This paper proposes a high-speed low-cost VLSI system capable of on-chip online learning for classifying address-event representation (AER) streams from dynamic vision sensor (DVS) retina chips. The proposed system executes a lightweight statistic algorithm based on simple binary features extracted from AER streams and a Random Ferns classifier to classify these features. The proposed system’s characteristics of multi-level pipelines and parallel processing circuits achieves a high throughput up to 1 spike event per clock cycle for AER data processing. Thanks to the nature of the lightweight algorithm, our hardware system is realized in a low-cost memory-centric paradigm. In addition, the system is capable of on-chip online learning to flexibly adapt to different in-situ application scenarios. The extra overheads for on-chip learning in terms of time and resource consumption are quite low, as the training procedure of the Random Ferns is quite simple, requiring few auxiliary learning circuits. An FPGA prototype of the proposed VLSI system was implemented with 9.5~96.7% memory consumption and <11% computational and logic resources on a Xilinx Zynq-7045 chip platform. It was running at a clock frequency of 100 MHz and achieved a peak processing throughput up to 100 Meps (Mega events per second), with an estimated power consumption of 690 mW leading to a high energy efficiency of 145 Meps/W or 145 event/μJ. We tested the prototype system on MNIST-DVS, Poker-DVS, and Posture-DVS datasets, and obtained classification accuracies of 77.9%, 99.4% and 99.3%, respectively. Compared to prior works, our VLSI system achieves higher processing speeds, higher computing efficiency, comparable accuracy, and lower resource costs.
Aquatic unmanned aerial vehicles (AquaUAV) have aroused much attention from researchers, though no fully-featured aerial-aquatic UAV exists so far. The assistance of webbed foot hydroplaning can accomplish rapid takeoff of a cormorant. A significant impact force and moment can be generated due to the webbed foot propulsion in the water-to-air transition. However, the change law of force and moment experienced by the cormorant during takeoff has not been captured. Based on previous achievements in the biological investigation, we developed a biomimetic prototype with curve fitting model and parameter optimization to attain specific movements to imitate cormorant's hydroplaning strategy. The bionic webbed foot considers the elastic mechanics, and the forepart is regarded as flexible material for fluid-structure interaction (FSI). Dynamic process of rapid takeoff in the aspects of flow characteristics and mechanical properties can be estimated by computational fluid dynamics (CFD) in our proposed FSI model, which establishes a foundation for further applications in the design of the assisted propulsion system of aerialaquatic UAV. INDEX TERMS Biomimetics, computational biophysics, fluid dynamics, coupled mode analysis, military aircraft.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.