Advancements in Robot Manipulation and Human-Robot Interaction

The field of robotics is moving towards more advanced and nuanced manipulation capabilities, with a focus on dexterity, adaptability, and human-robot interaction. Recent developments have seen the introduction of new robotic hands and end-effectors, such as the ISyHand and MiniBEE, which offer improved dexterity and compactness. Additionally, researchers are exploring new methods for transferring manipulation skills from humans to robots, including the use of trajectory alignment and active perception. These advancements have the potential to significantly improve the capabilities of robots in areas such as manufacturing, healthcare, and rehabilitation. Noteworthy papers include:

  • Best of Sim and Real: Decoupled Visuomotor Manipulation via Learning Control in Simulation and Perception in Real, which presents a decoupled framework for sim-to-real transfer.
  • ISyHand: A Dexterous Multi-finger Robot Hand with an Articulated Palm, which introduces a highly dexterous and low-cost robotic hand.
  • ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations, which presents a framework for transferring human demonstrations to robots using active perception.

Sources

Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform

Best of Sim and Real: Decoupled Visuomotor Manipulation via Learning Control in Simulation and Perception in Real

ISyHand: A Dexterous Multi-finger Robot Hand with an Articulated Palm

From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment

Tele-rehabilitation with online skill transfer and adaptation in $\mathbb{R}^3 \times \mathit{S}^3$

Prometheus: Universal, Open-Source Mocap-Based Teleoperation System with Force Feedback for Dataset Collection in Robot Learning

MiniBEE: A New Form Factor for Compact Bimanual Dexterity

ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations

Built with on top of