DeepRoute.ai, an artificial intelligence (AI) company, has signed a cooperation agreement with Qualcomm Technologies to create high-performance, cost-effective advanced driver assistance solutions (ADAS) and automated driving systems.
These intelligent driving solutions will be based on the Qualcomm’s Snapdragon Ride Platforms, specifically the SA8650 model.
The partnership will see DeepRoute.ai leveraging the Snapdragon Ride Platform to develop intelligent driving solutions that encompass both LiDAR and vision-only ADAS systems.
These systems will support advanced driving features such as Urban Navigation on Autopilot (NOA), Highway NOA, and automated parking.
The technology will be designed to be deployable on both fuel vehicles and new energy vehicles, catering to the diverse needs of global automakers for a broad spectrum of vehicles.
Furthermore, the two companies will collaborate to optimise AI models, including end-to-end (E2E) Birds Eye View (BEV) and transformers, on the Snapdragon Ride Platforms.
The architecture, which simulates the human neural network, allows the intelligent driving systems to more naturally comprehend traffic environments and the logic behind driving behaviours.
This is particularly useful in complex road scenarios such as human-vehicle interaction, navigating around parked vehicles, irregular intersections, and driving on narrow roads.
The E2E model will enable vehicles to understand human driving culture, allowing for real-time traffic analysis and efficient lane changes when faced with obstructions like road construction.
For enhanced safety, DeepRoute.ai has optimised its algorithms to handle complex lighting conditions, including strong light, low light, and backlight.
These improvements aim to bring the performance of vision-only systems in line with that of LiDAR-based solutions, even in extreme environments.
The open architecture of the Snapdragon Ride Platforms allows automakers and Tier-1 suppliers to implement a range of ADAS algorithms, including camera perception, sensor fusion, driving strategies, automated parking, and driver monitoring.
Featuring AI accelerator and image processing engine, the platforms allow to process data from multiple radars, up to 16 cameras, and lidars concurrently to meet the advanced requirements of intelligent driving solutions.
Qualcomm Technologies product management vice-president Anshuman Saxena said: “Our technology cooperation with DeepRoute.ai is a collaborative effort that harnesses DeepRoute.ai’s algorithmic expertise and the technological advantages of working utilizing Snapdragon Ride Platforms.
“Together we aim to reduce hardware costs and deliver advanced intelligent driving experiences to users globally. We look forward to continuing our relationship with DeepRoute.ai and their proven expertise in integrating end-to-end AI models into mass-produced vehicles.”
Earlier this year, Qorix and Qualcomm Technologies teamed up to advance software-defined vehicles (SDVs) through integrated, high-performance, and scalable solutions.
