Skip to main content

Waymo redesigns fifth generation hardware sensor suite

Waymo has redesigned its fifth-generation hardware sensor suite with the aim of enabling the scaled deployment of Waymo Driver autonomous vehicles (AVs).
By Ben Spencer March 16, 2020 Read time: 2 mins
Waymo's self-driving Jaguar I-Pace electric SUV 1 (Source: Waymo)

In a blog post, Satish Jeyachandran, head of hardware at Waymo, says the new 360 Lidar system provides a bird's-eye view of the cars, cyclists and pedestrians surrounding the vehicle. It allows Waymo Driver to navigate the complexities of city driving by distinguishing the opening of a car door a city block away while also allowing its trucks to spot debris hundreds of metres ahead on the highway, he adds.
 
Perimeter Lidars are now placed at four points around the sides of the vehicle to help it navigate tight gaps in city traffic and cover potential blind spots on hilly terrain.
 
According to Jeyachandran, long range cameras and a 360 vision system identify pedestrians and stop signs greater than 500m away.
 
Additionally, a perimeter vision system is expected to work in conjunction with its perimeter Lidars to give Waymo Driver another perspective of objects close to the vehicle.
 
“For example, while our perimeter Lidars detect obstacles directly in front of the vehicle with precision, our perimeter cameras provide our machine learning algorithms additional details to reliably identify objects, providing more context to the traffic scene,” Jeyachandran explains.
 
He claims that a peripheral vision system allows Waymo to ‘peek’ around a truck driving in front to determine whether it is safe to overtake or wait.
 
Waymo has also redesigned the architecture, outputs and signal processing capabilities of the hardware sensor suite to create an “imaging radar system for self-driving”.
 
“Our next-generation radar can also see objects at great distances, including detecting a motorcyclist from hundreds of metres away,” he continues. “Like with our other long-range sensors, being able to accurately detect objects at greater distances gives us a longer reaction time to make a more comfortable experience for our riders.”
 
The company has integrated its new generation of sensors on its Jaguar I-PACE vehicle.
 
“With the first of these new vehicles, we’ve completed comprehensive module-level and system-level tests to ensure our next-generation hardware can withstand whatever the roads throw at it - from stormy weather and salted roads, to extreme heat and dirt storms,” Jeyachandran concludes.

 

Related Content

  • June 11, 2015
    Transportation applications move to machine vision’s mainstream
    The adaptation of machine vision to transport applications continues apace. That the machine vision industry is taking traffic installations seriously is evident by the amount of hardware and software products tailor-made for ITS applications that are now available on the market. A good example comes from US-based Gridsmart Technologies which has developed a single wire fisheye camera that provides a horizon to horizon view for use at intersections. Not only does the single camera replace four or more in a
  • November 3, 2021
    Ouster Lidar aids German V2X plans 
    Researchers built 60 mobile measuring stations to be deployed across a 4.3km stretch
  • September 8, 2015
    Hackers can fool self-driving car sensors into evasive action
    The laser ranging (LIDAR) systems that most self-driving cars rely on to sense obstacles can be hacked by a setup costing just US$60, a security researcher has told IEEE spectrum. According to Jonathan Petit, principal scientist at software security company Security Innovation, he can take echoes of a fake car, pedestrian or wall and put them in any location. Using such a system, which he designed using a low-power laser and pulse generator, attackers could trick a self-driving car into thinking somethin
  • September 15, 2014
    CCTV brings transit safety into view
    David Crawford looks at camera-based vulnerable road users protection systems.Safe and efficient operation of road-based transit depends on minimising the risks of incidents involving other vehicles or vulnerable road users such as pedestrians, cyclists and passengers boarding or alighting from buses or trams. The extent and quality of the visibility available to drivers is crucial in preventing and avoiding incidents. Conventionally, they have had to rely on fairly basic equipment - essentially the human