Self-driving trucking company Kodiak Robotics, Inc. today announced its fourth-generation autonomous truck. The new generation is designed for improved autonomous system robustness, with greater fleet uptime, manufacturing, and serviceability in mind—all of which the company says are critical to scale the technology quickly, safely, and efficiently.
“Complex and bulky systems that require an engineer to hand-build and hand-tune are expensive, unreliable, and difficult to debug,” said Don Burnette, Co-founder and CEO of Mountain View, CA-based Kodiak Robotics. “We believe that reliability and scalability flow from simplicity, and the best hardware modifications should be barely visible. Our fourth-generation platform is designed for simple, scaled production, which means easy calibration, troubleshooting, and maintenance for our partners.”
The fourth-generation truck features a modular and more discreet sensor suite in three locations—a slim-profile “center pod” on the front roof above the windshield and pods integrated into both side-view mirrors. This better-integrated sensor placement is said to vastly simplify sensor installation and maintenance and increases safety.
Recognizing self-driving supplier contributions
The fourth-generation technology represents the culmination of the company’s hard work and achievements since its founding in 2018, as well as its decades of collective experience in the industry, according to Jamie Hoffacker, Head of Hardware, Kodiak Robotics, in a Medium blog post.
“It is the result of close collaboration between our hardware, systems engineering, and operations teams, as well as a deep partnership with our industry-leading partner ecosystem,” wrote Hoffacker.
“Simulation allowed us to understand sensors’ performance requirements for critical metrics such as range, acuity, and field of view, while our real-world testing program allowed us to validate those sensor requirements on our partners’ actual hardware,” he wrote. “Additionally, we were able to choose our Gen4 sensor partners not only based on classic perception parameters such as precision and recall but also to maximize performance in critical regions-of-interest, as determined from real-world testing.”
The Kodiak Vision perception system takes a unique approach of considering every sensor—including LiDAR, camera, and radar—as primary, according to the company. The system fuses information from the sensors and considers the relative strengths and weaknesses of each type. It incorporates extra redundancies and cross-validates data, adding another layer of safety to the self-driving system.
This new truck’s autonomous driving system will feature Luminar’s Iris LiDAR, Hesai’s 360-degree scanning LiDARs for side- and rear-view detection, ZF’s Full Range Radar, and the Nvidia Drive platform.
New additions: ZF radar and Luminar LiDAR
The fourth-generation truck improves Kodiak Vision’s performance and reliability by incorporating the ZF Full Range Radar and Luminar’s long-range Iris LiDAR. These sensor integrations, combined with previously announced use of Hesai 360-degree scanning LiDARs for side- and rear-view detection, provide the necessary automotive-grade reliability needed for long-haul trucks.
All three sensors are purpose-built to meet the needs of autonomous trucks, which need to “see” long-range in a variety of weather conditions to safely operate at highway speeds.
The ZF Full Range Radar provides four-dimensional (4D) capabilities, measuring the distance, height, lateral angle, and velocity of an object out to more than 300 m (984 ft). Traditional radar cannot measure the vertical position of an object.
Kodiak sees the ZF Full-Range Radar technology “as critical to helping us bring self-driving trucks to market at scale,” wrote Court Hinricher, Senior Hardware Engineer, Kodiak Robotics, in a Medium blog post. “The addition of the ZF Full-Range Radar sensor allows our perception system to accurately track vehicle velocity at a range of up to 350 m, even in harsh weather conditions, and when integrated with additional sensors in our perception system we can build a highly precise and expansive model of the world around our self-driving trucks.
As he explained it, traditional radars rely on a single MMIC (Monolithic Microwave Integrated Circuit), while in the ZF Full-Range Radar four MMICs are cascaded, resulting in a total of 192 channels that provide highly accurate measurements of azimuth, elevation, range, and doppler. The long-range elevation (vertical position) measurement helps the Kodiak Driver resolve complex perception scenarios such as a stopped vehicle under a bridge, or a disabled vehicle on the shoulder under a road sign.
Luminar’s new automotive-grade Iris LiDAR’s wide horizontal and vertical field-of-view enables Kodiak trucks to recognize objects both near and far, adding further redundancy for long-range detections up to 600 m (1969 ft). The high resolution and range allow the system to reliably “see” objects such as pedestrians and motorcycles. The LiDAR’s slim design has a profile of just 10 cm (3.9 in) so it seamlessly integrates into the truck’s center front roof pod.
The patent-pending mirror pods—which will start with one Hesai LiDAR, two long-range 4D radars, and three cameras—don’t require specialized sensor calibration. Rather than replacing a sensor in need of maintenance, a mechanic can replace the mirror pod in minutes. This single point of integration will allow maintenance and serviceability at scale.
To make sense of all the data, the trucks will feature Nvidia Drive Orin as the supercomputing platform once available. With more than 250 TOPS (trillion operations per second) of compute performance, the platform is architected for safety and addresses systematic safety standards such as ISO 26262 ASIL-D (Automotive Safety Integrity Level-D). In the interim, Kodiak will use the current-generation Nvidia Drive AGX Pegasus to process data from the cameras.
Hitting the road in Q4
The fourth-generation trucks will debut on-road starting in Q4 of 2021, as Kodiak begins to take delivery of new tractors. Kodiak has placed an order for 15 PACCAR trucks to be delivered over the next year, more than doubling the company’s fleet size for delivering freight for commercial customers in Texas and elsewhere. Over the next couple of years, the company plans to expand throughout the southern half of the U.S. into other freight-rich corridors.
The truck will be powered by Cummins X15 Series engines and roll on Bridgestone Americas smart-sensing tire technology.
The X15 Series engines feature the Cummins ADS Powertrain control interface allowing the autonomous system to securely communicate with the engine. In addition, the 2021 X15 engines meet EPA and Greenhouse Gas Phase 2 requirements, providing a fuel economy improvement over previous generation engines.
The Kodiak trucks run exclusively on Bridgestone tires and will be equipped with the supplier’s cloud-connected sensors that capture critical tire-centric data, as highlighted by Futurride in June. That data will be analyzed and processed to increase uptime, improve overall safety, and enhance the operational efficiency of the automated system.
