The development kit includes cocoro SB's emotional engine, which was developed by leveraging its sensitivity technology to recognize emotional states such as confidence or uncertainty based on the driver's voice. The car's response to the driver's emotional state is displayed through a new driver-related user interface (UI) implemented in Renesas' R-Car SoC system. Because the car can understand the driver's words and emotional state, it can provide the appropriate response to ensure optimal driver safety. As this technology is linked to machine learning-based artificial intelligence, the car can learn from conversations with the driver, allowing it to evolve into a vehicle capable of providing the best possible response. Renesas plans to launch the development kit later this year.
Renesas considers the driver's emotional state, facial expression, and gaze direction as key information that, combined with the driver's vital signs, enhances the driver-car interface, bringing drivers closer to the era of autonomous vehicles. For example, if the car can recognize that the driver is experiencing an uncomfortable emotional state, even if they have verbally agreed to switch to hands-free autonomous driving mode, the car might ask the driver, "Would you prefer to continue driving and not switch to autonomous driving mode for now?" Furthermore, understanding the driver's emotions allows the car to control the vehicle's speed according to how the driver feels while driving at night in autonomous mode. With the development kit that leverages this emotional engine, Renesas hopes to expand the possibilities of this service model for developing new car-driver interfaces and other mobility markets that can utilize emotional state information.
Based on the recently launched Renesas Autonomy™, a new Advanced Driver Assistance System (ADAS) and automated driving platform, Renesas offers a safe, reliable, and practical driving experience by providing next-generation solutions for connected cars.
Note 1: The Emotion Engine, an artificial sensitivity and intelligence technology, consists of two parts. The first part is voice emotion recognition, which analyzes a voice signal. The second part is emotion generation technology, which generates emotions for the device by creating a virtual hormonal balance derived from various connected sensors. It then makes it possible to perceive the speaker's emotion by plotting an "emotional map" as a color—for example, yellow for happiness and red for sadness—and as a volume level from 1 to 10.
