Advances in Human-Robot Interaction and Control

The field of human-robot interaction and control is moving towards more intuitive and efficient methods for non-expert users to operate and program robots. Researchers are focusing on developing innovative solutions to improve the usability of robots, such as optimizing force signals from human demonstrations and estimating payload inertial parameters without dedicated calibration. Whole-body geometric calibration of humanoid robots is also being explored, with novel methods being proposed to simplify this complex task. Additionally, the development of advanced control formulations, such as inverse dynamics whole-body control and passivity-based whole-body control, is being experimentally compared to improve the performance and robustness of humanoid robots. Notable papers in this area include:

  • Estimation of Payload Inertial Parameters from Human Demonstrations by Hand Guiding, which proposes a method to estimate payload inertial parameters without dedicated calibration.
  • Humanoid Robot Whole-body Geometric Calibration with Embedded Sensors and a Single Plane, which presents a novel method for whole-body geometric calibration of humanoid robots using a single plane and embedded sensors.

Sources

Improving Low-Cost Teleoperation: Augmenting GELLO with Force

Estimation of Payload Inertial Parameters from Human Demonstrations by Hand Guiding

Optimizing Force Signals from Human Demonstrations of In-Contact Motions

Humanoid Robot Whole-body Geometric Calibration with Embedded Sensors and a Single Plane

Experimental Comparison of Whole-Body Control Formulations for Humanoid Robots in Task Acceleration and Task Force Spaces

Built with on top of