MIT News  March 22, 2021 Unlike rigid robots which operate with compact degrees of freedom, soft robots must reason about an infinite dimensional state space. This continuum state space presents significant challenges when working with a finite set of discrete sensors. Sensor location has a profound downstream impact on the richness of learned models for robotic tasks. Researchers at MIT present a novel representation for co-learning sensor placement and complex tasks. They developed a neural architecture which processes on-board sensor information to learn a salient and sparse selection of placements for optimal task performance. They evaluated their model and learning […]

Science Daily  February 17, 2021 Pneumatically actuated soft robots are controlled with bulky and expensive electromechanical components. Researchers at UC San Diego have created a soft-legged robot using simple pneumatic circuits without any electronic components. Locomotive gaits are produced using ring oscillators composed of soft valves that generate oscillating signals analogous to biological central pattern generator neural circuits, which are acted upon by pneumatic logic components in response to sensor inputs. The robot requires only a constant source of pressurized air to power both control and actuation systems. The circuits generate walking gaits with three degrees of freedom per leg […]