On September 16, the all-new Mercedes-Benz long-wheelbase GLE SUV was launched in China, equipped with an urban and highway Navigate on Autopilot (NOA) assisted driving system jointly developed by Mercedes-Benz and Momenta. When introducing this solution, Momenta explicitly mentioned its dedicated algorithm for ICE (Internal Combustion Engine) vehicles. An intelligent driving system is essentially used for environmental perception, driving decision-making, and vehicle control. So why does a change in powertrain type require re-adapting the algorithms specifically for the vehicle?
01. Intelligent Driving Capabilities Can Be Reused, but Vehicle Control Differs
Whether for ICE vehicles or BEVs (Battery Electric Vehicles), intelligent driving systems need to perceive the road environment through sensors such as cameras and LiDAR (Light Detection and Ranging), identify vehicles, pedestrians, road structures, and traffic conditions, generate driving decisions based on the current scenario, and ultimately translate them into control commands for acceleration, braking, and steering. Therefore, ICE vehicles do not need to build an intelligent driving system from scratch. Perception, prediction, and some decision-making capabilities inherently possess a strong foundation for reuse.
For intelligent driving in ICE vehicles, the real difference lies in how decisions are translated into vehicle actions. The intelligent driving system ultimately controls not an abstract motion model, but a real car. BEVs are driven directly by electric motors, and motor torque can be adjusted through the motor control system.
ICE vehicles, however, involve multiple components such as the engine, clutch or torque converter, and transmission. Different gears and powertrain operating conditions affect the transmission of driving force and the longitudinal response of the vehicle. Therefore, for the same acceleration or braking target, different powertrains will produce completely different vehicle responses. For the intelligent driving system, what truly needs to be mastered is not only how the vehicle should move, but also how this specific vehicle can execute the action, and whether the commands can be delivered to the execution end timely and accurately within the vehicle architecture.
02. Why Do ICE Vehicles Need Re-adaptation?
Car following, starting off, low-speed acceleration and deceleration, and parking are scenarios frequently encountered while driving. For instance, when a vehicle is following the car ahead, the intelligent driving system needs to continuously adjust longitudinal control. If the vehicle is in different gears or undergoing a gear shift, the power response may change. At this point, the controller faces not a fixed input-output relationship, but a dynamic system that varies with the vehicle's state.
Therefore, in vehicle control engineering, it is necessary to establish a dynamics model matched to the specific vehicle, identify parameters through testing and operational data, and then apply control compensation based on actual responses. Model identification here can be simply understood as estimating the vehicle's power response under different states through vehicle testing and operational data, enabling the controller to more accurately predict the vehicle motion resulting from a current control request. This is also a core part of adapting intelligent driving for ICE vehicles.
The intelligent driving system does not simply copy the control parameters originally used for BEVs. Instead, it needs to integrate the working characteristics of the specific powertrain to establish a more accurate correspondence between high-level decision-making and low-level vehicle control. The technical disclosure by Mercedes-Benz and Momenta regarding the new long-wheelbase GLE is a quite interesting example. According to their public introductions, at the software level, refined transmission modeling and algorithm compensation were conducted around half-clutch engagement, shift logic, power response, and multi-gear power output; at the hardware level, additional water-cooling designs were implemented to ensure stable system operation in complex scenarios. This demonstrates that adapting intelligent driving for ICE vehicles is not just about modifying high-level intelligent driving algorithms, but also involves the thermal design of the intelligent driving system itself, as well as the coordination between intelligent driving control and the ICE powertrain.
Momenta disclosed that in high-frequency parking scenarios, the system can shorten the waiting time for each gear shift by issuing shift requests in advance. In fact, during the parking process, the vehicle needs to frequently switch between moving forward, stopping, and reversing. If the intelligent driving system has already determined the next driving direction, it can coordinate the shifting process in advance, rather than waiting until the vehicle actually needs to move to execute the shift. This also illustrates that intelligent driving for ICE vehicles does not simply add an independent shifting module, but incorporates the shifting process into the timing planning of longitudinal control.
This also echoes the vehicle architecture issue mentioned earlier. Besides the powertrain, the adaptation of intelligent driving for ICE vehicles is also constrained by the underlying Electrical/Electronic Architecture (EEA). Many traditional ICE vehicles adopt distributed ECUs (Electronic Control Units), where modules primarily communicate via CAN or CAN-FD buses. The bandwidth and latency of standard CAN and CAN-FD cannot meet the real-time transmission requirements of high-level intelligent driving for multiple high-definition sensor data streams. The intelligent driving system needs to process data from multiple cameras, LiDAR, and other sensors simultaneously, which imposes much higher demands on bandwidth, computing power, and inter-module coordination. If the underlying communication and computing architectures cannot keep up, the data flow among perception, decision-making, and control will be restricted, making it difficult for even the most powerful algorithms to be stably translated into vehicle actions. Therefore, adapting intelligent driving for ICE vehicles is not just about enabling the algorithms to understand the powertrain, but also ensuring that the entire control chain runs smoothly within the vehicle architecture.
03. Intelligent Driving Ultimately Controls the Entire Vehicle
After discussing so much, it is evident that the technologies for intelligent driving in ICE vehicles and BEVs are not completely disconnected. Many capabilities in the perception, prediction, and decision-making layers can be reused; what truly needs to be reprocessed for the vehicle is the control relationship between the intelligent driving system and the specific vehicle. The same car-following trajectory and the same acceleration target may result in different vehicle responses when applied to different powertrains. Especially in scenarios such as starting off, low-speed car following, acceleration and deceleration transitions, gear shifting, and parking, if the control system does not fully consider the state of the powertrain, issues may arise where the actual vehicle response does not perfectly match the expected control target.
Therefore, it is not that ICE vehicles cannot implement intelligent driving, nor is it mandatory to develop a completely different intelligent driving architecture from scratch. Rather, the intelligent driving system must be truly integrated into the vehicle's motion control system. For ICE vehicles, the power transmission processes involving the engine, transmission, clutch, and gear shifting are not traditional mechanical components outside the intelligent driving system. Once intelligent driving begins to participate in vehicle control such as starting off, car following, acceleration and deceleration, and parking, the states and response characteristics of these power systems become part of the intelligent driving control problem. This is also why intelligent driving for ICE vehicles cannot simply copy BEV solutions. The intelligent driving system can be reused, but vehicle control must be adapted to the specific power and motion characteristics.
#AutonomousDriving #ICEVehicleIntelligentDriving