Socially-Aware Navigation of Omnidirectional Mobile Robot with Extended Social Force Model in Multi-Human Environment

Yang, Chun-Tang; Zhang, Tianshi; Chen, Li-Pu; Fu, Li-Chen

doi:10.1109/smc.2019.8913844

Cited by 18 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional methods attempt to tackle the robot navigation problem in crowded environments through well-engineered rules. A pioneer work develops social force model that defines attractive and repulsive forces to describe human interactions and has been successfully applied in both simulation and realworld environments [20][21][22]. Reciprocal velocity obstacles (RVO) [23] and optimal reciprocal collision avoidance (ORCA) [24] are velocity-based breakthrough algorithms in multi-agent collision avoidance.…”

Section: Related Workmentioning

confidence: 99%

Safe and socially compliant robot navigation in crowds with fast-moving pedestrians via deep reinforcement learning

Feng,

Xue,

Wang

et al. 2024

Robotica

View full text Add to dashboard Cite

Safe and socially compliant navigation in a crowded environment is essential for social robots. Numerous research efforts have shown the advantages of deep reinforcement learning techniques in training efficient policies, while most of them ignore fast-moving pedestrians in the crowd. In this paper, we present a novel design of safety measure, named Risk-Area, considering collision theory and motion characteristics of different robots and humans. The geometry of Risk-Area is formed based on the real-time relative positions and velocities of the agents in the environment. Our approach perceives risk in the environment and encourages the robot to take safe and socially compliant navigation behaviors. The proposed method is verified with three existing well-known deep reinforcement learning models in densely populated environments. Experiment results demonstrate that our approach combined with the reinforcement learning techniques can efficiently perceive risk in the environment and navigate the robot with high safety in the crowds with fast-moving pedestrians.

show abstract

Section: Related Workmentioning

confidence: 99%

Safe and socially compliant robot navigation in crowds with fast-moving pedestrians via deep reinforcement learning

Feng,

Xue,

Wang

et al. 2024

Robotica

View full text Add to dashboard Cite

show abstract

“…As intelligent interactive systems continue to advance, it is becoming increasingly critical for machines to understand human behavior and provide reliable human-machine interactions. In many applications, such as a mobile social robot [1,2] in a crowded area, an autonomous vehicle [3,4] navigating complicated roadways, or a mobile agent [5] in an unstructured setting, pedestrian trajectory prediction is a critical process. These machines must avoid collisions with pedestrians or other obstacles to accomplish their tasks.…”

Section: Introductionmentioning

confidence: 99%

Predicting Pedestrian Trajectories with Deep Adversarial Networks Considering Motion and Spatial Information

Lao,

Du,

Chen

2023

Algorithms

View full text Add to dashboard Cite

This paper proposes a novel prediction model termed the social and spatial attentive generative adversarial network (SSA-GAN). The SSA-GAN framework utilizes a generative approach, where the generator employs social attention mechanisms to accurately model social interactions among pedestrians. Unlike previous methodologies, our model utilizes comprehensive motion features as query vectors, significantly enhancing predictive performance. Additionally, spatial attention is integrated to encapsulate the interactions between pedestrians and their spatial context through semantic spatial features. Moreover, we present a novel approach for generating simulated multi-trajectory datasets using the CARLA simulator. This method circumvents the limitations inherent in existing public datasets such as UCY and ETH, particularly when evaluating multi-trajectory metrics. Our experimental findings substantiate the efficacy of the proposed SSA-GAN model in capturing the nuances of pedestrian interactions and providing accurate multimodal trajectory predictions.

show abstract

“…e crowd evacuation simulation is performed using the density evacuation algorithm and the social force model and they can effectively improve the efficiency of crowd evacuation [32]. However, the social force model mainly is applied in the case of human-human interaction, rather than in scenarios of human-vehicle interaction [16,[33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Research on the Behavioral Dynamics Motion Planning Method of the Human-Vehicle Social Force Model

Gai-ning

Zhang

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The interactive motion planning between unmanned vehicles and pedestrians in urban road environments is the key to realizing the autonomous motion of unmanned vehicles in hybrid traffic scenarios. The problem of human-vehicle interaction motion planning modeling at complex intersections is studied for an unmanned vehicle in this article. First, the motion planning of pedestrians and the unmanned vehicles is established according to the social force model and the behavioral dynamics model. Then, the autonomous vehicle is added to the crowd, and the human-vehicle interaction force is established. The virtual force is added to the social force model and the behavioral dynamics model, respectively, and the improved social force model and the behavioral dynamics model are used for the motion planning of pedestrians and unmanned vehicles. In this way, the established model solves the problems of simple pedestrian interaction motion planning in the social force model and single-body motion planning in the behavioral dynamics and thus provides a strong support for multibody motion planning. Finally, through the interactive motion planning trajectory of pedestrians and unmanned vehicles in different scenes, the vehicle and pedestrian motion planning trajectory can effectively avoid overlapping or crossing, so as to avoid the collision, which verifies the effectiveness and feasibility of the proposed model.

show abstract

Socially-Aware Navigation of Omnidirectional Mobile Robot with Extended Social Force Model in Multi-Human Environment

Cited by 18 publications

References 28 publications

Safe and socially compliant robot navigation in crowds with fast-moving pedestrians via deep reinforcement learning

Safe and socially compliant robot navigation in crowds with fast-moving pedestrians via deep reinforcement learning

Predicting Pedestrian Trajectories with Deep Adversarial Networks Considering Motion and Spatial Information

Research on the Behavioral Dynamics Motion Planning Method of the Human-Vehicle Social Force Model

Contact Info

Product

Resources

About