Shengshan Ma

About

Shengshan Ma is a researcher specializing in autonomous robotic systems for environmental monitoring, with a particular focus on plume source localization—the challenge of using robots to autonomously trace chemical or gas leaks to their origin. His work bridges robotics, computer vision, and probabilistic modeling to enable efficient, real-world search strategies. In his 2023 study on autonomous plume near-source search, Ma integrated a finite state machine with YOLOv3-tiny, a lightweight deep learning object detector, to leverage intermittent visible plume information for faster, more reliable source identification. This work, cited 5 times, demonstrates a practical approach to combining visual cues with autonomous decision-making. Expanding on this, Ma developed a multi-robot strategy employing a Dirichlet Process Gaussian Mixture Model and a mutation random salp swarm algorithm, enabling self-coloring-driven coordination among robots to locate plume sources in complex environments. Though early in its citation impact, this research introduces novel probabilistic and swarm intelligence methods to a field critical for industrial safety and environmental protection. Ma’s contributions are laying groundwork for more adaptive, vision-guided robotic systems in hazardous search-and-localize missions.

Research Focus

Key Achievements

Top Papers

1. 1
   Autonomous plume Near-Source search assisted by intermittent visible plume information using finite state Machine and YOLOv3-tiny

   5 citations · 2023
2. 2
   Self-coloring-Driven Plume Source Localization Strategy for Multiple Robots Using Dirichlet Process Gaussian Mixture Model and Mutation Random Salp Swarm Algorithm

   2 citations · 2023

Key Collaborators

Contact & Links