in driverless cars. Most robotic systems use a combination of techniques. Object recognition for real-time obstacle detection and traffic negotiation is the most challenging for AI (far left).
Figure 8.3 Arthur Samuel playing checkers on the IBM 7090 (February 24, 1956). Source: Courtesy of IBM Archives
Figure 9.1 High-definition map of an intersection, overlaid with sensor data. Source: HERE
Figure 9.2 What your eye sees (left) versus what the cameras sees (right). Can you tell the difference between the human and the background just by looking at the numbers? Source: Photo of Manhattan 14th Street, looking west from Fifth Avenue; Wikipedia.
Figure 9.3 View of 3-D point cloud data captured from a lidar mounted on a car driving through a bustling intersection. Source: Alex Kushleyev and Dan Lee, University of Pennsylvania
Figure 9.4 Raw target density plot of a forward-looking radar (left), and corresponding front view from the car (right). Large static objects are captured (parking cars, building barriers, street lamps). Grid based operation at 24Ghz. Source: SmartMicro 3DHD
Figure 9.5 Key sensors used in driverless cars. Most autonomous vehicles use multiples and combinations of some of these sensors.
Figure 10.1 Frank Rosenblatt and the Perceptron, shown here in connection with a television appearance. The 20 × 20 “eye” is shown, alongside wires from the “A” unit. Source: Robert Hecht-Nielsen, “Perceptrons,” UCSD Institute for Neural Computation Technical Report #0403, 17 October 2008. Photo courtesy of Veridian Engineering/General Dynamics Corp.
Figure 10.2 Sampling of images from ImageNet 2012. Similar images are placed closer to each other. Source: Andrej Karpathy and Fei-Fei Li, Stanford University
Figure 10.3 Schematic structure of a deep neural network. Spheres represent individual neurons. All neurons in a single layer are identical clones. Insets show actual visual features that some individual neurons respond to when trained on images of cars. Leftmost features represent edged; center features represent car segments such as doors and wheels; rightmost features represent nearly complete vehicles. Source: Feature insets from Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng, “Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations,” in Proceedings of the 26th Annual International Conference on Machine Learning, pp. 609–616 (ACM, 2009)
Figure 10.4 Deep learning recognizing objects on the road, in real time. Source: Courtesy of NVIDIA
Figure 10.5 A snapshot of our network as it spontaneously learned to respond to faces in a live video stream. Note that the two blurry white areas in the highlighted circle correspond to the two faces in the image frame. Source: Jason Yosinski, Cornell University
Figure 11.1 A 3-D map built using a process of simultaneous localization and mapping (SLAM). Source: Jakob Engel, Jorg Stuckler, and Daniel Cremers, “Large-Scale Direct Slam with Stereo Cameras,” in 2015 IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 1935–1942. IEEE, 2015; Andreas Geiger, Philip Lenz, and Raquel Urtasun, “Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite,” in 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354–3361, IEEE, 2012.
Figure 12.1 GM’s Electric Networked-Vehicle (EN-V) Concept pod, an autonomous two-seater codeveloped with Segway for short trips in cities. Source: General Motors
Figure 12.2 The most common job in most U.S. states in 2014 was truck driving. Source: National Public Radio
Figure 12.3 Passengers relax with electronics in this driverless concept mockup. Source: Rinspeed AG; image © Rinspeed, Inc.
Figure 12.4 Autonomous delivery method. Source: Image courtesy Starship Technologies
Figure 12.5 Autonomous delivery truck. Source: Inage courtesy IDEO
Figure 13.1 Progress of robots over hundreds of generations.

Guide

Cover
Table of Contents