fig1
Figure 1. Classical admittance control (dashed) vs. DRL-based HRI control (solid). In the classical loop the human force Fh is the input to the fixed law [Equation (1)], whose output is the commanded correction xd; the DRL loop replaces that fixed map with a policy πθ updated from the interaction reward. DRL: Deep reinforcement learning; HRI: human-robot interaction.
