Sen Cheng

About

Sen Cheng is a leading researcher in neuro-inspired robotics, specializing in simultaneous localization and mapping (SLAM) algorithms modeled after rodent brain navigation systems. His major contributions center on advancing RatSLAM, a biologically plausible SLAM approach, by making it more practical and scalable for real-world applications. Cheng pioneered automatic parameter tuning for RatSLAM using Irace and Iterative Closest Point methods, significantly improving its adaptability across diverse environments. He also developed a neuro-inspired multi-robot mapping framework that leverages shared video information to reduce mapping time, and created multisession SLAM techniques for incremental map building. His work includes the xRatSLAM extensible computational framework and a parallel C++ library implementation, both designed to make RatSLAM more accessible and efficient for the robotics community. With over 20 citations across his most-cited papers, Cheng’s research bridges neuroscience and robotics, offering elegant solutions to fundamental SLAM challenges. His achievements demonstrate how biological principles can inspire robust, flexible algorithms for autonomous navigation, making him a key figure in the growing field of neurorobotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Automatic Tuning of RatSLAM’s Parameters by Irace and Iterative Closest Point

   8 citations · 2020
2. 2
   A Neuro-Inspired Approach to Solve a Simultaneous Location and Mapping Task Using Shared Information in Multiple Robots Systems

   6 citations · 2018
3. 3
   A Multisession SLAM Approach for RatSLAM

   3 citations · 2023
4. 4
   xRatSLAM: An Extensible RatSLAM Computational Framework

   3 citations · 2022
5. 5
   A Parallel RatSlam C++ Library Implementation

   2 citations · 2019

Key Collaborators

Contact & Links