Learning for Microrobot Exploration: Model-based Locomotion, Sparse-robust Navigation, and Low-power Deep Classification
2020 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)(2020)
摘要
Building intelligent autonomous systems at any scale is challenging. The sensing and computation constraints of a microrobot platform make the problems harder. We present improvements to learning-based methods for on-board learning of locomotion, classification, and navigation of microrobots. We show how simulated locomotion can be achieved with model-based reinforcement learning via on-board sensor data distilled into control. Next, we introduce a sparse, linear detector and a Dynamic Thresholding method to FAST Visual Odometry for improved navigation in the noisy regime of mm scale imagery. We end with a new image classifier capable of classification with fewer than one million multiply-and-accumulate (MAC) operations by combining fast downsampling, efficient layer structures and hard activation functions. These are promising steps toward using state-of-the-art algorithms in the power-limited world of edge-intelligence and microrobots.
更多查看译文
关键词
microrobot exploration,model-based locomotion,sparse-robust navigation,low-power deep classification,building intelligent autonomous systems,computation constraints,microrobot platform,learning-based methods,simulated locomotion,model-based reinforcement learning,on-board sensor data,sparse detector,linear detector,Dynamic Thresholding method,FAST Visual Odometry,improved navigation,mm scale imagery,multiply-and-accumulate operations,power-limited world,edge-intelligence
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要