AutoAAI — AI Agents for Optimized Vehicle Assistance
1. Overview
AI Agents for Optimized Vehicle Assistance (AutoAAI) is an RD&I initiative of LISHA at UFSC, along with Stellantis, Intelbras, and ES2 Tech, sponsored by Program MOVER
. The project's main goal is to develop a set of reusable software components that can be integrated into partners' existing infrastructure systems to add value, mainly by leveraging AI Agents for Optimized Vehicle Assistance, integrated into an HMI easily interface clients and mechanics team. Expected outcomes include the AutoAAI software platform, the publication of high-impact scientific papers, and the training of highly qualified human resources, strengthening competitiveness of the automotive industry.
. The project's main goal is to develop a set of reusable software components that can be integrated into partners' existing infrastructure systems to add value, mainly by leveraging AI Agents for Optimized Vehicle Assistance, integrated into an HMI easily interface clients and mechanics team. Expected outcomes include the AutoAAI software platform, the publication of high-impact scientific papers, and the training of highly qualified human resources, strengthening competitiveness of the automotive industry.
1.1. AutoAAI Consortium
The Software/Hardware Integration Lab (LISHA) was founded in 1985 to promote research in the frontiers between hardware and software. Since then, it has dedicated considerable efforts to research in areas such as computer architecture, operating systems, computer networks and the related applications. Currently, the laboratory focuses on innovative techniques and tools to support the development of embedded systems.
was founded in 1985 to promote research in the frontiers between hardware and software. Since then, it has dedicated considerable efforts to research in areas such as computer architecture, operating systems, computer networks and the related applications. Currently, the laboratory focuses on innovative techniques and tools to support the development of embedded systems.
is a constellation of 14 iconic automotive brands. As an automaker partner, Stellantis will provide access to data, vehicles, and technical expertise for the validation of predictive maintenance use cases.
Intelbras S.A is one of the largest technology companies in Brazil, specializing in security, connectivity and energy solutions. Intelbras will support the project integration, ensuring seamless implementation and specialized technical alignment throughout the process.
is one of the largest technology companies in Brazil, specializing in security, connectivity and energy solutions. Intelbras will support the project integration, ensuring seamless implementation and specialized technical alignment throughout the process.
2. AutoAAI Architecture
An overview of the AutoAAI architecture is depicted in Figure 1 and illustrates the major entities that will be developed. These entities also define the project's goals:
- Embedded Monitoring and Pre-Analysis Subsystem: Develop an embedded vehicle monitoring subsystem capable of performing local processing of high-frequency signals, such as vibration, acoustic, and electrical current data, enabling feature extraction, early anomaly detection, and the generation of vehicle health indicators directly on-board.
- Cloud-Based AI Agent and LLM-Enabled HMI Subsystem: Develop a cloud-based AI subsystem that integrates health indicators from embedded devices with historical and contextual data, leveraging advanced predictive models and LLM-based agents to support diagnostics, predictive maintenance, service scheduling, and fleet management.
Fig 1: AutoAAI Architecture Overview.