[MERL Seminar Series Spring 2026] Is locomotion really that hard… and other musings on the virtues.. скачать в хорошем качестве

[MERL Seminar Series Spring 2026] Is locomotion really that hard… and other musings on the virtues..

[MERL Seminar Series Spring 2026] Is locomotion really that hard… and other musings on the virtues of simplicity Zac Manchester, MIT, presented a talk in the MERL Seminar Series on January 20, 2026. Abstract: For decades, legged locomotion was a challenging research topic in robotics. In the last few years, however, both model-based and reinforcement-learning approaches have not only demonstrated impressive performance in laboratory settings, but are now regularly deployed "in the wild." One surprising feature of these successful controllers is how simple they can be. Meanwhile, Art Bryson’s timeless advice to control engineers, “Be wise – linearize,” seems to be increasingly falling out of fashion and at risk of being forgotten by the next generation of practitioners. This talk will discuss several recent works from my group that try to push the limits of how simple locomotion (and, possibly, manipulation) controllers for general-purpose robots can be from several different viewpoints, while also making connections to state-of-the-art generative AI methods like diffusion policies.