Femtosecond laser micromachining can be used to fabricate nitinol living hinges with arbitrary cross-sections while retaining the material's superelastic properties, enabling the development of high-performance millimeter-scale robotic devices.
Neural networks can effectively model the hysteretic kinematic behavior of tendon-actuated continuum robots, outperforming standard feedforward neural networks by capturing temporal dependencies.
This work presents a bio-inspired robotic shoulder with two degrees of freedom that utilizes self-sensing Peano-HASEL actuators, eliminating the need for external sensors and enabling precise closed-loop control of the end-effector position in the task space.
This study proposes a simple and efficient inverse kinematics computation strategy for industrial serial manipulators that considers the joint motion efficiency to provide practical solutions.
Implementation of reinforcement learning in robotic manipulator trajectory planning.
Evolutionary Computation methods outperform brute force in optimizing robotic designs, enhancing efficiency and usability.
Vision-based tactile sensors enhance underactuated fingers' capabilities.
Enhancing step-climbing and reducing vibrations with the Passive Transformable Omni-Ball design.
Scalable robotic solution for military gap crossing using modular robots.
RoboCertProb allows quantitative property specification for probabilistic robotic systems in RoboChart models.