Author name cluster

Wentong Cai

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AIJ Journal 2024 Journal Article

A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees

Xiaoyu He
Xueyan Tang
Wentong Cai
Jingning Li

Multi-agent path finding (MAPF) is a classical NP-hard problem that considers planning collision-free paths for multiple agents simultaneously. A MAPF problem is typically solved via addressing a sequence of single-agent path finding subproblems in which well-studied algorithms such as A ⁎ are applicable. Existing methods based on this idea, however, rely on an exhaustive search and therefore only have asymptotic performance guarantees. In this article, we provide a modeling paradigm that converts a MAPF problem into a stochastic process and adopts a confidence bound based rule for finding the optimal state transition strategy. A randomized algorithm is proposed to solve this stochastic process, which combines ideas from conflict based search and Monte Carlo tree search. We show that the proposed method is almost surely optimal while enjoying non-asymptotic performance guarantees. In particular, the proposed method can, after solving N single-agent subproblems, produce a feasible solution with suboptimality bounded by O ( 1 / N ). The theoretical results are verified by several numerical experiments based on grid maps.

Details DOI

AAAI Conference 2023 Conference Paper

Crowd-Level Abnormal Behavior Detection via Multi-Scale Motion Consistency Learning

Linbo Luo
Yuanjing Li
Haiyan Yin
Shangwei Xie
Ruimin Hu
Wentong Cai

Detecting abnormal crowd motion emerging from complex interactions of individuals is paramount to ensure the safety of crowds. Crowd-level abnormal behaviors (CABs), e.g., counter flow and crowd turbulence, are proven to be the crucial causes of many crowd disasters. In the recent decade, video anomaly detection (VAD) techniques have achieved remarkable success in detecting individual-level abnormal behaviors (e.g., sudden running, fighting and stealing), but research on VAD for CABs is rather limited. Unlike individual-level anomaly, CABs usually do not exhibit salient difference from the normal behaviors when observed locally, and the scale of CABs could vary from one scenario to another. In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net). MSMC-Net first captures the spatial and temporal crowd motion consistency information in a graph representation. Then, it simultaneously trains multiple feature graphs constructed at different scales to capture rich crowd patterns. An attention network is used to adaptively fuse the multi-scale features for better CAB detection. For the empirical study, we consider three large-scale crowd event datasets, UMN, Hajj and Love Parade. Experimental results show that MSMC-Net could substantially improve the state-of-the-art performance on all the datasets.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Minimising Task Tardiness for Multi-Agent Pickup and Delivery

Saravanan Ramanathan
Yihao Liu
Xueyan Tang
Wentong Cai
Jingning Li

Multi-agent pickup and delivery, a variant of the multi-agent path finding problem, aims to find collision-free paths for a set of agents performing a continuous stream of pickup and delivery tasks. Owing to the service guarantee nature of applications, these agents often need to execute the tasks within their stipulated deadlines. When failure to meet task deadlines is unavoidable, there is a need to minimise the tardiness experienced by the tasks. To address this problem, we propose a cost-based integrated task assignment and path planning algorithm to assign tasks to the agents.

PDF

AAMAS Conference 2016 Conference Paper

A Hyper-Heuristic Framework for Agent-Based Crowd Modeling and Simulation (Extended Abstract)

Jinghui Zhong
Wentong Cai

This paper proposes a hyper-heuristic crowd modeling framework to generate realistic crowd dynamics that can match video data. In the proposed framework, motions of agents are driven by a high-level heuristic (HH) which intelligently selects way-points for agents based on the current situations. Three low-level heuristics are defined and used as building blocks of the HH. Based on the newly defined building blocks and fitness evaluation function, the Self-Learning Gene Expression Programming (SL-GEP) is utilized to automatically evolve a suitable HH. To test its effectiveness, the proposed framework is applied to learn suitable HHs based on real video data. The best HH learned is then applied to generate crowd simulations and the simulation results demonstrate that the proposed method is effective to generate realistic crowd dynamics.

PDF

JAAMAS Journal 2016 Journal Article

Learning behavior patterns from video for agent-based crowd modeling and simulation

Jinghui Zhong
Wentong Cai
Mingbi Zhao

Abstract This paper proposes a novel data-driven modeling framework to construct agent-based crowd model based on real-world video data. The constructed crowd model can generate crowd behaviors that match those observed in the video and can be used to predict trajectories of pedestrians in the same scenario. In the proposed framework, a dual-layer architecture is proposed to model crowd behaviors. The bottom layer models the microscopic collision avoidance behaviors, while the top layer models the macroscopic crowd behaviors such as the goal selection patterns and the path navigation patterns. An automatic learning algorithm is proposed to learn behavior patterns from video data. The learned behavior patterns are then integrated into the dual-layer architecture to generate realistic crowd behaviors. To validate its effectiveness, the proposed framework is applied to two different real world scenarios. The simulation results demonstrate that the proposed framework can generate crowd behaviors similar to those observed in the videos in terms of crowd density distribution. In addition, the proposed framework can also offer promising performance on predicting the trajectories of pedestrians.

Details DOI