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)

引用 0|浏览4
暂无评分
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