Paper Reading AI Learner

Cyborg Beetle Achieves Efficient Autonomous Navigation Using Feedback Control

2022-04-28 04:33:11
Huu Duoc Nguyen, Van Than Dung, T. Thang Vo-Doan, Hirotaka Sato

Abstract

Terrestrial cyborg insects, the fusion between ambulatory insects and mountable electronic controller, have been long discussed as potential complements for artificial insect-scaled legged mobile robots. These cyborgs inherit the living insects' amazing locomotory skills, a flexible but robust body structure, a vast collection of sensory organs, and a top-notch central nervous control system, favoring their maneuvers in complex and unstructured terrains, such as post-disaster environments. However, the development of automatic navigation for these terrestrial cyborg insects has not yet been comprehensively studied. The struggle in selecting stimulation parameters for individual insects challenges the attainment of their reliable and accurate navigations. This study demonstrates the implementation of feedback control to overcome this obstacle and provides a detailed look at the navigation control for terrestrial cyborg insects. Herein, a feedback control system is developed to realize the automatic navigation of a darkling beetle. Using a thrust controller for the beetle's acceleration and a proportional controller for its turning motion, the system alters the stimulation command (i.e., left/right turn, forward motion) and its parameters (i.e., frequency) depending on the beetle's instantaneous status. Adjusting the system's control parameters allows the beetle to be reliably and precisely navigated following a predetermined path with a success rate of ~80% and an accuracy of ~10 mm. Moreover, the system allows altering its performance by regulating the control parameters, providing flexibility to navigation applications of terrestrial cyborg insects.

Abstract (translated)

URL

https://arxiv.org/abs/2204.13281

PDF

https://arxiv.org/pdf/2204.13281.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot