Overview

Robotic control turns sensor readings and task goals into actions, from steering mobile robots to coordinating humanoid bodies and handling delicate contact. Methods range from feedback control, inverse kinematics, and model predictive control to reinforcement learning, imitation learning, and vision-language-action policies. Current work often combines these approaches, adding force or tactile feedback, safety constraints, and sim-to-real adaptation to improve performance on manipulation, locomotion, and human-robot interaction tasks. A central challenge is achieving safe, stable behavior that generalizes to unfamiliar conditions while meeting real-time limits and retaining task performance.

Latest papers

CardsList

631 papers51 papers in the last four weeks, down 53% on the four weeks before. 0.4% of all new papers.

  1. A Tutorial on Gaussian Process Learning-based Model Predictive Control

    Apr 2, 2024Jie Wang, Youmin ZhangModel Predictive ControlRobotic Control