Sign in Subscribe
Machine learning

Enhanced Navigation System for Unmanned Surface Vehicles

Strategic Insights

— 2 min read

Researchers from Shanghai Jiao Tong University have proposed an innovative navigation framework for unmanned surface vehicles (USVs) operating in urban waterways. The framework aims to address the limitations of Global Navigation Satellite System (GNSS) in providing accurate localization in GNSS-attenuated areas, while also mitigating collision threats from vessels and piloting errors. The system incorporates a tightly coupled LiDAR-Visual-Inertial Odometry via Smoothing and Mapping (LVI-SAM) framework for localization and mapping, along with an incrementally mapping data structure to improve computation efficiency and accuracy. Additionally, the system utilizes valid GNSS measurements to provide absolute reference in the factor graph optimization framework, enabling optimum state estimation.

Key Takeaways:

  • The proposed navigation framework consists of a tightly coupled LiDAR-Visual-Inertial Odometry via Smoothing and Mapping (LVI-SAM) framework for localization and mapping, which is selected as the fundamental framework of localization and mapping subsystem.
  • The LVI-SAM framework is enhanced with an incrementally mapping data structure to improve the computation efficiency and accuracy of the LiDAR odometry optimization process.
  • The system incorporates valid GNSS measurements to provide absolute reference in the factor graph optimization framework, which can achieve optimum state estimation by maximum a posteriori given all the noisy measurements from multiple sensors.
  • A dynamic occupancy grid map framework, based on sequential Monte Carlo and probability hypothesis density method, is developed to enhance situational awareness of USVs for risk anticipation of dynamic obstacles and facilitate predictive avoidance.
  • Extensive real-world experiments have been carried out to demonstrate that the proposed autonomous navigation system is capable of robust and accurate localization over long-term urban waterway navigation, and dynamic obstacle avoidance through a safer predictive strategy.
  • The research was funded by the National Natural Science Foundation of China (No. 52271284) and the Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (No. SL2021ZD201).
  • The research concluded that the proposed navigation system is capable of addressing the limitations of GNSS in providing accurate localization in GNSS-attenuated areas, while also mitigating collision threats from vessels and piloting errors.

Statistics:

  • The proposed navigation framework consists of multiple sensors, including LiDAR, visual, and inertial sensors.
  • The system utilizes an incrementally mapping data structure to improve the computation efficiency and accuracy of the LiDAR odometry optimization process.
  • The system incorporates valid GNSS measurements to provide absolute reference in the factor graph optimization framework.
  • The dynamic occupancy grid map framework is based on sequential Monte Carlo and probability hypothesis density method.
  • The research was conducted in Shanghai, People's Republic of China, and involved extensive real-world experiments.

Sources:

  • An Enhanced Navigation System With Predictive Motion Planning for Unmanned Surface Vehicles In Gnss-attenuated Dynamic Urban Waterways. Journal of Field Robotics, 2025.
  • NewsRx. Findings in Field Robotics Reported from Shanghai Jiao Tong University (An Enhanced Navigation System With Predictive Motion Planning for Unmanned Surface Vehicles In Gnss-attenuated Dynamic Urban Waterways). Robotics & Machine Learning. July 28, 2025; p 107.
  • National Natural Science Foundation of China (No. 52271284)
  • Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (No. SL2021ZD201)
  • Shanghai Jiao Tong University, Sch Ocean & Civil Engn, Shanghai, People's Republic of China.

Read more