ct 16(8): e3

Research Article

Gist+RatSLAM: An Incremental Bio-inspired Place Recognition Front-End for RatSLAM

Download215 downloads
  • @ARTICLE{10.4108/eai.3-12-2015.2262532,
        author={S. M. Ali Musa Kazmi and B\aa{}rbel Mertsching},
        title={Gist+RatSLAM: An Incremental Bio-inspired Place Recognition Front-End for RatSLAM},
        journal={EAI Endorsed Transactions on Creative Technologies},
        volume={3},
        number={8},
        publisher={ACM},
        journal_a={CT},
        year={2016},
        month={5},
        keywords={gist, bio-inspired mapping, scene recognition, global image feature, self-organizing neural network, competitive learning},
        doi={10.4108/eai.3-12-2015.2262532}
    }
    
  • S. M. Ali Musa Kazmi
    Bärbel Mertsching
    Year: 2016
    Gist+RatSLAM: An Incremental Bio-inspired Place Recognition Front-End for RatSLAM
    CT
    EAI
    DOI: 10.4108/eai.3-12-2015.2262532
S. M. Ali Musa Kazmi1,*, Bärbel Mertsching1
  • 1: University of Paderborn, Paderborn, Germany
*Contact email: kazmi@get.upb.de

Abstract

There exists ample research exploiting cognitive processes for robot localization and mapping, for instance RatSLAM [10]. In this regard, tasks such as visual perception and recognition, which are primarily governed by visual and perirhinal cortices, receive a little attention. To bridge this gap, we present a novel bio-inspired place recognition front-end for the RatSLAM system. Our algorithm uses Gist features to obtain the perceptual structure of the scenes and employs a modified growing self-organizing map (GSOM) to model the behavior of the cells found in perirhinal cortex, called recency and familiarity neurons [6]. This enables an online learning and recognition of the places without acquiring apriori knowledge of the environment. The experiments carried out on the standard St. Lucia dataset demonstrate that on average our approach achieves almost 10% improvement (in F1-Score); it is able to correctly flag the visited and unvisited places even for noisy and blurred visual inputs. The results show that the proposed method reaches fast convergence and utilizes a smaller number of cells (consumes less physical memory) to represent the traversed path compared to the RatSLAM approach.