NDT-PSO, a New NDT based SLAM Approach using Particle Swarm Optimization


This paper deals with the problem of simultaneous localization and mapping (SLAM). Providing both accurate environment’s map and pose estimation is necessary to correctly navigate, which is a key issue for a mobile robot interacting with human beings. It is a line of research that is always active, offering various solutions to this issue. Nevertheless, among many SLAM methods, Normal Distributions Transform (NDT) has shown high performances, where numerous works have been published up to date and many studies demonstrate its efficiency wrt to other methods. In this paper a new NDT based SLAM method using Particle Swarm Optimization called NDT-PSO is proposed. The main contribution is to invest the bio-inspired approach PSO to solve pose estimation problem based on iterative NDT maps. Real experiments have been performed on a car-like mobile robot to confirm the performances of NDT-PSO approach and its efficiency in both static and dynamic environments.

In The 16th International Conference on Control, Automation, Robotics and Vision (ICARCV 2020)
Abdelhak Bougouffa
Abdelhak Bougouffa
Ph.D. Student | R&D Engineer

My research interests include robotics, state estimation, data fusion, AI, and embedded systems.