This article presents a transfer learning (TL) followed by reinforcement learning (RL) algorithm mapped onto a hierarchical embedded memory system to meet the stringent power budgets of autonomous drones. The… Click to show full abstract
This article presents a transfer learning (TL) followed by reinforcement learning (RL) algorithm mapped onto a hierarchical embedded memory system to meet the stringent power budgets of autonomous drones. The power reduction is achieved by 1. TL on meta-environments followed by online RL only on the last few layers of a deep convolutional neural network (CNN) instead of end-to-end (E2E) RL and 2. Mapping of the algorithm onto a memory hierarchy where the pre-trained weights of all the conv layers and the first few fully connected (FC) layers are stored in dense, low standby leakage Spin Transfer Torque (STT) RAM eNVM arrays and the weights of the last few FC layers are stored in the on-die SRAM. This memory hierarchy enables real-time RL as the drone explores unknown territories and the system only reads the weights from eNVM (that are slow and power hungry to write otherwise) for inference and uses the on-die SRAM for low latency training through both write and read of the weights of the last few layers. The proposed system is extensively simulated on a virtual environment and dissipates 83.5% lower energy per image frame as well as 79.4% lower latency as compared to E2E RL without any loss of accuracy. The speed of the drone is improved by a factor of $3\times $ due to higher frame rates as well.
               
Click one of the above tabs to view related content.