Hardware Accelerators

The development of perception and sensor fusion algorithms sees an increasing use of artificial intelligence (AI) methods, such as neural networks. After training and initial validation in the laboratory, these algorithms must be validated and optimized in the vehicle under real conditions and in the context of the entire vehicle using rapid prototyping methods. To run AI, the AUTERA AutoBox can be extended with dedicated hardware accelerators, such as graphics processing units (GPUs) or field-programmable gate arrays (FPGAs). In addition to the rapid prototyping of perception and sensor fusion algorithms, the AUTERA AutoBox also offers new possibilities, such as direct preprocessing of data during data logging to reduce data volumes in a targeted and automated manner based on their relevance as soon as they are recorded.

Currently, the AUTERA AutoBox can be extended with an NVIDIA^® RTX A5000 GPU. The support of additional hardware accelerators is possible on request.