Particle Swarm Optimization (PSO) is a versatile population-based optimization technique, in many respects similar to evolutionary algorithms. The PSO has its origin on the swarm intelligence algorithms, which are concerned with the design of intelligent multi-agent systems by taking stimulation from the collective behavior of social insects such as ants, termites, bees, and wasps, as well as from other animal societies such as flocks of birds or schools of fish. In PSO method, the particles that represent potential solutions move around in the phase space with a velocity updated by the particle’s own experience and the experience of the particle’s neighbors or the experience of the whole swarm.

Particle Filter (PF) performs sequential Monte Carlo estimation (PSO is not Monte Carlo method) based on particle representation of probability densities, by representing the posterior density function by a set of random samples with associated weights and computing estimates based on these samples and weights. In this method the particles with high weights propagate and the particles with smallest weights are eliminated by a re-sampling procedure.

Your answer is a high-quality answer which can make the problem easy to understand. After reading your answer, I understand that PSO and PF have the only similar point “particle” ,but particle has different meaning in the two algorithm. PSO is a intelligence algorithm. PF is an algorithm from Probability Theory.

Reference: https://blog.csdn.net/daaikuaichuan/article/details/81382794

https://www.youtube.com/watch?v=JhgDMAm-imI

간단하게 모델 입히는 방법은 관측 데이터 x,y를 PSO 모델에 넣어서 PSO에 있는 파티클들에 조건(particle velocity, global goal, local goal)에 따라 Iterate를 하여서 관측 데이터의 정확한 X,Y를 영상이면 카메라 이미지 안에서 찾는 다던가, 맵이라면, 맵 상에서 Global Minimum이 되는 곳을 찾아 얻게 된다.

exsitng, 2D gird or 3D voxel map

put a model that we want to know pose

global 상에 pose를 공식에다가 넣고, 3개의 particle velocity를 가지고 Iteration하게 업데이트 하여서 위치를 구하는 방법

https://blog.csdn.net/TOMJJY/article/details/104403381