Grasping with a Human Touch: Robots Learn to Handle Objects Like We Do

New research demonstrates how reinforcement learning, guided by human grasping patterns, enables robots to perform complex object manipulation tasks with greater dexterity and intention.





![The research extends closed-loop inverse kinematics (CLIK) to infinite dimensions, enabling task-solving reasoning across the entirety of a soft robot’s shape, and overcomes the practical difficulty of obtaining analytical Jacobians for such models through the implementation of a neural network embedding learned from simulations [latex] \mathbb{J} [/latex].](https://arxiv.org/html/2602.18655v1/fig/abstract-no-background.png)