Intel and Altera team on real-time sensor bridge for edge AI

The collaboration arrives as edge and physical AI systems increasingly require data from different sensors and interfaces to be brought together under strict timing, performance, power and cost constraints. Some applications also need very high bandwidth or flexible form factors where input/output is located away from the compute board, forcing sensor data to be streamed rapidly into memory for the host Intel processor.

Intel and Altera plan to address these challenges through modular reference solutions that combine programmable hardware with a consistent Intel compute and software foundation. The goal is to give OEMs greater flexibility as applications, sensors and workloads evolve, while helping them move more efficiently from prototype to deployment.

The companies plan to apply the collaboration across healthcare, aerospace and defense, and robotics, with reference solutions targeting stringent latency requirements, size, weight and power needs for converged AI and signal-processing workloads, and the complex sensing and real-time processing requirements of intelligent machines.