The most cutting-edge robots seem to be those that can learn directly from the organisms they are modelled after, as seen in Laikago, the machine learning robotic dog. You might have seen a version of Laikago on Youtube; its design is reminiscent of a dog, and as prances on its tiny footpads, it seems more realistic than most robots. Instead of coding the “mechanical quadruped’s” movement line by line for each small movement, researchers at Boston Dynamic turned to machine learning to teach Laikago how to learn from imitation as to how to move better, and more realistically. Researchers gathered motion-capture videos of puppies walking, playing, even chasing their own tails and translated their movements into algorithms that they could then “feed” to the robotic docs. These “reinforcement learning algorithms” give Laikago the means to figure out basic movements but also refine its gate over time. The researchers are also teaching Laikago to respond to real-life environments, both in terms of tweaking the physical environment and adjusting its response to new environments. Researcher Jason Peng says that the diversity of environments means that Laikago will hopefully be able to learn and adapt to its surroundings in the real world. Boston Dynamics has been working on this project for almost ten years, with some support from DARPA, which could apply a robotic dog in conflict zones to delivers supplies or help soldiers, though that reality is still far off. There are questions of whether this robotic dog will be co-opted for military defence, but that is not unique to this technology; rather, innovative research can often pique the interest of defence officials and raises questions about the ethical issues that arise with military interaction in technology development.
Bloss, Richard. “Robot walks on all four legs and carries a heavy load.” Industrial Robot: An International Journal (2012)
Bloss, Richard. “Robot walks on all four legs and carries a heavy load.” Industrial Robot: An International Journal (2012).
Murphy, Michael P., Aaron Saunders, Cassie Moreira, Alfred A. Rizzi, and Marc Raibert. “The little dog robot.” The International Journal of Robotics Research 30, no. 2 (2011): 145-149
Simon, Matt. “How a real dog taught a robot dog how to walk.” Wied, April 3, 2020. https://www.wired.com/story/how-a-real-dog-taught-a-robot-dog-to-walk/?bxid=5be9eedf3f92a404692828a9&cndid=48470981&esrc=bounceX&source=EDT_WIR_NEWSLETTER_0_DAILY_ZZ&utm_brand=wired&utm_campaign=aud-dev&utm_mailing=WIR_Daily_040520&utm_medium=email&utm_source=nl&utm_term=list2_p2
Categories
Artificial Intelligence, Artificial Life, Ecological Modelling, Monitoring
Air Pollution Robot
The dangers of air pollution to human health are well documented, though the traditional methodology of collecting and reporting on sample lags behind the need to keep abreast and regulate air pollution in a meaningful amount of time. The use of drones and robots have been identified by researchers as resources that can be tweaked […]
Artificial Life, Biodiversity, Climate Change, Ecological Monitoring, Industry/Natural Commodities, Lifestyle, Monitoring
Telematic Rivers
Erica Kermani’s artwork seeks to answer a central question: if rivers were seeing an equal, living entity, would humans take issues like climate change threatening them more seriously? In his year-long art exhibition in 2017, Kermani, in collaboration with Diana Salcedo & Jeana Chesnik, created a new forum of interaction between humans and rivers to […]
Climate Change, Ecological Monitoring, Lifestyle, Monitoring, Pollution, Visual Technologies
Co-occupied Boundaries
Art is easily found in nature but rarely is what considered art today inherently natural. The concept of co-occupied mediums that serve to be both functional for nature and aesthetically pleasing to people is being actively explored by Asya Ilgun and Phil Ayres, from the CITAstudio at The Royal Danish Academy of Fine Arts. In […]
Climate Change, Ecological Monitoring, Lifestyle, Monitoring, Pollution, Visual Technologies