Stochastic Bayesian Computation for Autonomous Robot Sensorimotor System - Archive ouverte HAL Access content directly
Conference Papers Year :

Stochastic Bayesian Computation for Autonomous Robot Sensorimotor System

(1, 2, 3) , (4) , (5) , (1, 2, 3) , (1, 3)
1
2
3
4
5

Abstract

This paper presents a stochastic computing implementation of a Bayesian sensorimotor system that performs obstacle avoidance for an autonomous robot. In a previous work we have shown that we are able to automatically design a probabilistic machine which computes inferences on a Bayesian model using stochastic arithmetic. We start from a high level Bayesian model description, then our compiler generates an electronic circuit, corresponding to the probabilistic inference, operating on stochastic bit streams. Our goal in this paper is to show that our compilation toolchain and simulation device work on a classic robotic application, sensor fusion for obstacle avoidance. The novelty is in the way the computations are implemented, opening the way for future low power autonomous robots using such circuits to perform Bayesian Inference.
Fichier principal
Vignette du fichier
stochastic-bayesian-computation.pdf (1.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01265559 , version 1 (01-07-2016)

Identifiers

  • HAL Id : hal-01265559 , version 1

Cite

Marvin Faix, Jorge Lobo, Raphael Laurent, Dominique Vaufreydaz, Emmanuel Mazer. Stochastic Bayesian Computation for Autonomous Robot Sensorimotor System. Workshop on Unconventional Computing for Bayesian Inference (UCBI) at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), Sep 2015, Hambourg, Germany. ⟨hal-01265559⟩
311 View
212 Download

Share

Gmail Facebook Twitter LinkedIn More