Interactive Imitation Learning of Bimanual Movement Primitives

Research output: Contribution to journalArticleScientificpeer-review


Performing bimanual tasks with dual robotic setups can drastically increase the impact on industrial and daily life applications. However, performing a bimanual task brings many challenges, such as synchronization and coordination of the single-arm policies. This article proposes the safe, interactive movement primitives learning (SIMPLe) algorithm, to teach and correct single or dual arm impedance policies directly from human kinesthetic demonstrations. Moreover, it proposes a novel graph encoding of the policy based on Gaussian process regression where the single-arm motion is guaranteed to converge close to the trajectory and then toward the demonstrated goal. Regulation of the robot stiffness according to the epistemic uncertainty of the policy allows for easily reshaping the motion with human feedback and/or adapting to external perturbations. We tested the SIMPLe algorithm on a real dual-arm setup where the teacher gave separate single-arm demonstrations and then successfully synchronized them only using kinesthetic feedback or where the original bimanual demonstration was locally reshaped to pick a box at a different height.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalIEEE/ASME Transactions on Mechatronics
Publication statusAccepted/In press - 11 Aug 2023


  • Bimanual manipulation
  • Covariance matrices
  • Education
  • impedance control
  • interactive imitation learning (IIL)
  • movement primitives (MPs)
  • Robot kinematics
  • Robots
  • Stability analysis
  • Task analysis
  • Trajectory


Dive into the research topics of 'Interactive Imitation Learning of Bimanual Movement Primitives'. Together they form a unique fingerprint.

Cite this