To cap off a rollercoaster of a year, we invited Brad Templeton to present a year-end Deep Dive to DeepMap employees. Brad discussed mapping technology for semi-autonomous and autonomous vehicles (AVs), and provided an analysis of significant events in the AV space in 2020.
Detailed Maps = Advanced Knowledge
Brad spoke about the importance of highly-detailed maps, such as those from DeepMap, for semi-autonomous and autonomous driving. This type of map is designed to be read by machines, rather than humans. …
GeoSpatial World is a global organization that raises awareness about the tremendous potential of geospatial technologies. Recently they invited DeepMap to present our perspectives on HD mapping and Level 2+ / Level 3 autonomy. We were delighted to do so.
You can read the full GeoSpatial World post, authored by Dr. Erwin A. Frei, here. We’ve summarized it below:
Many vehicle owners are familiar with automated safety features that fall under the umbrella term of Advanced Driver-Assistance Systems (ADAS). Examples of ADAS features available today include:
Automakers are now in a fierce competition to offer the next generation of ADAS functionality. These systems are rolling out in new car and truck models now and over the next few years, offering features such…
Every quarter, we like to send our friends, supporters, and partners a curated update on what we’ve been up to here at DeepMap. Below, you will find our Quarterly Newsletter: November 2020 Issue. If you would like to keep up-to-date on DeepMap news, you can subscribe to our newsletter here.
Dear DeepMap customers, partners, and supporters:
As we approach the close of the year, we hope you, your families, and your colleagues are staying safe and healthy.
To say that 2020 was unusual is an understatement. But innovation never sleeps, and there were bright spots in the autonomous-driving industry this year. …
Although we might think the world is already sufficiently mapped by the advent of global satellite images and street views, it’s far from complete because much of the world is still uncharted territory. Maps are designed for humans, and can’t be consumed by autonomous vehicles, which need a very different technology of maps with much higher precision.
DeepMap, a Palo Alto startup, is the leading technology provider of HD mapping and localization services for autonomous vehicles. These two services are integrated to provide high-precision localization maps, likely down to a centimeter precision. This demands processing a high volume of data to maintain precision and localization accuracy. In addition, road conditions can change minute to minute, so the maps guiding self-driving cars have to update in real time. …
DeepMap’s VP of Corporate Development, Dr. Erwin Frei, participated in a roundtable last week hosted by Girish Joshi, Director Americas, Geospatial Media & Communications.
The conversation covered topics such as:
In his intro, Erwin showed a video highlighting DeepMap mapping technology in a variety of situations, including highways, sparse environments, and tunnels.
Erwin then discussed the critical “drivers” for automated and autonomous driving: safety, comfort, and efficiency. …
From time to time, DeepMap shares perspectives from industry experts on our blog. Today we recommend Brad Templeton’s commentary on Tesla’s “Full Self-Driving” beta.
In a 10/23/20 Forbes article, analyst Brad Templeton provides an overview of the recent “Full Self-Driving” (FSD) beta released by Tesla. Templeton writes: “The package is impressing many of these owners. A few have posted videos to Youtube showing the system in operation on city streets.”
Templeton presents a list of the “big questions” posed by the controversial beta release. Of particular relevance to DeepMap is the following:
→ How does Tesla’s decision to avoid LIDAR and detailed maps affect the quality of their system? …
Today we announced DeepMap HDR™ (High-Definition Reference), a service for companies who are building hands-free Level 2+ driving systems using crowd-sourced maps.
Complementing existing perception-based Level 2+ autonomy platforms, DeepMap HDR registers and aligns crowd-sourced perception outputs to generate and update live, high-fidelity maps.
James Wu, DeepMap Co-Founder and CEO, said, “DeepMap HDR solves a critical piece of the puzzle for companies seeking to validate and improve crowd-sourced mapping data. We developed this service to enable our customers to offer safe, reliable, and high-performance hands-free driving, while expanding the Operational Design Domain (ODD) of next-generation consumer vehicles.”
The announcement was made on the opening day of the NVIDIA GPU Technology Conference (GTC), where DeepMap Co-Founder and CTO Mark Wheeler is presenting on “Future-Proof Mapping for Level 2+ Autonomy and Beyond.” The on-demand session (A21158) will be available on the GTC website on October 5 at 9am PDT, following NVIDIA CEO Jensen Huang’s keynote. …
DeepMap Co-Founder and CEO James Wu sat down with Grayson Brulte for an interview on The Road to Autonomy, Grayson’s self-driving car podcast. In the interview, the two discussed a wide range of issues, including how HD maps are enabling all SAE Levels of autonomy, from Level 2+ to Level 4.
To start, James described three observations that inspired him and Mark Wheeler, DeepMap Co-Founder and CTO, to start DeepMap in 2016:
On occasion, we like to highlight viewpoints and commentary written by other companies in the industry. Today we recommend an informative post by Waymo.
* * *
Waymo, formerly known as the Google self-driving car project, recently published a blog post about the mapping component of its full-stack autonomous driving system. We recommend the post as a quick read that clearly describes the role of maps designed for machines, rather than humans.
The Waymo authors write:
“The information our vehicles care about is quite different from someone trying to find their way to a restaurant. …
DeepMap COO and Head of Product, Wei Luo, delivered the keynote address today to members of the Open AutoDrive Forum (OADF), an organization focused on standards for autonomous driving.
Speaking via Zoom to an audience of (physical) attendees in Germany as well as (virtual) participants around the world, Wei explained the critical role of high-definition (HD) maps in the safety and performance of autonomous vehicles (AVs).
“AVs need to know lane level rules and need to have the ability to take proactive actions on the road to enhance driving smoothness and safety. When an HD map has errors, the vehicle can fail to localize and fail to take appropriate actions,” she said. “The richer the data is in the HD map, the more ADAS and AV features it can help to unlock. …