Search for: All records

Location-Based Social Network (LBSN) check-in trajectory data are important for many practical applications like POI recommendation, advertising, and pandemic intervention. However, the high collection costs and ever-increasing privacy concerns prevent us from accessing large-scale LBSN trajectory data. The recent advances in synthetic data generation provide us with a new opportunity to achieve this, which utilizes generative AI to generate synthetic data that preserves the characteristics of real data while ensuring privacy protection. However, generating synthetic LBSN check-in trajectories remains challenging due to their spatially discrete, temporally irregular nature and the complex spatio-temporal patterns caused by sparse activities and uncertain human mobility. To address this challenge, we propose GeoGen, a two-stage coarse-to-fine framework for large-scale LBSN check-in trajectory generation. In the first stage, we reconstruct spatially continuous, temporally regular latent movement sequences from the original LBSN check-in trajectories and then design a Sparsity-aware Spatio-temporal Diffusion model (S^2TDiff) with an efficient denosing network to learn their underlying behavioral patterns. In the second stage, we design Coarse2FineNet, a Transformer-based Seq2Seq architecture equipped with a dynamic context fusion mechanism in the encoder and a multi-task hybrid-head decoder, which generates fine-grained LBSN trajectories based on coarse-grained latent movement sequences by modeling semantic relevance and behavioral uncertainty. Extensive experiments on four real-world datasets show that GeoGen excels state-of-the-art models for both fidelity and utility evaluation, e.g., it increases over 69% and 55% in distance and radius metrics on the FS-TKY dataset. 

Order dispatch systems play a vital role in ride-hailing services, which directly influence operator revenue, driver profit, and passenger experience. Most existing work focuses on improving system efficiency in terms of operator revenue, which may cause a bad experience for both passengers and drivers. Hence, in this work, we aim to design a human-centered ride-hailing system by considering both passenger fairness and driver preference without compromising the overall system efficiency. However, it is nontrivial to achieve this target due to the potential conflicts between passenger fairness and driver preference since optimizing one may sacrifice the other. To address this challenge, we design HCRide, a Human-Centered Ride-hailing system based on a novel multi-agent reinforcement learning algorithm called Harmonization-oriented Actor-Bi-Critic (Habic), which includes three major components (i.e., a multi-agent competition mechanism, a dynamic Actor network, and a Bi-Critic network) to optimize system efficiency and passenger fairness with driver preference consideration. We extensively evaluate our HCRide using two real-world ride-hailing datasets from Shenzhen and New York City. Experimental results show our HCRide effectively improves system efficiency by 2.02%, fairness by 5.39%, and driver preference by 10.21% compared to state-of-the-art baselines. 

The field of human-robot interaction has been rapidly expanding but an ever-present obstacle facing this field is developing accessible, reliable, and effective forms of communication. It is often imperative to the efficacy of the robot and the overall human-robot interaction that a robot be capable of expressing information about itself to humans in the environment. Amidst the evolving approaches to this obstacle is the use of light as a communication modality. Light-based communication effectively captures attention, can be seen at a distance, and is commonly utilized in our daily lives. Our team explored the ways light-based signals on robots are being used to improve human understanding of robot operating state. In other words, we sought to determine how light-based signals are being used to help individuals identify the conditions (e.g., capabilities, goals, needs) that comprise and dictate a robot’s current functionality. We identified four operating states (e.g., “Blocked”, “Error”, “Seeking Interaction”, “Not Seeking Interaction”) in which light is utilized to increase individuals’ understanding of the robot’s operations. These operating states are expressed through manipulation of three visual dimensions of the onboard lighting features of robots (e.g., color, pattern of lighting, frequency of pattern). In our work, we outline how these dimensions vary across operating states and the effect they have on human understanding. We also provide potential explanations for the importance of each dimension. Additionally, we discuss the main shortcomings of this technology. The first is the overlapping use of combinations of dimensions across operating states. The remainder relate to the difficulties of leveraging color to convey information. Finally, we provide considerations on how this technology might be improved going into the future through the standardization of light-based signals and increasing the amount of information provided within interactions between agents.