For　the　path　planning　problem　of　search　and　rescue　robot　in　unknown　environment,　a　bionic　learning　algorithm　was　proposed.　The　GSOM　(Growing　Self-organizing　Map)　algorithm　was　used　to　build　the　environment　cognitive　map.　The　heuristic　search　A*　algorithm　was　used　to　find　the　global　optimal　path　from　initial　state　to　target　state.　When　the　local　environment　was　changed,　reinforcement　learning　algorithm　based　on　sensor　information　was　used　to　guide　the　search　and　rescue　robot　behavior　of　local　path　planning.　Simulation　results　show　the　method　effectiveness.　©　(2013)　Trans　Tech　Publications,　Switzerland.