An official website of the United States government
Pedestrian flow in densely-populated or congested areas usually presents irregular or turbulent motion state due to competitive behaviors of individual pedestrians, which reduces flow efficiency and raises the risk of crowd accidents. Effective pedestrian flow regulation strategies are highly valuable for flow optimization. Existing studies seek for optimal design of indoor architectural features and spatial placement of pedestrian facilities for the purpose of flow optimization. However, once placed, the stationary facilities are not adaptive to real-time flow changes. In this paper, we investigate the problem of regulating two merging pedestrian flows in a bottleneck area using a mobile robot moving among the pedestrian flows. The pedestrian flows are regulated through dynamic human-robot interaction (HRI) during their collective motion. We adopt an adaptive dynamic programming (ADP) method to learn the optimal motion parameters of the robot in real time, and the resulting outflow through the bottleneck is maximized with the crowd pressure reduced to avoid potential crowd disasters. The proposed algorithm is a data-driven approach that only uses camera observation of pedestrian flows without explicit models of pedestrian dynamics and HRI. Extensive simulation studies are performed in both Matlab and a robotic simulator to verify the proposed approach and evaluate the performances
more »
« less
Robot-Assisted Pedestrian Regulation Based on Deep Reinforcement Learning
Pedestrian regulation can prevent crowd accidents and improve crowd safety in densely populated areas. Recent studies use mobile robots to regulate pedestrian flows for desired collective motion through the effect of passive human-robot interaction (HRI). This paper formulates a robot motion planning problem for the optimization of two merging pedestrian flows moving through a bottleneck exit. To address the challenge of feature representation of complex human motion dynamics under the effect of HRI, we propose using a deep neural network to model the mapping from the image input of pedestrian environments to the output of robot motion decisions. The robot motion planner is trained end-to-end using a deep reinforcement learning algorithm, which avoids hand-crafted feature detection and extraction, thus improving the learning capability for complex dynamic problems. Our proposed approach is validated in simulated experiments, and its performance is evaluated. The results demonstrate that the robot is able to find optimal motion decisions that maximize the pedestrian outflow in different flow conditions, and the pedestrian-accumulated outflow increases significantly compared to cases without robot regulation and with random robot motion.
more »
« less
- PAR ID:
- 10109298
- Date Published:
- Journal Name:
- IEEE Transactions on Cybernetics
- ISSN:
- 2168-2267
- Page Range / eLocation ID:
- 1 to 14
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Effective human-robot interaction is increasingly vital across various domains, including assistive robotics, emotional communication, entertainment, and industrial automation. Visual feedback, a common feature of current interfaces, may not be suitable for all environments. Audio feedback serves as a critical supplementary communication layer in settings where visibility is low or where robotic operations generate extensive data. Sonification, which transforms a robot's trajectory, motion, and environmental signals into sound, enhances users' comprehension of robot behavior. This improvement in understanding fosters more effective, safe, and reliable Human-Robot Interaction (HRI). Demonstrations of auditory data sonification's benefits are evident in real-world applications such as industrial assembly, robot-assisted rehabilitation, and interactive robotic exhibitions, where it promotes cooperation, boosts performance, and heightens engagement. Beyond conventional HRI environments, auditory data sonification shows substantial potential in managing complex robotic systems and intricate structures, such as hyper-redundant robots and robotic teams. These systems often challenge operators with complex joint monitoring, mathematical kinematic modeling, and visual behavior verification. This dissertation explores the sonification of motion in hyper-redundant robots and teams of industrial robots. It delves into the Wave Space Sonification (WSS) framework developed by Hermann, applying it to the motion datasets of protein molecules modeled as hyper-redundant mechanisms with numerous rigid nano-linkages. This research leverages the WSS framework to develop a sonification methodology for protein molecules' dihedral angle folding trajectories. Furthermore, it introduces a novel approach for the systematic sonification of robotic motion across varying configurations. By employing localized wave fields oriented within the robots' configuration space, this methodology generates auditory outputs with specific timbral qualities as robots move through predefined configurations or along certain trajectories. Additionally, the dissertation examines a team of wheeled industrial/service robots whose motion patterns are sonified using sinusoidal vibratory sounds, demonstrating the practical applications and benefits of this innovative approach.more » « less
-
Existing methods for pedestrian motion trajectory prediction are learning and predicting the trajectories in the 2D image space. In this work, we observe that it is much more efficient to learn and predict pedestrian trajectories in the 3D space since the human motion occurs in the 3D physical world and and their behavior patterns are better represented in the 3D space. To this end, we use a stereo camera system to detect and track the human pose with deep neural networks. During pose estimation, these twin deep neural networks satisfy the stereo consistence constraint. We adapt the existing SocialGAN method to perform pedestrian motion trajectory prediction from the 2D to the 3D space. Our extensive experimental results demonstrate that our proposed method significantly improves the pedestrian trajectory prediction performance, outperforming existing state-of-the-art methods.more » « less
-
Human emotions are expressed through multiple modalities, including verbal and non-verbal information. Moreover, the affective states of human users can be the indicator for the level of engagement and successful interaction, suitable for the robot to use as a rewarding factor to optimize robotic behaviors through interaction. This study demonstrates a multimodal human-robot interaction (HRI) framework with reinforcement learning to enhance the robotic interaction policy and personalize emotional interaction for a human user. The goal is to apply this framework in social scenarios that can let the robots generate a more natural and engaging HRI framework.more » « less
-
Abstract Effective interactions between humans and robots are vital to achieving shared tasks in collaborative processes. Robots can utilize diverse communication channels to interact with humans, such as hearing, speech, sight, touch, and learning. Our focus, amidst the various means of interactions between humans and robots, is on three emerging frontiers that significantly impact the future directions of human–robot interaction (HRI): (i) human–robot collaboration inspired by human–human collaboration, (ii) brain-computer interfaces, and (iii) emotional intelligent perception. First, we explore advanced techniques for human–robot collaboration, covering a range of methods from compliance and performance-based approaches to synergistic and learning-based strategies, including learning from demonstration, active learning, and learning from complex tasks. Then, we examine innovative uses of brain-computer interfaces for enhancing HRI, with a focus on applications in rehabilitation, communication, brain state and emotion recognition. Finally, we investigate the emotional intelligence in robotics, focusing on translating human emotions to robots via facial expressions, body gestures, and eye-tracking for fluid, natural interactions. Recent developments in these emerging frontiers and their impact on HRI were detailed and discussed. We highlight contemporary trends and emerging advancements in the field. Ultimately, this paper underscores the necessity of a multimodal approach in developing systems capable of adaptive behavior and effective interaction between humans and robots, thus offering a thorough understanding of the diverse modalities essential for maximizing the potential of HRI.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TCYB.2018.2878977
