In 2009, Google started the Self-Driving Car project and it had been over a decade and there are no self-driving cars yet. In 2016, 1.35 million lives are lost to traffic crashes around the world, and in the U.S. the number of tragedies is growing.
How does Waymo Cars Works? Waymo mainly uses Lidar technology with its Laser Bear Honeycomb™. It is a lidar with a design for 95˚vertical Field Of View (FOV) and up to a 360° horizontal FOV. The lidar has been tested in Waymo’s self-driving cars for over 2 million hours, 20 millions of miles, and billions of simulated miles.
Sensors in Waymo Cars To See
The first step for any cars to work is to sense and see the world we see. There have been different approaches towards the self-driving cars, from using
- cameras mainly with image processing in Tesla or Intel
- lidar mainly in Waymo and NVIDIA Drive with 3D maps.
There are many issues in which using mainly cameras can fail, especially facing a new scenario. For example, a camera might misrecognized buses as speed signs due to some buses with the speed limits at the back of buses.
The ultrasound to supplement cameras detect only close distance (around 70ft) and a minor accident would still happen even if brakes were applied as soon as possible.
Therefore, Waymo went to the approach of lidar and 3D maps. That created a different set of problems, requiring a proper 3D map of the world. At the beginning of the self-driving car program, the company spent $75,000 for each lidar system from Velodyne In 2017, the cost decreased approximately 90 percent, with Waymo designing its own version of lidar. (en.wikipedia.org)
Below is the full range of sensors reportedly used by Waymo, including its own cheaper and better version of lidar:
Lidar (Laser) System Lidar (Light Detection and Ranging)
Lidar works day and night by beaming out millions of laser pulses per second—in 360° degrees—and measuring how long it takes to reflect off a surface and return to the vehicle. Waymo’s system includes three types of lidar developed in-house: a short-range lidar that gives our vehicle an uninterrupted view directly around it, a high-resolution mid-range lidar, and a powerful long-range lidar that can see almost three football fields away.
Vision (Camera) System
The vision system includes cameras designed to see the world in context, as a human would, but with a simultaneous 360° degree field of view. Because our high-resolution vision system detects color, it can help our system spot traffic lights, construction zones, school buses, and the flashing lights of emergency vehicles. Waymo’s vision system is comprised of several sets of high-resolution cameras, designed to work well at long range, in daylight and low-light conditions.
Radar System Radar
It uses electromagnetic waves to perceive objects and movement. Radar remains effective in rain, fog, and snow, and operates equally well day or night. Waymo’s radar system has a continuous 360° degree view, so it can track the presence and speed of road users in front, behind, and to both sides of the vehicle.
Inertial Measurement Unit
This module uses accelerometers and gyroscopes with input from GPS, maps, wheels speeds, and laser and radar measurements to provide highly accurate position, velocity, and heading information to the vehicle. This information remains highly accurate even in the event of a sensor, vehicle component, or other system failures.
Waymo vehicles also have a number of additional sensors, including our audio detection system that can hear police and emergency vehicle sirens up to hundreds of feet away, and GPS to supplement our vehicles’ extensive understanding of their physical locations in the world.
The World Most Experienced Driver
Waymo plans to create the World’s Most Experienced DriverTM using lots of data and sensors to provide the best safety. In their 2020 September car safety report, Waymo broke down how it works logically:-
- Before our cars drive in any location, our team builds our own detailed three-dimensional maps that highlight information such as road profiles, curbs and sidewalks, lane markers, crosswalks, traffic lights, stop signs, and other road features. Rather than rely on GPS, the Waymo Driver cross-references our pre-built maps with real-time sensor data to precisely determine their location on the road.
- Our sensors and software scan constantly for objects around the vehicle — pedestrians, cyclists, vehicles, road work, obstructions — and continuously read traffic controls, from traffic light color and railroad crossing gates to temporary stop signs. The Waymo sensor suite has a 360° degree view around the vehicle and is designed to respond to objects up to up to 300 meters away (nearly three football fields)
- For every dynamic object on the road, our software predicts future movements based on current speed and trajectory. It understands that a vehicle will move differently than a cyclist or pedestrian. The software then uses that information to predict the many possible paths that other road users may take. Our software also takes into account how changing road conditions, such as a blocked lane, may impact the behavior of others around it
- Waymo's software considers all of this information as it finds an appropriate route for the vehicle to take, then selects the exact trajectory, speed, lane, and steering maneuvers needed to progress along this route safely. Because our Waymo Driver constantly monitors the environment and predicts the future behavior of other road users in 360° degrees around our vehicles, our Driver can respond quickly and safely to any changes on the road.
Fully Self Driving Car
Regardless of which technology (camera or lidar) the cars are using, the goal is to remove human drivers from the road due to safety reasons.
In 2012, Waymo developed and tested a Level 3 system that would drive autonomously on the freeway in a single lane but would still require a driver to take over at a moment’s notice. During our internal testing, however, we found that human drivers over-trusted the technology and were not monitoring the roadway carefully enough to be able to safely take control when needed.
Gallup (reported in vox.com) polled the question on self-driving cars and found
- 9 percent of Americans who'd get such a car right away,
- 38 percent saying they'd wait a while, and
- around 50% steadfast that they'd never use one.
Self-driving is a matter of when the Authority will start letting cars self-drive given sufficient data and trust. People will then enjoy the ride better with in-car entertainment much like a public transport.
This brief scanned the following sources (title, domain, description):
- Inside Waymo's Secret World for Training Self-Driving Cars (theatlantic.com) - An exclusive look at how Alphabet understands its most ambitious artificial intelligence project
- Self-driving cars from Tesla, Google, and others are still not here(vox.com) - Engineering teams at Tesla, GM, Honda, and others are struggling to make self-driving cars work properly.
- Waymo's Self-Driving Cars: How They Work (lifewire.com) - Waymo's driverless car tech has come a long way since the Google Self-Driving Car project began in 2009, and you may be able to catch a ride soon.
- Interview: How Waymo's Lidar Plan Works (eetasia.com) - Among all self-driving car developers, Waymo is currently the only company making its lidar commercially available. But Waymo's partners are limited to only those who work in non-automotive autonomy.
- Waymo 360-degree video shows how autonomous vehicles work (techcrunch.com) - Fresh on the heels of settling a contentious and expensive lawsuit with Uber, Alphabet's self-driving unit Waymo is looking to get out there and educate the public on how its autonomous vehicles work. In a blog post announcing that Waymo self-driving cars have racked up 5 million miles of driving experience on public roads, the […]
- How Self-Driving Cars Work (letstalkselfdriving.com) - Waymo multi-layered sensor suite works seamlessly to paint a detailed 3D picture of the world, showing dynamic and static objects and other road features.
- How do Google's driverless cars work? (alphr.com) - Driverless cars will hit the roads in trials in three British cities next year, but how do self-driving cars work? Google has been testing its prototype car on US roads – it's yet to be trialed in the UK.
- Lyft and Waymo are working together on self-driving car tech (theverge.com) - Waymo, Alphabet's self-driving car company, will work with ride-sharing service Lyft to develop new autonomous vehicle technologies. The two companies confirmed the partnership today, stating that...
- Learn how Waymo drives - Waymo Help (support.google.com) - Waymo cars see and understand the world around them through a number of sensors, external cameras, and software. Waymo uses the information it gathers to drive safely through real city streets every day.
- How does Google's Waymo self-driving car work: (businessinsider.com) - Waymo will begin testing a fleet of 100 self-driving Chrysler Pacifica minivans by the end of the month here's how they are able to get around.
- Some of the biggest critics of Waymo and other self-driving cars (washingtonpost.com) - “I don't want to be the guinea pig. I don't want my husband to be the guinea pig,” said a Silicon Valley resident.
- Waymo: Home (waymo.com) - Waymoâformerly the Google self-driving car projectâstands for a new way forward in mobility. Our mission is to make it safe and easy for people and things to move around.
- How Driverless Cars See the World Around Them (nytimes.com) - On Sunday, a woman in Arizona died after being struck by a self-driving car operated by Uber. Here is a guide to how autonomous vehicles operate.