Kodiak Robotics, a self-driving trucking company, has announced a new autonomous truck which will debut in Q4 of 2021.
The new truck will feature Luminar’s Iris LiDAR, ZF’s Full Range Radar, Hesai’s 360-degree scanning LiDARs for side- and rear-view detection, Cummins X15 Series engines, Bridgestone Americas smart-sensing tire technology, and the NVIDIA Drive development platform.
The new truck features a suite of sensors at three locations: a slim profile center pod on the front roofline of the truck, and pods integrated into both of the side mirrors. The placement of these sensors simplifies their installation and maintenance, and increases safety. Kodiak’s new truck will improve the robustness of the company’s autonomous system. It has been designed to enhance fleet uptime, manufacturing, and serviceability – all of which are critical to scale quickly, safely and efficiently.
Kodiak Vision, Kodiak’s perception system, considers every sensor, including LiDAR, camera and radar, as a primary source. The system combines information from these sensors and considers the strengths and weaknesses of each type. This incorporates extra redundancies and cross-validates data, and enhances the safety of Kodiak’s self-driving system.
The new truck improves performance and reliability of Kodiak Vision through the integration of ZF’s Full Range Radar and Luminar’s long-range Iris LiDAR. These integrations, alongside integrations with Hesai’s 360-degree scanning LiDARs for side- and rear-view detection, provide the 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 wide variety of weather conditions to operate safely at highway speeds.
ZF’s Full Range Radar provides Kodiak’s new truck with four-dimensional sensor capabilities – measuring the distance, height, lateral angle, and velocity of an object out to more than 300 meters. 4D radar allows the truck’s autonomous system to distinguish overhead objects, such as road signs and bridges, from road hazards, such as a stopped vehicle under a bridge or an overhead sign.
The wide horizontal and vertical field of view featured on Luminar’s Iris LiDAR allows Kodiak’s trucks to recognize objects near and far, adding further redundancy for long-range detections up to 600 meters. The system’s high resolution and range allows the system to detect objects such as pedestrians and motorcycles. Its slim design allows it to be easily integrated into Kodiak Robotics’ center roof pod in the front of the truck.
Kodiak Robotics’ patent-pending mirror pods – which will initially consist of one Hesai LiDAR, two long-range 4D radars, and three cameras – do not require specialized sensor calibration for easy upfit and repair. This allows the pods to be quickly replaced by a mechanic – providing maintenance and serviceability at scale.
Once available, Kodiak’s fourth-generation truck will also take advantage of the NVIDIA Drive Orin supercomputing platform. The platform is capable of more than 250 TOPS (trillion operations per second) of compute performance and addresses systematic safety standards such as ISO 26262 ASIL-D. In the interim, Kodiak will use the current generation NVIDIA DRIVE AGX Pegasus to process data fed from the truck’s cameras – allowing the autonomous system to perceive its surrounding environment.
Kodiak’s fourth-generation trucks will be powered by Cummins X15 Series engines. These engines feature the Cummins ADS Powertrain interface, a control interface that allows the truck’s autonomous system to safely, reliably and securely communicate with the engine. The truck’s tires, supplied by Bridgestone, are with Bridgestone cloud-connected sensors that capture critical tire-centric data. That data will be analyzed and processed into live actionable insights, increasing uptime, improving safety, and enhancing the efficiency of Kodiak’s automated systems.