As　robots　get　closer　to　humans,　higher　requests　to　robots　are　put　forward.　Human-like　motion　is　one　of　those　important　issues,　especially　for　humanoid　service　robots,　advanced　industrial　robots　and　assistive　robots.　In　this　paper,　a　motion-decision　algorithm　is　proposed　and　applied　to　human-like　motion　planning　of　robotic　arms.　The　algorithm　consists　of　two　parts:　intelligent　decision　and　calculation　of　the　joint　trajectory.　The　former　includes　two　parts:　the　hierarchical　planning　strategy　(HPS)　and　the　Bayesian　decision.　The　HPS　reflects　the　general　rules　of　human　arm　movements　and　the　robotic　arms　using　the　HPS　can　simulate　the　movements　of　human　arms　accurately.　The　Bayesian　decision　is　used　to　make　robotic　arms　choose　an　appropriate　mode　of　motion.　The　calculation　of　the　joint　trajectory　builds　a　motion　framework　of　robotic　arms　to　generate　human-like　movements.　The　human　performance　measures　(HPMs)　in　different　planning　hierarchies　are　proposed.　Finally,　the　validity　of　the　proposed　algorithm　is　verified　by　experiments.