In November of 2005, the Defense Advanced Research Projects Agency initiated a new robotics program, Learning Locomotion, designed to solve some of the key outstanding issues. The expectation was that a combination of machine learning techniques and smart development would accelerate the pace of making autonomous legged systems robust and useful.
No takes yet. Share an insight, caveat, or question.
Pippine et al. (2010) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: