Detecting Human Motion Intention during pHRI Using Artificial Neural Networks Trained by EMG Signals

Abstract

With the recent advances in cobot (collaborative robot) technology, we can now work with a robot side by side in manufacturing environments. The collaboration between human and cobot can be enhanced by detecting the intentions of human to make the production more flexible and effective in future factories. In this regard, interpreting human intention and then adjusting the controller of cobot accordingly to assist human is a core challenge in physical human-robot interaction (pHRI). In this study, we propose a classifier based on Artificial Neural Networks (ANN) that predicts intended direction of human movement by utilizing electromyography (EMG) signals acquired from human arm muscles. We employ this classifier in an admittance control architecture to constrain human arm motion to the intended direction and prevent undesired movements along other directions. The proposed classifier and the control architecture have been validated through a path following task by utilizing a KUKA LBR iiwa 7 R800 cobot. The results of our experimental study with 6 participants show that the proposed architecture provides an effective assistance to human during the execution of task and reduces undesired motion errors, while not sacrificing from the task completion time.

EMG Characterization and Processing in Production Engineering

“…Some examples of the collaborative activities analyzed are supervisory control, fatigue adaptation, hand-over activities, and motion prediction. Artificial intelligence processing techniques are widely used to classify information obtained from EMG acquisition systems, which can be combined with ECG signals [ 54 ] or augmented reality kits [ 114 ]. The analyzed studies are carried out in simulated environments.…”

“…Although the system does not reach 100% reliability, it is highly effective and adds advantages to the process, allowing the transfer to be controlled naturally and even accepting or rejecting the object that is being delivered to the user. Techniques of human motion prediction are also analyzed by Tortora et al [ 113 ], introducing a real-time classification system with a 94.3% ± 2.9% of accuracy for human–machine industrial systems, and Sirintuna et al [ 114 ], developing a collaboration system adapted to path following tasks.…”

Adaptive Human Force Scaling via Admittance Control for Physical Human-Robot Interaction

“…Tsumugiwa et al [14] and Rahman et al [15] estimated human arm stiffness and adjusted the admittance damping on-the-fly in proportion to the estimated stiffness and depending on some velocity thresholds. In [16]- [18], human intention was estimated based on the measurement of muscle activation of human arm via EMG sensors to provide effective assistance in co-manipulation tasks. Keemink et al [19] proposed a position-dependent admittance damping for co-manipulation of heavy objects and investigated its effect on the accuracy of object positioning, reaching time, and magnitude of force applied by human.…”

“…Also, the estimation of human arm stiffness in [14] and [15] requires additional computational effort, which is not trivial if pHRI task is complex. Similarly, utilizing EMG sensors for intent detection is not very practical [16]- [18], since it requires to attach them to user's arm.…”

A Cooperative Shared Control Scheme Based on Intention Recognition for Flexible Assembly Manufacturing

“…Generally, electromyography (EMG) signals can be utilized to profile the interactions between a human and a robot, which, in a sense, reflect the human operation intention (Peternel et al, 2018 ). For example, Sirintuna et al ( 2020 ) utilized EMG signals to detect human motion by collaborating with a KUKA LBR cobot. Detecting the human intention in cooperative telemanipulation is challenging and an augmentation algorithm of haptic intention was presented by Panzirsch et al ( 2017 ) to help the human operators in a cooperation task.…”