Consider this scene from the 2014 movie, Ex Machina: A young nerd, Caleb, is in a weak room with a lightly dressed femmebot, Kyoko. Nathan, a brilliant robot, stumbles drunk and suddenly tells Caleb to dance with Kyoko-bot. To kick things off, Nathan presses a panel on the wall, and the room lights suddenly change to an ominous red, while Oliver Cheatham’s classic disco “Get Down Saturday Night” begins to sing. Kyoko – who seems to have done this before – starts dancing without words, and Nathan joins his robotic creation in a complicated and choreographed piece of pelvic thrust. The scene suggests that Nathan soaked his robot creation with disco features, but how did he choreograph the dance on Kyoko and why?
Ex Machina he may not answer these questions, but the scene gestures to an emerging area of robotic research: choreography. Ultimately, choreography is making decisions about how bodies move through space and time. In the dance sense, choreography means articulating movement patterns for a given context, generally optimizing expressiveness instead of utility. Being in tune with the choreography of the world means being aware of how people move and interact in complex, technology-laden environments. Choreo-robots (ie choreographers who work choreographically) believe that incorporating dancing gestures into mechanical behaviors will make robots look less like industrial fireworks and, instead, more lively, more empathetic and more attentive. Such an interdisciplinary intervention could make it easier for robots to be around and work with them – not least, given their proliferation in consumer, medical and military contexts.
While the concern for body movement is central to both dance and robotics, historically, disciplines have rarely overlapped. On the one hand, the Western tradition of dance has been known to maintain a generally anti-intellectual tradition that poses great challenges to those interested in interdisciplinary research. George Balanchine, the acclaimed founder of the New York City Ballet, told the famous dancers, “Don’t think, darling, do it.” As a result of this type of culture, the stereotype of dancers as servile bodies that are better seen than heard, unfortunately, has long been calcified. Meanwhile, the field of computer science – and extension robotics – demonstrates comparable, albeit distinct, body problems. As sociologists Simone Browne, Ruha Benjamin, and others have shown, there is a long history of emerging technologies that throw human bodies away as mere objects of surveillance and speculation. The result has been the perpetuation of racist, pseudo-scientific practices such as phrenology, mood reading software and AI, which claim to know if you are gay by the appearance of your face. The body is a problem for computer scientists; and the overwhelming response of the field was technical “solutions” that try to read bodies without significant feedback from their owners. That is, the insistence that bodies be seen, but not heard.
Despite the historical gap, it may not be too large to consider robots as choreographers of a specialized type and to believe that the integration of choreography and robotics could benefit both areas. Usually, the movement of robots is not studied for meaning and intentionality as it is for dancers, but robots and choreographers are concerned with the same fundamental concerns: articulation, extension, strength, form, effort, effort and power. “Robotists and choreographers aim to do the same thing: to understand and convey subtle choices in motion in a given context,” writes Amy Laviers, a certified motion analyst and founder of the robotics, automation and dance (RAD) laboratory in a recent National Paper funded by the Science Foundation. When robots work choreographically to determine the behaviors of robots, they make decisions about how human and inhuman bodies move expressly in the intimate context of the other. This is distinct from the utilitarian parameters that tend to govern most robotic research, in which optimization reigns (does the robot do its job?) And what it means to move a device or make someone feel it has no apparent consequences.
Madeline Gannon, founder of the AtonAton research studio, leads the field of exploring robot expressiveness. Its installation commissioned by the World Economic Forum, hands, exemplifies the possibilities of choreo-robotics both in its brilliant choreographic consideration and in its innovative mechanical engineering facts. The piece consists of 10 robot arms displayed behind a transparent panel, each strong and brightly lit. The arms remind us of the design of the production of technical-dystopian films as well Ghost in the Shell. Such robotic arms are designed to perform repetitive work and are commonly used for utility purposes, such as painting the car chassis. But when hands is activated, the arms of his robot do not incorporate any of the expected and repetitive rhythms of the assembly line, but instead appear alive, each moving individually to interact animatedly with its surroundings. Depth sensors installed at the base of the robot’s platform track the movement of human observers through space, measuring distances and responding iteratively to them. This tracking data is distributed throughout the robotic system, functioning as a common view for all robots. When passers-by move close enough to any arm of the robot, it will “look” closer by tilting its “head” in the direction of the stimuli and then move closer to engage. Such simple, subtle gestures have been used by puppets for millennia to soak objects with animus. Here it has the cumulative effect of doing hands they seem curious and very vivid. These tiny choreographies give the appearance of personality and intelligence. These represent the functional difference between a random row of industrial robots and the coordinated movements of the intelligent behavior of the packets.