To address the technical difficulties of artificial potential filed (APF)-based automatic collision avoidance (CA) algorithms, a stable and reliable technological framework was established for autonomous CA from the perspectives of navigation practice and real-ship application. First, an improved route-plan-guided APF (RPGAPF) approach was introduced, considering the ship motion and constraints by the International Regulations for Preventing Collisions at Sea (COLREGS). Second, a simulation-based real-ship accompanying test system (SRSATS) was well-designed for the intelligent navigation projects and installed on a 45.0 m length ship. Third, various real-ship open-loop CA tests were conducted under different encountering situations, and concurrently, simulation testing in both open-loop and closed-loop were carried out. The results indicated that simulation tests may be used as precursors before real-ship trials, and that the proposed SRSATS can be employed as a practical verification method for real-ship testing to generate variety of complex encountering situations. The CA procedures and results for the corresponding real-ship and simulation tests produced similar trends, and the improved RPGAPF approach can be applied in real-ship automatic CA systems owing to its dependability, determinism, and repeatability. This study proposes a complete solution for the APF-base CA approach, including system modelling, integration and testing. The findings provide valuable insights into the ship CA research and contribute to the improvement of ship intelligence.