To　solve　the　path　planning　problem　of　mobile　robot　in　static　unknown　environment,　a　new　path　planning　method　was　proposed　which　combined　the　deep　auto-encoder　with　the　Q-learning　algorithm,　namely　the　DAE-Q　path　planning　method.　The　deep　auto-encoder　processed　the　raw　image　data　to　get　the　feature　information　of　the　environment.　The　Q-learning　algorithm　chose　an　action　according　to　the　environmental　information　and　the　robot　moved　to　a　new　position,　changing　the　surrounding　environment　of　the　mobile　robot.　The　robot　realized　autonomous　learning　through　the　interaction　with　the　environment.　The　system　processed　raw　image　data　and　extracted　the　image　feature　autonomously　by　combining　the　deep　auto-encoder　and　the　Q-learning　algorithm,　and　the　autonomy　of　the　system　was　improved.　In　addition,　an　improved　Q-learning　algorithm　to　improve　the　system＇s　convergence　speed　and　shorten　the　learning　time　was　utilized.　Experimental　evaluation　validates　the　effectiveness　of　the　method.　©　2016,　Editorial　Department　of　Journal　of　Beijing　University　of　Technology.　All　right　reserved.