Mental or Cognitive fatigue (CF) is the exhaustion of neurological system brought on by prolonged cognitive tasks. It causes performance to decline in day-to-day life. Throughout this paper, we present an experimental setup where artificially induce participants. During process, collected electroencephalogram (EEG) signals from subjects that participated experiment. The goal study detect presence absence fatigue. Our proposed solution was able classify with accuracy 88.17%.

Cognitive Fatigue (CF) is the decline in cognitive abilities due to prolonged exposure mentally demanding tasks. In this paper, we used gait cycle analysis, a biometric method related human locomotion identify fatigue individuals. The proposed system paper takes two asynchronous videos of individuals classify if they are cognitively fatigued or not. We leverage pose estimation library OpenPose, extract body keypoints from frames videos. To capture spatial and temporal information cycle,...

This paper describes a novel teleoperation interface system to program industrial robotic arms. The demonstrates the potential create programmable that enables users with no prior knowledge of robotics safely mechanical manipulators use Virtual Reality and Leap Motion Controller. takes full advantage navigate virtual workspace robot was created through kinematic properties real robot. implementation application deemed possible by interfacing Unity Engine Barrett WAM arm. Preliminary...

There is a recent trend of research and applications Cyber-Physical Systems (CPS) in manufacturing to enhance human-robot collaboration production. In this paper, we propose CPS framework for personalized Human-Robot Collaboration Training promote safe environments. We human-centric approach that focuses on multimodal human behavior monitoring assessment, worker safety enable training tasks. present the architecture our proposed system, experimental testbed methods physiological sensing,...

This paper describes a novel system that can demonstrate the potential to track and estimate torques affect human arm of an individual performs rehabilitation exercises with use Kinect v2. The focuses on eliminating jerky motions captured by incorporation robotic mechanics methodologies have been applied in field mechanical design. In order achieve this results, takes full advantage dynamic kinematic formulas describe motion rigid bodies. Lastly, simulation experiment is depicted results system.

Upper-limb robotic rehabilitation systems should inform the therapists for their patients status. Such therapy must be developed carefully by taking into consideration real life uncertainties that associate with sensor error. In our paper, we describe a system which is composed of depth camera tracks motion upper limb, and manipulator challenges patient repetitive exercises. The goal this study to propose analysis improves readings camera, through use kinematic model describes human arm....

This article presents a method for extracting high-level semantic information through successful landmark detection using 2D RGB images. In particular, the focus is placed on presence of particular labels (open path, humans, staircase, doorways, obstacles) in encountered scene, which can be fundamental source enhancing scene understanding and paving path towards safe navigation mobile unit. Experiments are conducted manual wheelchair to gather image instances from four indoor academic...

This paper describes a novel shared control teleoperation framework for mobile robots that utilizes Control Barrier Functions (CBFs) as filtering mechanism to prevent human operator from making dangerous actions. The proposed demonstrates the potential create CBF controller enables users with no prior knowledge of robotics safely tele-navigate limited situational awareness. As formal methods, we utilize hand-crafted CBF, which acts repulsive field describe unsafe regions withing robot's...

We propose a dual-stream, semi-supervised, attention-based approach that employs feature fusion of RGB and Laser Range Finder (LRF) modalities. Our method lever-ages the strength two powerful transformer-based networks, i.e. Vision Transformer (ViT) SegFormer, along with LRF information, to adequately predict whether scene encountered in image is safe for robot traverse. Towards this effort, we introduce an automated labelling system profiting from combination raw velocity readings laser...

We propose a novel system to track human lower-body motion as part of larger movement assessment for clinical evaluation. Our combines multiple wearable Inertial Measurement Unit (IMU) sensors and single external RGB-D camera. use factor graph with Sliding Window Filter (SWF) formulation that merges 2-D joint data extracted from the RGB images via Deep Neural Network, raw depth information, IMU gyroscope readings, estimated foot contacts accelerometer data. For system, we an articulated...

We present a method for binary (go/no-go) indoors traversability estimation from 2D images. Our exploits the power of pre-trained Vision Transformer (ViT) which we fine-tune on our own dataset. conduct experiments using mobile robotic platform to gather image data. fine-tuning approach includes use en route towards developing semi-supervised deep learning technique enhance indoor scenarios where only small amount data is available. evaluate accuracy and generalization against...

Considerable amount of research is being carried out in robot based rehabilitation techniques. One the main focus when building a smart system its ability to adapt on user experience. In this poster we attempt build such that recognizes strain/ negative emotions from participants facial expression and adjusts force exerted. The accuracy recognize assessed as whole estimated through surveys.

In this paper, we present a novel method to learn end-to-end visuomotor policies for robotic manipulators. The computes state-action mappings in supervised learning manner from video demonstrations and robot trajectories. We show that the learns perform different tasks by associating image features with corresponding movement primitives of grasp poses. To evaluate effectiveness proposed method, conduct experiments PR2 simulation environment. purpose these is system's ability manipulation tasks.

Lego construction task paradigms are utilized in order to develop logico-mathematical abilities through visuospatial memory. This study aims assess the relationship between cognition and performance a simulated industrial environment by employing humanoid robots stated metrics. system proposes smart vocational assessment intervention service that assesses worker's needs for training rehabilitation an experimental setup simulates factory. The proposed approach collects analyzes multi-sensing...

A considerable amount of research in the field human-robot interaction has shown that a human teacher can be an integral component during learning process robot. In this paper, we propose framework is based on from demonstration at trajectory level. Specifically, illustrate scenario where Sawyer Robotic Arm must learn to pick and place specific object according teacher. The purpose experiment facilitate effectiveness proposed method.

It is generally accepted in the field of human-robot interaction (HRI) that role a human teacher critical for robot environmental adaptation. As such, ability to adapt novel environment based on capabilities teacher. In this paper, we propose metric robots evaluate quality We illustrate scenario where Sawyer Robotic Arm must learn grasp cup according demonstration ofa good and bad