Tianyi Zhang, Haowu Luo, Ning Liu, Feiyan Min, Zhixin Liang and Gao Wang
As the demand for human–robot collaboration in manufacturing applications grows, the necessity for collision detection functions in robots becomes increasingly paramount for…
Abstract
Purpose
As the demand for human–robot collaboration in manufacturing applications grows, the necessity for collision detection functions in robots becomes increasingly paramount for safety. Hence, this paper aims to improve the existing method to achieve efficient, accurate and sensitive robot collision detection.
Design/methodology/approach
The external torque is estimated by momentum observers based on the robot dynamics model. Because the state of the joints is more accessible to distinguish under the action of the suppression operator proposed in this paper, the mutated external torque caused by joint reversal can be accurately attenuated. Finally, time series analysis (TSA) methods can continuously generate dynamic thresholds based on external torques.
Findings
Compared with the collision detection method based only on TSA, the invalid time of the proposed method is less during joint reversal. Although the soft-collision detection accuracy of this method is lower than that of the symmetric threshold method, it is superior in terms of detection delay and has a higher hard-collision detection accuracy.
Originality/value
Owing to the mutated external torque caused by joint reversal, which seriously affects the stability of time series models, the collision detection method based only on TSA cannot detect continuously. The consequences are disastrous if the robot collides with people or the environment during joint reversal. After multiple experimental verifications, the proposed method still exhibits detection capabilities during joint reversal and can implement real-time collision detection. Therefore, it is suitable for various engineering applications.
Details
Keywords
Nowadays, more and more brands are developing their own virtual ambassadors for interactive communication and marketing with consumers. Exploring the interactive effectiveness of…
Abstract
Purpose
Nowadays, more and more brands are developing their own virtual ambassadors for interactive communication and marketing with consumers. Exploring the interactive effectiveness of virtual brand ambassadors on consumer behavior is crucial to understanding the interactions between brands, virtual ambassadors and consumers as well as further increasing consumer engagement in AI-mediated interactive marketing.
Design/methodology/approach
This study investigated different interactive effects of virtual ambassadors on consumer behavior in terms of virtual ambassadors’ anthropomorphism, virtual experience and consumer behavior through a mixed method of questionnaires and semi-structured interviews.
Findings
The results indicate that consumers’ sharing, reviewing and purchasing behavior is significantly and positively influenced by virtual ambassadors’ anthropomorphism and virtual experience. In addition, specific anthropomorphic features and virtual experiences were discussed in detail.
Originality/value
This study helps brands develop and manage their virtual ambassadors and consumers in AI-mediated interactive marketing and communication.