In recent years, utility optimization and fairness have emerged as key objectives in spatial-temporal resource allocation systems, such as ridesharing and food delivery, attracting significant research interest due to their often conflicting nature. Systems focused solely on optimizing utility can create disparities, such as disparate earnings among rideshare drivers, leading to ethical and economic issues. Conversely, focusing solely on fairness can paradoxically reduce overall utility, resulting in a scenario where no one truly benefits. To address this, many Reinforcement Learning (RL)-based approaches have been proposed due to its capacity to generate dynamic, non-myopic allocation plans. Typically, RL-based approaches balance utility and fairness by constructing direct trade-off functions between them. However, this paper argues that in dynamic situations, the scale of the objectives may differ significantly, causing RL to overemphasize one objective at the expense of the other. To effectively address this issue, we propose formulating the challenge of balancing utility and fairness in spatial-temporal resource allocation as a Constrained Markov Decision Process. Here, fairness is treated as a constraint while utility optimization serves as the standard reward. Building on this foundation, we introduce Dynamic Budgeted Proximal Policy Optimization (DB-PPO). We demonstrate that DB-PPO outperforms existing approaches in fairness-oriented spatial-temporal resource allocations using two real-world publicly available datasets.

Dynamic Vehicle Routing Problem (DVRP), is an extension of the classic Vehicle Routing Problem (VRP), which is a fundamental problem in logistics and transportation. Typically, DVRPs involve two stakeholders: service providers that deliver services to customers and customers who raise requests from different locations. Many real-world applications can be formulated as DVRP such as ridesharing and non-compliance capture. Apart from original objectives like optimising total utility or efficiency, DVRP should also consider fairness for all parties. Unfairness can induce service providers and customers to give up on the systems, leading to negative financial and social impacts. However, most existing DVRP-related applications focus on improving fairness from a single side, and there have been few works considering two-sided fairness and utility optimisation concurrently. To this end, we propose a novel framework, a Two-sided Fairness-aware Genetic Algorithm (named 2FairGA), which expands the genetic algorithm from the original objective solely focusing on utility to multi-objectives that incorporate two-sided fairness. Subsequently, the impact of injecting two fairness definitions into the utility-focused model and the correlation between any pair of the three objectives are explored. Extensive experiments demonstrate the superiority of our proposed framework compared to the state-of-the-art.

Event cameras are recent sensors that measure intensity changes in each pixel asynchronously. It is being used due to lower latency and higher temporal resolution compared to traditional frame-based camera. We propose a method of 3D model-based object tracking directly from events captured by event camera. To enable reliable and accurate tracking of objects, we use a new event representation and predict brightness increment images with motion interpolation. Results of object tracking show the new methods significantly improves tracking duration and robustness, both for perspective and fisheye cameras. Our implementation succeeds in tracking objects when the camera speed is reaching 2 m/s.

Accuracy and timeliness are indeed often conflicting goals in prediction tasks.Premature predictions may yield a higher rate of false alarms, whereas delaying predictions to gather more information can render them too late to be useful.In applications such as wildfires, crimes, and traffic jams, timely forecasting are vital for safeguarding human life and property.Consequently, finding a balance between accuracy and timeliness is crucial.In this paper, we propose an early spatio-temporal forecasting model based on Multi-Objective reinforcement learning that can either implement an optimal policy given a preference or infer the preference based on a small number of samples.The model addresses two primary challenges: 1) enhancing the accuracy of early forecasting and 2) providing the optimal policy for determining the most suitable prediction time for each area.Our method demonstrates superior performance on three large-scale real-world datasets, surpassing existing methods in early spatio-temporal forecasting tasks.

Given the increasing importance of predicting spatiotemporal events such as wildfire, crime, and traffic congestion, existing methods are faced with the challenge of balancing timeliness and accuracy. Late predictions may result in tremendous economic costs and human life loss, while inaccurate predictions are likely to cause unnecessary public resources and social anxiety. Therefore, balancing accuracy and timeliness is essential in general spatiotemporal event prediction problems. In this paper, we propose an Early Spatiotemporal Graph Convolutional Network (ESTGCN)1to adaptively determine the optimal prediction time, which makes a tradeoff between prediction accuracy and timeliness and addresses two major questions: 1) How can we determine optimal prediction time points for different areas, taking into account their unique characteristics and conditions? 2) How can we minimize the propagation of prediction errors throughout the forecast timeline? Extensive experiments on two large-scale real-world datasets demonstrate that our proposed approaches can give an optimal prediction time in advance for each area and outperform all baselines in early spatiotemporal prediction tasks.

Many real-world ubiquitous applications, such as parking recommendations and air pollution monitoring, benefit significantly from accurate long-term spatio-temporal forecasting (LSTF). LSTF makes use of long-term dependency structure between the spatial and temporal domains, as well as the contextual information. Recent studies have revealed the potential of multi-graph neural networks (MGNNs) to improve prediction performance. However, existing MGNN methods do not work well when applied to LSTF due to several issues: the low level of generality, insufficient use of contextual information, and the imbalanced graph fusion approach. To address these issues, we construct new graph models to represent the contextual information of each node and exploit the long-term spatio-temporal data dependency structure. To aggregate the information across multiple graphs, we propose a new dynamic multi-graph fusion module to characterize the correlations of nodes within a graph and the nodes across graphs via the spatial attention and graph attention mechanisms. Furthermore, we introduce a trainable weight tensor to indicate the importance of each node in different graphs. Extensive experiments on two large-scale datasets demonstrate that our proposed approaches significantly improve the performance of existing graph neural network models in LSTF prediction tasks.

Traveling Salesman Problem (TSP) is a classic NP-hard problem in Combinatorial Optimization (CO), which has been widely studied. Traveling Officer Problem (TOP) derived from illegal parking in urban areas is a variant of TSP. Its solution aims to capture as many illegally parked vehicles as possible in a limited time. However, traditional methods of solving TSP cannot be applied to TOP because the illegally parked vehicle may leave before the officer arrives. Existing methods to solve TOP include heuristic search and deep learning algorithms such as ant colony optimization and feed-forward neural network. However, the performance based on capture rate and traveling distance of these algorithms is still comparably low. Hence, in this paper, we propose the heterogeneous pointer network to address this problem by modifying the encoder of the traditional pointer network to suit the spatial-temporal features of TOP. We conduct experiments using real-world datasets from Melbourne open data platform to show that our method achieves significant improvement and outperforms the existing algorithms based on capture rate and traveling distance.