Research On Navigation Method Of Service Robot Based On Pedestrian Social Attributes

With an aging population and an increasing labor shortage in services,medical care,education and other industries,the demand for service robots is on the rise.There is a huge market potential and development space for service robots.However,the existing service robots can’t satisfy people’s expectations,and Tri-Co Robot has become the development direction of next generation service robots.For service robots working in crowds,improving the navigation ability in a human-robot coexistence environment is the basis of human-robot interaction,human-robot collaboration and other high-level tasks.Compared with traditional mobile robots,the emergence of humans increases the difficulty of deploying service robots in real-world environments.How to represent pedestrians with social attributes during robot navigation tasks is the first problem that needs to be solved to achieve human-robot coexistence.Specifically,humans are different from obstacles in the environment who have social attributes.Secondly,forecasting the trajectory of pedestrians is an indispensable part of robots working in dynamic scenes,which can alleviate the problems,such as "turning" and "freezing robot." While solving the above problems,considering the human comfort space and predicted trajectory in the motion planning algorithm to generate a trajectory that considers the comfort of pedestrians is the crucial point of human-aware navigation.Lastly,the evaluation of robot behavior is essential for enhancing robot navigation ability and continuously optimizing robot behavior.Because of these problems,this paper explores the field of human comfort space modelling,pedestrian trajectory prediction,human-aware robot navigation,and robot behavior evaluation.The main contributions are listed as follows:(1)Modeling of human dynamic comfort space based on asymmetric gaussian function:In view of the previous pedestrian comfort space model,it has a fixed shape and cannot satisfy the comfort needs of various pedestrians.This paper proposes a novel dynamic personal comfort space model based on asymmetric Gaussian function.First,human movement is used to calculate the shape of different comfort spaces.Then a scalable fuzzy reasoning framework is proposed to define the size of personalized comfort space,which considers differences in individual social attributes such as emotion and gesture.On the basis of completing the modeling of single-person comfortable space,this paper uses the adaptive space density function method to realize the grouping of people,and constructs a group comfortable space that integrates social attribute characteristics.In the experimental part,the proposed dynamic comfortable space model is quantitatively and qualitatively analyzed to verify the rationality of the model.(2)Pedestrian trajectory prediction using group constrained hierarchical graph attention networks:Most of the existing interaction models in trajectory prediction only focus on the interaction between pairs of pedestrians and do not consider the group movement of pedestrians and the interaction between groups.Subsequently,this paper proposes a group-constrained hierarchical graph attention network based on generative adversarial networks for pedestrian trajectory prediction.Firstly,a dynamic group detection module is introduced,and the time series motion features,spatial distribution features and correlations of pedestrian trajectories are extracted through the attention transformation network to construct an adjacency matrix reflecting the group relationship.Then,the above-mentioned group constraints are introduced on the basis of traditional paired pedestrian interaction modeling,the interaction between pedestrians is considered from two levels of individual and group,and the interaction between pedestrians in the scene is divided into group,between groups,and then employ a hierarchical graph attention network to model these two interactions separately.Through experiments on public datasets(ETH and UCY),the method proposed in this paper produces predicted trajectories that satisfy social rules while significantly improving prediction accuracy.(3)Design of robot social navigation framework based on temporal cost map:Aiming at the lack of consideration of the time dimension in the traditional navigation strategy,this paper proposes a social navigation framework with interactive awareness.The framework designs a temporal social cost map to represent dynamic and static obstacles in the environment based on the layered cost map mechanism.Firstly,a pedestrian dynamic comfort space model is applied to characterize pedestrians in the current scene,which is normalized into a social cost map usable for robot navigation.At the same time,the trajectory prediction module is used to obtain the predicted trajectory of pedestrians at T moments in the future,and a time-series social cost map about T moments in the future is constructed.Finally,the time-series social cost map is applied to the time-dependent A*algorithm as a cost item for evaluating motion primitives,and trajectories satisfying pedestrian comfort and low collision probability are screened out in the process of motion primitive selection,so as to realize the robot navigation with pedestrian interaction perception ability,and prove the effectiveness of the navigation strategy through simulation experiments.(4)In addition,it is not easy to quantitatively evaluate the comfort level of the robot’s movement.This paper proposes a robot behavior evaluation network based on Transformer and graph attention mechanism.This chapter uses manually annotated public datasets,takes people and robots as nodes in the graph,and then uses graph neural networks to aggregate the information of each node.The characteristics of the entire scene are obtained to evaluate the discomfort caused by the presence of the robot in the current scene.Since the dataset is manually annotated,there are people involved in the evaluation process,so the annotation of the dataset includes human cognition of comfort.Compared with the traditional robot behavior evaluation method without considering human subjectivity,the evaluation network trained according to the manually labelled dataset includes human subjectivity.It is closer to the real feelings of humans.The effectiveness of the proposed robot behavior evaluation network is proved by simulation experiments.This paper first completes the personalized representation of pedestrian social attributes through human dynamic comfort space modelling.Subsequently,by exploiting the characteristics of pedestrian movement,group constraints are introduced into pedestrian interaction modelling for trajectory prediction,which significantly improves prediction accuracy.The comfort space model and pedestrian trajectory prediction module are applied to the motion planning algorithm to generate socially accepted trajectories.In this way,the robot can understand human interaction when navigating in crowds.Lastly,the robot behavior evaluation network is trained by manually annotated data sets and integrates human cognition during the evaluation process.