In　order　to　effectively　prevent　particle　swarm　into　local　optimum　and　enhance　the　ability　of　particles　to　find　the　optimal　solution,　the　paper　proposes　an　improved　particle　swarm　algorithm.　The　paper　is　on　the　background　of　vehicle　scheduling,　which　is　using　the　load　priority　strategy,　and　establishes　the　model　for　vehicle　scheduling　problem　with　load　and　vehicle　scheduling　problem　with　soft　time　windows.　The　experimental　results　show　that　the　improved　particle　swarm　can　quickly　and　efficiently　obtain　the　optimal　solution　for　vehicle　routing　problem.