ElectronsX > Autonomy > ADAS/AV Stack > Compute Platforms
EV ADAS/AV Compute Platforms
ADAS (Advanced Driver-Assistance Systems) and AV (Autonomous Vehicle) compute is the hardware that runs perception, sensor fusion, path planning, and vehicle control workloads in real time. In most vehicles today, this is primarily an inference platform — a vehicle-side computer that runs trained AI models on sensor data to generate driving decisions without cloud latency dependency. The choice of compute platform determines ADAS capability ceiling, OTA upgrade path, and the semiconductor supply chain exposure of every vehicle in the OEM's lineup.
The market is consolidating around a small number of dominant platforms. NVIDIA DRIVE (Orin and Thor) has captured the largest share of announced programs across both Chinese and Western OEMs. Mobileye EyeQ retains deep penetration among volume OEMs via its camera-centric co-packaged approach. Tesla runs a fully proprietary in-house silicon strategy — HW3, HW4, and the AI5 roadmap — with its own chip, board, and software stack. Qualcomm Snapdragon Ride is gaining ground in Western premium brands. Huawei's ADS platform dominates the Chinese domestic market for vehicles using Huawei's full autonomous driving stack. The directory below maps every major OEM to its current inference compute platform.
For technical architecture depth — SoC hardware blocks, safety supervision, autonomy level compute scaling, IVN networking, and thermal constraints — see: ADAS/AV Compute Architecture
For supply chain coverage — automotive SoC supply, DRAM, Ethernet PHYs, and functional safety components — see: SDV Systems Supply Chain
Compute Terminology
OEM naming for ADAS compute varies widely. The underlying hardware architecture is consistent regardless of label:
| Term | What It Means | Typical Scope | Example |
|---|---|---|---|
| Inference Platform / Inference Computer | Vehicle-side compute running real-time perception and planning models | ADAS/AV domain | Tesla FSD Computer (HW4), NVIDIA DRIVE Orin module |
| ADAS Computer / ADAS ECU | OEM label for the ADAS compute module; functionally equivalent to inference platform | ADAS/AV domain | Mobileye EyeQ system ECU, Bosch ADAS domain controller |
| Domain Controller (ADAS DCU) | May include inference workloads plus gateway and supervision functions | ADAS + gateway/supervision | Continental ADCU, Aptiv ADAS domain controller |
| Central Compute / Zonal Architecture | Architecture trend consolidating multiple domains (ADAS, body, infotainment) into fewer high-power compute nodes; ADAS inference is one domain within the consolidated compute | Multi-domain vehicle platform | Tesla's Full Self-Driving Computer as part of central architecture, NVIDIA DRIVE Thor targeting central compute consolidation |
Major Inference Compute Platforms
Tesla FSD Computer (HW3 / HW4 / AI5) - fully proprietary; Tesla-designed SoC and board; HW3 (2019): 72 TOPS; HW4 (2023): ~200 TOPS; AI5 in development; sole supplier to Tesla vehicles; OTA upgrade path is Tesla-controlled; the most integrated proprietary stack in the industry
NVIDIA DRIVE Orin - 254 TOPS; dominant platform for Chinese OEMs (BYD, Geely, Nio, Li Auto, XPENG) and Western (Mercedes, Volvo, Jaguar); ISO 26262 ASIL-D; software-compatible with DRIVE Hyperion sensor suite
NVIDIA DRIVE Thor - 2,000 TOPS; targets central compute consolidation (ADAS + cockpit + body in one chip); designed for L4 and next-generation L2+ platforms; production 2025-2026
Mobileye EyeQ5 / EyeQ6 - camera-centric; co-packaged with Mobileye's full sensor fusion and perception stack; Ford BlueCruise, GM Super Cruise historically; 24-112 TOPS depending on variant; SuperVision system for higher-autonomy applications
Qualcomm Snapdragon Ride - Snapdragon Ride Elite and Ride Vision; BMW, GMC, GWM; 360-700 TOPS depending on configuration; strong in cockpit+ADAS combined architecture; 4nm process
Huawei ADS SoC (MDC) - Huawei Mobile Data Center; Ascend AI compute; dominant in China for OEMs using Huawei's full autonomous driving stack (AITO, Arcfox, AVATR, Seres); subject to US export controls on Huawei but serving domestic China market
In-house OEM Silicon - XPENG XNet, Li Auto custom inference, BYD exploring proprietary; following Tesla's playbook; reduces dependency on Tier 1 SoC suppliers; requires massive software investment
Compute scale by autonomy level
Compute requirements scale with sensor count, model complexity, and redundancy requirements.
| Autonomy level (informal) | Typical compute pattern | Redundancy expectation | Network implication |
|---|---|---|---|
| L2 (ADAS) | Single ADAS SoC module or integrated ADAS ECU | Fail-safe; limited redundancy | Ethernet begins for cameras; CAN remains dominant for control |
| L2+ / L3 (conditional) | Higher-end SoC with more sensors and compute headroom | More supervision; increasing redundancy | Ethernet backbone expands; gateways bridge legacy buses |
| L4 (high autonomy) | Multi-SoC or redundant compute modules; higher storage and data logging | Fail-operational; physical redundancy expected | High-speed Ethernet fabrics; 10G-T1 becomes relevant |
ADAS for cars
| Car brand | ADAS system | Inference compute platform |
|---|---|---|
| Aion | ADiGO | NVIDIA DRIVE Orin |
| Aito | Qiankun ADAS (Huawei) | Huawei ADS SoC |
| Arcfox | α-Pilot ADS | Huawei Kirin 990A |
| Audi | Audi Pre Sense | Infineon |
| AVATR | Qiankun ADAS (Huawei) | Huawei ADS SoC |
| Baojun | Chengxing | Zhuoyu 7V+32 |
| BMW | BMW Personal Pilot L3 | Qualcomm Snapdragon Ride |
| BYD | DiPilot | NVIDIA DRIVE Orin/Thor |
| Chevrolet | UltraCruise | Snapdragon, Infineon |
| Denza | DiPilot | NVIDIA Drive Orin |
| Ford | BlueCruise | Intel Mobileye EyeQ |
| Geely | G-Pilot | NVIDIA DRIVE Orin | Ecarx |
| GMC | Super Cruise | Qualcomm Snapdragon Ride |
| GWM | Qualcomm Snapdragon Ride | |
| HiPhi | HiPhi Pilot | NVIDIA DRIVE Orin |
| Huawei | Huawei ADAS | Ascend AI |
| Hyper | NVIDIA DRIVE Thor | |
| Hyundai | SmartSense | NVIDIA DRIVE Orin |
| IM | UNP | NVIDIA Drive Orin |
| Jaguar | InControl | NVIDIA Drive Orin |
| Land Rover | InControl | NVIDIA Drive Orin |
| Leapmotor | Leapmotor Pilot | NVIDIA Drive Orin |
| Li Auto | NOA | NVIDIA DRIVE Thor |
| Lotus | NVIDIA DRIVE Orin | |
| Lucid | DreamDrive | NVIDIA DRIVE Orin |
| Luxeed | Qiankun ADAS (Huawei) | Huawei ADS SoC |
| Lynk & Co | G-Pilot | NVIDIA Drive Orin |
| Mazda | iActivsense | Qualcomm SA8155P |
| Mercedes-Benz | Drive Pilot | NVIDIA DRIVE Orin |
| Neta | Hozon Pilot | NVIDIA Drive Orin |
| NIO | NOP+ | NVIDIA DRIVE Orin |
| Nissan | ProPILOT | Renesas R-Car |
| Polestar | ADAS | NVIDIA DRIVE Orin |
| Porsche | InnoDrive | Intel Mobileye EyeQ |
| Renault | Active Driver Assist | Qualcomm Snapdragon Ride |
| Rivian | Rivian Driver+ | NVIDIA DRIVE Orin |
| SAIC | Navigation on Pilot | Horizon Robotics Journey 6 |
| Smart | SuperVision | Intel Mobileye EyeQ |
| Stelato | Qiankun ADAS (Huawei) | Huawei ADS SoC |
| Stellantis | STLA AutoDrive | Qualcomm Snapdragon Ride |
| Subaru | EyeSight | Xilinx Zynq UltraScale+ |
| Tata | Qualcomm Snapdragon Ride | |
| Tesla | Autopilot | Tesla FSD |
| Toyota | Safety Sense | NVIDIA DRIVE PX |
| Volvo | NVIDIA DRIVE Orin | |
| Voyah | Voyah Vpilot | Qualcomm Snapdragon Ride |
| VW | Travel Cruise | Qualcomm Snapdragon Ride |
| Wuling | Horizon Robotics Journey | |
| Xiaomi | Xiaomi Pilot (XP) | NVIDIA DRIVE Orin |
| Xpeng | XNGP | NVIDIA DRIVE Orin/Thor |
| Yangwang | NVIDIA DRIVE Orin | |
| Zeekr | Huohan 2.0+ | NVIDIA DRIVE Thor |
Related Coverage
Technical Architecture: ADAS/AV Compute Architecture | Full ADAS/AV Tech Stack |
Supply Chain: SDV Systems Supply Chain | Power Electronics SC
Autonomy: Autonomous Vehicles | Robotaxi Platforms | Autonomy in Robots
Sister Site: SemiconductorX - Tesla FSD Silicon Spotlight