A hexapod using GOLLUM autonomously learned multiple locomotion skills in about an hour by growing new neural subnetworks for new conditions and by blending previously learned skills through supplementary connections.
Journal of Intelligent & Robotic Systems 99(3-4): 659--671
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Growable and Interpretable Neural Control with Online Continual Learning for Autonomous Lifelong Locomotion Learning Machines
A hexapod using GOLLUM autonomously learned multiple locomotion skills in about an hour by growing new neural subnetworks for new conditions and by blending previously learned skills through supplementary connections.