When you control the power of batteries and gas engines, you make the powertrain more efficient. When you make powertrains more efficient, you improve fuel economy. One group of technologies that can you help you better manage your vehicle’s energy: ADAS, or advanced driver assistance systems.
The same radar, LIDAR, ultrasonic sensors, and imaging systems used to keep drivers from colliding with objects or straying from lanes can all be repurposed to make your gas engines more productive.
In a Tech Briefs feature article, see the promising results that demonstrated the role of repurposed commercially available ADAS tech in implementing what’s known as an Optimal Energy Management Strategy (EMS).
Gas Engines and ADAS
Traditional ADAS tracks and utilizes details like vehicle location, distance of objects to the driver, and lane detection to allow a car to drive more safely.
What if those same components could determine that the vehicle/driver is going to slow down for a while? Could the ADAS systems then initiate a shutdown of the gas engine to reduce fuel consumption?
This Tech Briefs article reviews a demonstration – and improvement – of different ADAS technologies and algorithms. The systems each pick up data regarding stop signs and stoplights, nearby vehicles, and upcoming turns.
To reduce fuel consumption in gas engines, the data required from an ADAS system has to provide as close to perfect of a prediction as possible. This so-called ground truth data is obtained from human researchers, instead of a computer algorithm.
See how the researchers used ground-truth measured values and gas-engine simulations to validate a baseline Optimal EMS.
Three Types of ADAS Models Were Used to Optimize Gas Engines
- Vehicle Operation Prediction Model ADAS data, along with current GPS location and current vehicle velocity, predicted future vehicle operation within the perception subsystem. An artificial neural network combined the outputs from sensors and signals to generate a vehicle velocity prediction.
- A Planning Subsystem Model helped to issue a control request to the vehicle's “running controller,” which evaluates component limitations before actuating the vehicle powertrain.
- A Vehicle Subsystem Model handled Optimal EMS control requests related to fuel consumption, gas engine power, and battery state of charge. These results were then compared to the outputs from baseline EMS simulation.
When reviewing worldwide energy consumption, fuel economy must be considered. One way to improve fuel economy is to use driver feedback to promote better habits that save energy. Emerging research, shown in this Tech Briefs Application Brief, demonstrates how Advanced Driver-Assistance Systems (ADAS) promote this kind of “eco-driving.”
Globally Optimal EMS fuel economy improvement is possible when the entire drive cycle is predicted 100% accurately from time zero. In this Tech Briefs article, get a close-up look at a team’s effort to improve ADAS algorithms and detection to support energy-management efforts.Improving Vehicle Economy with ADAS