Dataset Information

Hierarchical Spatial Concept Formation Based on Multimodal Information for Human Support Robots.

ABSTRACT: In this paper, we propose a hierarchical spatial concept formation method based on the Bayesian generative model with multimodal information e.g., vision, position and word information. Since humans have the ability to select an appropriate level of abstraction according to the situation and describe their position linguistically, e.g., "I am in my home" and "I am in front of the table," a hierarchical structure of spatial concepts is necessary in order for human support robots to communicate smoothly with users. The proposed method enables a robot to form hierarchical spatial concepts by categorizing multimodal information using hierarchical multimodal latent Dirichlet allocation (hMLDA). Object recognition results using convolutional neural network (CNN), hierarchical k-means clustering result of self-position estimated by Monte Carlo localization (MCL), and a set of location names are used, respectively, as features in vision, position, and word information. Experiments in forming hierarchical spatial concepts and evaluating how the proposed method can predict unobserved location names and position categories are performed using a robot in the real world. Results verify that, relative to comparable baseline methods, the proposed method enables a robot to predict location names and position categories closer to predictions made by humans. As an application example of the proposed method in a home environment, a demonstration in which a human support robot moves to an instructed place based on human speech instructions is achieved based on the formed hierarchical spatial concept.

SUBMITTER: Hagiwara Y

PROVIDER: S-EPMC5859180 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hierarchical Spatial Concept Formation Based on Multimodal Information for Human Support Robots.

Hagiwara Yoshinobu Y Inoue Masakazu M Kobayashi Hiroyoshi H Taniguchi Tadahiro T

Frontiers in neurorobotics 20180313

In this paper, we propose a hierarchical spatial concept formation method based on the Bayesian generative model with multimodal information e.g., vision, position and word information. Since humans have the ability to select an appropriate level of abstraction according to the situation and describe their position linguistically, e.g., "I am in my home" and "I am in front of the table," a hierarchical structure of spatial concepts is necessary in order for human support robots to communicate sm ...[more]

PMID: 29593521

Similar Datasets

Project description:Assisting individuals in their daily activities through autonomous mobile robots is a significant concern, especially for users without specialized knowledge. Specifically, the capability of a robot to navigate to destinations based on human speech instructions is crucial. Although robots can take different paths toward the same objective, the shortest path is not always the most suitable. A preferred approach would be to accommodate waypoint specifications flexibly for planning an improved alternative path even with detours. Furthermore, robots require real-time inference capabilities. In this sense, spatial representations include semantic, topological, and metric-level representations, each capturing different aspects of the environment. This study aimed to realize a hierarchical spatial representation using a topometric semantic map and path planning with speech instructions by including waypoints. Thus, we present a hierarchical path planning method called spatial concept-based topometric semantic mapping for hierarchical path planning (SpCoTMHP), which integrates place connectivity. This approach provides a novel integrated probabilistic generative model and fast approximate inferences with interactions among the hierarchy levels. A formulation based on "control as probabilistic inference" theoretically supports the proposed path planning algorithm. We conducted experiments in a home environment using the Toyota human support robot on the SIGVerse simulator and in a lab-office environment with the real robot Albert. Here, the user issues speech commands that specify the waypoint and goal, such as "Go to the bedroom via the corridor." Navigation experiments were performed using speech instructions with a waypoint to demonstrate the performance improvement of the SpCoTMHP over the baseline hierarchical path planning method with heuristic path costs (HPP-I) in terms of the weighted success rate at which the robot reaches the closest target (0.590) and passes the correct waypoints. The computation time was significantly improved by 7.14 s with the SpCoTMHP than the baseline HPP-I in advanced tasks. Thus, hierarchical spatial representations provide mutually understandable instruction forms for both humans and robots, thus enabling language-based navigation.

Project description:One of the core issues of ecology is to understand the effects of landscape patterns on ecological processes. For this, we need to accurately capture changes in the fine landscape structures to avoid losing information about spatial heterogeneity. The landscape pattern indicators (LPIs) can characterize the spatial structures and give some information about landscape patterns. However, researches on LPIs had mainly focused on the horizontal structure of landscape patterns, while few studies addressed vertical relationships between the levels of hierarchical landscape structures. Thus, the ignorance of the vertical hierarchical relationships may cause serious biases and reduce LPIs' representational ability and accuracy. The hierarchy theory about the landscape pattern structures could notably reduce the loss of hierarchical information, and the information entropy could quantitatively describe the vertical status of landscape units. Therefore, we established a new multidimensional fusion method of LPIs based on hierarchy theory and information entropy. Here, we created a general fusion formula for commonly used simple LPIs based on two-grade land use data (whose land use classification system contains two grades/levels) and derived 3 fusion landscape pattern indicators (FLIs) with a case study. The results show that the information about fine spatial structure is captured by the fusion method. The regions with the most differences between the FLIs and the traditional LPIs are those with the largest vertical structure such as the ecological ecotones, where vertical structure was ignored before. The FLIs have a finer spatial representational ability and accuracy, not only retaining the main trend information of first-grade land use data, but also containing the internal detail information of second-grade land use data. Capturing finer spatial information of landscape patterns should encourage the application of fusion method, which should be suitable for more LPIs or more dimensional data. And the increased accuracy of FLIs will improve ecological models that rely on finer spatial information.

Dataset Information

Hierarchical Spatial Concept Formation Based on Multimodal Information for Human Support Robots.

Publications

Hierarchical Spatial Concept Formation Based on Multimodal Information for Human Support Robots.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets