Soft Robotics
Overview
Soft robotics investigates how deformable machines can move, manipulate objects, and assist people while adapting to contact and irregular surroundings. Common designs use pneumatic or hydraulic chambers, tendons, dielectric elastomers, and magnetic or shape-changing structures; models range from Cosserat rods and finite-element methods to learned dynamics. Control approaches include model-predictive control, reinforcement learning, visual servoing, and tactile or proprioceptive feedback, evaluated in tasks such as grasping, locomotion, wearable assistance, and medical navigation. A central challenge is balancing accurate, efficient modeling and control with the changing shapes, hysteresis, manufacturing variation, and sim-to-real gaps that make soft robots adaptable in the first place.
Latest papers
231 papers14 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.