Harvard University
Cambridge, MA, USA
Position Description
Project
Deep learning plays an essential role in the operation of an autonomous vehicle (AV), allowing for automated detection, prediction, mapping, and planning. During the vehicle’s operation, data is obtained through a myriad of sensors in an AV—including RADAR, LIDAR, cameras, and other advanced driver assistance systems (ADAS) sensors. These sensors generate a vast amount of data concurrently, which need real-time processing (latency-bound throughput) for vehicle safety. A crucial challenge meeting this requirement is the simultaneous need for low-power consumption.
The main objective of the project is to develop a complete end-to-end high-performance DNN system for on-premise computing applications—mainly for a SWaP-constrained AV—using hybrid electro-photonic accelerators. We propose to design and prototype a complete electro-photonic computing (EPiC) system (CPUs + accelerators), integrate it with the...