Machine Gesture Design
Boston Dynamics has just released a new video testing their four-legged robot SpotMini, where one helped another by opening a door. This video immediately went viralÂ and received more than 8 million views over the course of two weeks. It also sparked discussion among us in the robotics cluster: one commented on the similarity of its movement to a spider, and most of us felt uneasy watching the video.
Many commentators on the internet compared SpotMini to a dog, however, for anyone who has seen a dog in skeleton form, they would have noticed a difference in the back leg structure. For the majority of vertebrate mammals, like cats and dogs, the back legs are often bent forward. All the legs for SpotMini are engineered in such a way that is similar to insects, which might have been more effective for its function, but left me feeling deeply unsettled. I am not sure if it was Boston Dynamics’ intention to recall my cringing memory of reading The Metamorphosis by Franz Kafka; if not, perhaps they could have placed more consideration in the design of the machine gesture.
Goals for the week:
- Clarify theoretical vision
- Test out material for new machine gesture
This week has proven to be quite a struggle as I consider the possibility of enhancing the Machine Theatre experience through redesigning the machine gesture. My current prototype utilises an XY plotter, which yields a few limitations: all its movements are restricted in a two-dimensional plane, its gesture only communicate symbolically, and it does not embody a life-like attribute.
There are two potential directions I could see taking my design process:
- Continuing “the imitation machine” concept I initiated previously in my theory paper, I am interested in how the machine could replicate traits that are unique to homo sapien and how eventually that will revolutionalize human-machine relationship. Some of the special characteristicsÂ include the use of tools, autonomous goals, collaborative behaviours, development of social language, etc.
- Utilising new methods like AI, create tech art that is expressed in a physical way. Since we cannot recreate nature, perhaps we can make use of emerging technologies to create the “supernatural”. This will enable the viewers to experience the emotion of awe as they witness these phenomena.
I am especially excited to incorporateÂ new technologies in art, which relates to whatÂ Paul ValeÌry has poignantly expressed inÂ PIEÌ€CES SUR L’ART (1934):
“Our fine arts were developed, their types and uses were established, in times very different from the present, by men whose power of action upon things was insignificant in comparison with ours. But the amazing growth of our techniques, the adaptability and precision they have attained, the ideas and habits they are creating, make it a certainty that profound changes are impending in the ancient craft of the Beautiful. In all the arts there is a physical component which can no longer be considered or treated as it used to be, which cannot remain unaffected by our modern knowledge and power. For the last twenty years neither matter nor space nor time has been what it was from time immemorial. We must expect great innovations to transform the entire technique of the arts, thereby affecting artistic invention itself and perhaps even bringing about an amazing change in our very notion of art.”
I would love to become part of this movement as the technology today swiftly develops.Â With every improvement, it has given artists new toys to play with, opening up new possibilities to achieve visions that were unimaginable for the previous generation. The recent development in artificial intelligence has enabled bizarre but awe-inspiring work like the computer vision simulated by Google DeepDream, or the poetry-writing word.camera by Ross Goodwin. However, a major problem I have with art like these is the lack of a physical form. I hope that my final design would not merely exist in digital format butÂ retain a tangible outcome, dynamic in motion.
Extending my research in magnetic properties, I have tested the magnets in a few novel conditions.Â These experiments will inform the design of a new kind of machine gesture that will eventually be presented in a theatrical installation.
In recent years, surface electromyography (sEMG) signals have been increasingly used in pattern recognition and rehabilitation. In this paper, a real-time hand gesture recognition model using sEMG is proposed. We use an armband to acquire sEMG signals and apply a sliding window approach to segment the data in extracting features. A feedforward artificial neural network (ANN) is founded and trained by the training dataset. A test method is used in which the gesture will be recognized when recognized label times reach the threshold of activation times by the ANN classifier. In the experiment, we collected real sEMG data from twelve subjects and used a set of five gestures from each subject to evaluate our model, with an average recognition rate of 98.7% and an average response time of 227.76 ms, which is only one-third of the gesture time. Therefore, the pattern recognition system might be able to recognize a gesture before the gesture is completed.