cpmGO - The first purely edge-based automotive intelligent assistant launched by Facewall Intelligence

What is cpmGO?

cpmGO (MiniCPM Super Assistant) is the world's first purely edge-side intelligent assistant launched by Mianbi Intelligence, designed specifically for automotive intelligent cockpits. Developed based on the Mianbi MiniCPM edge-side model, cpmGO boasts rich capabilities including vision, voice, multimodal interaction, and graphical UI interaction, enabling end-to-end perception, decision-making, and execution from outside the cockpit to inside. cpmGO provides a "native edge-side experience" aligned with a large cloud-based model, supports weak or offline network environments, protects user privacy, and offers rapid response. cpmGO provides a full range of off-the-shelf atomic products, supports personalized customization, and helps intelligent vehicles achieve a smarter, safer, and more efficient interactive experience.

cpmGO's main functions

• Multimodal interactionIt supports multiple interaction methods such as voice, gesture, and graphical UI, realizing "what you see is what you can say".
• Intelligent decision-making and executionIt understands user intent and automatically completes tasks such as navigation and adjusting the air conditioning.
• Privacy protectionData processing is completed locally, without relying on the cloud, ensuring user privacy and security.
• Suitable for weak network environmentsIt supports stable operation in weak network or offline environments, achieving low power consumption and high performance.

cpmGO's technical principles

• End-side model architectureThe MiniCPM edge model is based on wall-facing intelligence. It is optimized for efficient local operation while maintaining strong performance. The model is precisely tailored in terms of function and size to meet the needs of automotive cockpits and OEMs.
• Deep adaptation and inference optimizationIt is deeply adapted to mainstream automotive chips, with joint tuning and inference acceleration to solve the power consumption and computing power consumption issues of automotive chips. Based on optimized algorithms and hardware acceleration, it achieves millisecond-level response speed.
• Multimodal perception and interactionIt combines multiple modalities such as visual, voice, and graphical UI to achieve a more natural and efficient interactive experience. Based on deep learning algorithms, it understands the user's ambiguous intentions and provides precise services.
• End-to-cloud collaborationBased on edge-cloud collaboration, it enables more powerful function expansion and data updates.

Application scenarios of cpmGO

• Smart car usersPursuing a high-tech driving experience, the vehicle system can be conveniently controlled based on intelligent interaction methods such as voice and gestures.
• Privacy-conscious usersUsers who have high requirements for personal data privacy and hope that in-vehicle data will not be leaked to ensure information security.
• People who frequently drive in environments with weak network conditionsFor example, people who frequently drive in tunnels, mountainous areas or remote areas need to use the vehicle's infotainment system normally in environments with weak or no network coverage.
• Home usersIt requires a smart assistant to help take care of children or pets in the car, and to identify and remind children that their seat belts are not fastened or that the pet is in an abnormal state.
• Users who pursue an efficient driving experienceImprove the ease of operation and safety during driving.