Paper Reading AI Learner

A Suitable Hierarchical Framework with Arbitrary Task Dimensions under Unilateral Constraints for physical Human Robot Interaction

2021-09-10 09:09:37
Juan David Munoz-Osorio, Felix Allmendinger

Abstract

In the last years, several hierarchical frameworks have been proposed to deal with highly-redundant robotic systems. Some of that systems are expected to perform multiple tasks and physically to interact with the environment. However, none of the proposed frameworks is able to manage multiple tasks with arbitrary task dimensions, while respecting unilateral constraints at position, velocity, acceleration and force level, and at the same time, to react intuitively to external forces. This work proposes a framework that addresses this problem. The framework is tested in simulation and on a real robot. The experiments on the redundant collaborative industrial robot (KUKA LBR iiwa) demonstrate the advantage of the framework compared to state-of-the-art approaches. The framework reacts intuitively to external forces and is able to limit joint positions, velocities, accelerations and forces.

Abstract (translated)

URL

https://arxiv.org/abs/2109.04743

PDF

https://arxiv.org/pdf/2109.04743.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