Event

Bayesian-optimization study tunes walking controllers on ATRIAS hardware

Sep 18, 2017 · Research Publication · Agility Robotics · Humanoid

  • The paper applies Bayesian optimization with a domain-informed feature transform to bipedal locomotion controller tuning.
  • The method is evaluated on the ATRIAS biped in simulation and on hardware, including two walking controllers on the real robot.
  • It gives ATRIAS a concrete learning-on-hardware research record for sample-efficient bipedal gait optimization.

US robotics company focused on humanoid systems for logistics and warehouse automation. Digit is designed for real-world material handling tasks in structured environments.

Segment
Humanoid
Event type
Research Publication
Geography
Salem · United States