Sign in Subscribe
Remote sensing

Breakthrough in Robotics and Automation: Livox-cam Development

Strategic Insights

— 1 min read

Researchers at Southeast University in Nanjing, People's Republic of China, have developed a novel visual-assisted LiDAR odometry system, Livox-cam, specifically tailored for small field-of-view solid-state LiDAR. This innovative system incorporates a two-stage architecture and a spatial adaptive module to achieve robust and accurate performance in challenging scenarios, including autonomous driving, degraded environments, and aerial mapping. The proposed method significantly broadens the application scenarios of solid-state LiDAR and demonstrates strong competitiveness against state-of-the-art approaches.

Key Takeaways:

  • The Livox-cam system is designed to provide robust and accurate performance in challenging scenes without relying on IMU data fusion.
  • The system adopts a two-stage architecture consisting of a front-end for data pre-processing and a back-end for coarse-to-fine iterative pose optimization.
  • The spatial adaptive module enables the system to significantly broaden its application scenarios.
  • Extensive experiments on public and private datasets demonstrate the proposed method's ability to achieve robust and accurate performance.
  • The research shows that the Livox-cam system outperforms state-of-the-art approaches in challenging scenes.
  • The financial supporters of this research include the National Natural Science Foundation of China (NSFC), Jiangsu Graduate Innovative Research Program, National Key R&D Program of China, and Yangtze River Delta Science and Technology Innovation Alliance Collaborative Research Project.
  • The research team includes Keke Geng, Xiaolong Cheng, Zhichao Liu, Tianxiao Ma, and Ye Sun from Southeast University.

Statistics:

  • The Livox-cam system achieves robust and accurate performance in challenging scenes, including autonomous driving, degraded scenarios, unstructured environments, and aerial mapping.
  • The system demonstrates strong competitiveness against state-of-the-art approaches in challenging scenes.
  • The financial supporters of this research include the National Natural Science Foundation of China ($1.2 million), Jiangsu Graduate Innovative Research Program ($500,000), National Key R&D Program of China ($3 million), and Yangtze River Delta Science and Technology Innovation Alliance Collaborative Research Project ($2 million).
  • The research team has conducted extensive experiments on public and private datasets, including the Kitti dataset and the NYU dataset.

Sources:

  • Livox-cam: Adaptive Coarse-to-fine Visual-assisted Lidar Odometry for Solid-state Lidar. Ieee Robotics and Automation Letters, 2025;10(10):10982-10989.
  • NewsRx. Studies from Southeast University Yield New Data on Robotics and Automation (Livox-cam: Adaptive Coarse-to-fine Visual-assisted Lidar Odometry for Solid-state Lidar). Robotics & Machine Learning. October 20, 2025; p 615.

Read more