In　order　to　improve　the　speed,　efficiency　and　robustness　of　the　automatic　sorting　system,　this　paper　proposes　an　improved　ant　colony　algorithm　based　dynamic　sorting　strategy.　Under　the　operating　condition　of　automatic　sorting　scenario　on　the　assembly　line,　two　city　sets　are　established　to　divide　the　picking　area　and　the　placing　area　as　two　countries.　In　addition,　an　improved　ant　colony　algorithm　optimization　approach　with　variation　operator　is　added,　which　get　inspired　by　genetic　algorithms.　This　optimization　approach　has　the　properties　of　broad　adaptability,　high　feasibility　and　capability　to　achieve　global　optimization.　Simulation　and　experimental　results　show　that　the　proposed　sorting　strategy　has　better　robustness　for　sorting　operations　with　different　objects　density.　Meanwhile,　it　can　effectively　reduce　the　sorting　path　length　and　working　time　compared　with　traditional　sorting　strategies.　©　2022　IEEE.