Learning for Microrobot Exploration: Model-based Locomotion, Sparse-robust Navigation, and Low-power Deep Classification
This work addresses the problem of deploying state-of-the-art algorithms on power-limited microrobot platforms, representing incremental improvements in edge-intelligence for autonomous systems.
The paper tackled the challenge of enabling intelligent autonomy for microrobots under severe sensing and computation constraints by improving learning-based methods for locomotion, navigation, and classification, achieving simulated locomotion via model-based reinforcement learning, enhanced navigation with sparse linear detectors and Dynamic Thresholding for FAST Visual Odometry, and a classifier requiring fewer than one million MAC operations.
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.