No 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.descriptor to obtain the structural formation of the scenes. This information is later fed to the modified growing selforganizing map (GSOM), a type of neural network, to organize the places based on their perceptual distances. A comprehensive evaluation of the proposed approach on the standard St. Lucia dataset is presented in Section 4, including comparison with the state-of-the-art RatSLAM algorithm. The results show that the proposed approach performs better than existing front-end module (data association) of the RatSLAM system and imposes less consumption of physical memory. Finally, we conclude the discussion in Section 5 with the possible directions of future work.

No abstract

No abstract

No abstract