Brain Computer Interface Robotic Co-Workers: Defective Part Picking System

2018 ◽  
Author(s):  
Yao Li ◽  
Thenkurussi Kesavadas
Keyword(s):  
Direct Instruction ◽  
Human Subject ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Human Operator ◽  
Human Being ◽  
Unstructured Environment ◽  
Human Operators ◽  
Application Fields ◽  
Picking System

Industrial robotic co-workers are robots that can work with human being in an unstructured environment. Such robots, must be able to assist human operators in a seamless way without receiving specific instructions. Robotic co-workers can open entirely new application fields in manufacturing as demonstrated in this paper. We designed such an industrial co-robot to pick up defective parts by simply monitoring a human operator directly through a brain computer interface (BCI). By constantly monitoring the operator using BCI sensors, the robotic co-worker can sense when an operator notices a defective part and then moves to remove the part from a moving conveyor with no direct instruction from the operator. The robot, equipped with an RGB camera, recognizes the part, tracks the position and generates accurate motion plan. We demonstrated the system using a human subject study.

SSVEP-based Brain-computer Interface for Part-picking Robotic Co-worker

2021 ◽  
pp. 1-13
Author(s):  
Yao Li ◽  
T. Kesavadas
Keyword(s):  
Human Subject ◽  
Visual Evoked Potential ◽  
Evoked Potential ◽  
Brain Computer Interface ◽  
Industrial Robots ◽  
Computer Interface ◽  
Human Cognition ◽  
Grasp Planning ◽  
Planning Algorithm

Abstract One of the expectations for the next generation of industrial robots is to work collaboratively with humans as robotic co-workers. Robotic co-workers must be able to communicate with human collaborators intelligently and seamlessly. However, industrial robots in prevalence are not good at understanding human intentions and decisions. We demonstrate a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) which can directly deliver human cognition to robots through a headset. The BCI is applied to a part-picking robot and sends decisions to the robot while operators visually inspecting the quality of parts. The BCI is verified through a human subject study. In the study, a camera by the side of the conveyor takes photos of each part and presents it to the operator automatically. When the operator looks at the photo, the electroencephalography (EEG) is collected through BCI. The inspection decision is extracted through SSVEPs in EEG. When a defective part is identified by the operator, the signal is communicated to the robot which locates the defective part through a second camera and removes it from the conveyor. The robot can grasp various part with our grasp planning algorithm (2FRG). We have developed a CNN-CCA model for SSVEP extraction. The model is trained on a dataset collected in our offline experiment. Our approach outperforms the existing CCA, CCA-SVM, and PSD-SVM models. The CNN-CCA is further validated in an online experiment that achieves 93% accuracy in identifying and removing a defective part.

Welding Robotic Co-Worker Using Brain Computer Interface

2018 ◽  
Author(s):  
Yao Li ◽  
Thenkurussi Kesavadas
Keyword(s):  
Human Subject ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Simulation Environment ◽  
Welding Simulation ◽  
Manufacturing Enterprises ◽  
Low Volume ◽  
Industrial Part ◽  
The Way

Robotic co-workers are an emerging generation of physical robots promises to transform manufacturing with its ability to communicate and collaborate, both robot-to-robot and robot-to-human, opening the way to greater innovation and productivity. We designed a welding robotic co-worker which observes industrial part, searches welding seams, plans welding trajectory, and simulates welding result automatically. It largely benefits small and medium-sized manufacturing enterprises (SMEs) by allowing manufacturers handle low-volume orders without re-programming. As a co-worker, the robot communicates with its operator though brain computer interface (BCI) as well as guarantees the operator’s safety. We demonstrated the performance of this robot using a human subject study in welding simulation environment.

Simultaneous Classification of Multiple Motor Imagery and P300 for Increase in Output Information of Brain-computer Interface

2013 ◽  
Vol 133 (3) ◽  
pp. 635-641
Author(s):  
Genzo Naito ◽  
Lui Yoshida ◽  
Takashi Numata ◽  
Yutaro Ogawa ◽  
Kiyoshi Kotani ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Output Information

NON-INVASIVE BCI METHOD: EEG - ELECTROENCEPHALOGRAPHY

2019 ◽  
pp. 139-145
Author(s):  
Selma Büyükgöze
Keyword(s):  
Brain Computer Interface ◽  
Computer Interface ◽  
Electrode Placement ◽  
Eeg Signals ◽  
Non Invasive ◽  
Brain Signals ◽  
Brain States ◽  
The Brain

Brain Computer Interface consists of hardware and software that convert brain signals into action. It changes the nerves, muscles, and movements they produce with electro-physiological signs. The BCI cannot read the brain and decipher the thought in general. The BCI can only identify and classify specific patterns of activity in ongoing brain signals associated with specific tasks or events. EEG is the most commonly used non-invasive BCI method as it can be obtained easily compared to other methods. In this study; It will be given how EEG signals are obtained from the scalp, with which waves these frequencies are named and in which brain states these waves occur. 10-20 electrode placement plan for EEG to be placed on the scalp will be shown.

Sign in / Sign up

Export Citation Format

Share Document