Paper Reading AI Learner

Millimeter-wave Foresight Sensing for Safety and Resilience in Autonomous Operations

2022-03-24 11:25:24
Daniel Mitchell, Jamie Blanche, Sam T. Harper, Theodore Lim, Valentin Robu, Ikuo Yamamoto, David Flynn

Abstract

Robotic platforms are highly programmable, scalable and versatile to complete several tasks including Inspection, Maintenance and Repair (IMR). Mobile robotics offer reduced restrictions in operating environments, resulting in greater flexibility; operation at height, dangerous areas and repetitive tasks. Cyber physical infrastructures have been identified by the UK Robotics Growth Partnership as a key enabler in how we utilize and interact with sensors and machines via the virtual and physical worlds. Cyber Physical Systems (CPS) allow for robotics and artificial intelligence to adapt and repurpose at pace, allowing for the addressment of new challenges in CPS. A challenge exists within robotics to secure an effective partnership in a wide range of areas which include shared workspaces and Beyond Visual Line of Sight (BVLOS). Robotic manipulation abilities have improved a robots accessibility via the ability to open doorways, however, challenges exist in how a robot decides if it is safe to move into a new workspace. Current sensing methods are limited to line of sight and are unable to capture data beyond doorways or walls, therefore, a robot is unable to sense if it is safe to open a door. Another limitation exists as robots are unable to detect if a human is within a shared workspace. Therefore, if a human is detected, extended safety precautions can be taken to ensure the safe autonomous operation of a robot. These challenges are represented as safety, trust and resilience, inhibiting the successful advancement of CPS. This paper evaluates the use of frequency modulated continuous wave radar sensing for human detection and through-wall detection to increase situational awareness. The results validate the use of the sensor to detect the difference between a person and infrastructure, and increased situational awareness for navigation via foresight monitoring through walls.

Abstract (translated)

URL

https://arxiv.org/abs/2203.12987

PDF

https://arxiv.org/pdf/2203.12987.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