January, 18, 2022

A Bioinspired Advanced Neural Control for Autonomous Walking Robots

Researchers from BRAIN-lab at VISTEC in Thailand developed a bioinspired advanced neural control with proactive behavior learning and short-term memory for autonomous walking robots that enables them to traverse complex terrain.

Image credit: BRAIN-lab at VISTEC

The proposed control consists of three main modular neural mechanisms to create insect-like gaits, adapt robot joint movement individually with respect to the terrain during the stance phase using only the torque feedback, and generate a short-term memory for proactive obstacle avoidance during the swing phase.

Their proposed control:

  • does not require robot and environmental models, exteroceptive feedback, or multiple learning trials
  • depends only on proprioceptive feedback and short-term memory
  • is general (no robot model is needed), and it can be used for autonomous locomotion of other walking robots

More information: