The invention discloses an FPGA
resource scheduling method for automatic driving
perception decision decoupling, and relates to the technical field of automatic driving. The method specifically comprises the following steps of: receiving multi-source heterogeneous sensor data by utilizing a reconfigurable sensory
memory interface module of a dynamic logic area at the front end of an FPGA (
Field Programmable Gate Array), executing time-space synchronization, and performing normalized projection to obtain a driving situation dynamic map data frame; a dual-port cache region is constructed by utilizing a cognitive fusion and
working memory module of FPGA on-
chip high-speed storage resources, and a multi-channel layered space-time
tensor serving as an on-
chip data exchange medium is maintained and refreshed in real time; a cognitive decision module of a rear-end static logic area is used for reading the dynamic map, reasoning is conducted in combination with priori knowledge called by a long-
term memory interface, and a control instruction is generated; the dynamic map is defined as a standardized boundary of
software and hardware interaction, and only a logic circuit of the sensory
memory interface module is refreshed when the configuration of the sensor is changed. The objective of the invention is to realize
perception and decision decoupling through a standardized architecture of a hardware bottom layer and improve the real-time performance and robustness of a
system.