Fumin Zhang
YOU?
Author Swipe
View article: Discovery of the reward function for embodied reinforcement learning agents
Discovery of the reward function for embodied reinforcement learning agents Open
Reward maximization is a fundamental principle in both the survival and evolution of biological organisms. In particular, in the contexts of cognitive science and embodied agents, reward-driven behavior has been widely regarded as importan…
View article: Experimental study on creep mechanical properties and failure modes of anthracite in dry and saturated states
Experimental study on creep mechanical properties and failure modes of anthracite in dry and saturated states Open
Water is crucial to the durability and safety of underground engineering. To investigate the effect of long-term goaf water infiltration on creep characteristics and long-term stability of the No.3 anthracite pillar in the Qinshui coalfiel…
View article: Epidemiological, etiological, and serological characteristics of hand, foot, and mouth disease in Guizhou Province, Southwest China, from 2008 to 2023
Epidemiological, etiological, and serological characteristics of hand, foot, and mouth disease in Guizhou Province, Southwest China, from 2008 to 2023 Open
Background Hand, foot, and mouth disease (HFMD) is caused by more than 20 different enteroviruses (EVs). The predominant EV serotypes of HFMD have been continuously changing in recent years. Guizhou Province has reported higher rates of se…
View article: Dynamics of HLB Transmission: Integrating Saturated Removal and Vector Bias in Spatial/Non-Spatial Models
Dynamics of HLB Transmission: Integrating Saturated Removal and Vector Bias in Spatial/Non-Spatial Models Open
Huanglongbing (HLB), a globally devastating citrus disease, demands sophisticated mathematical modeling to decipher its complex transmission dynamics and inform optimized disease management protocols. This investigation develops an innovat…
View article: Design of a Formation Control System to Assist Human Operators in Flying a Swarm of Robotic Blimps
Design of a Formation Control System to Assist Human Operators in Flying a Swarm of Robotic Blimps Open
Formation control is essential for swarm robotics, enabling coordinated behavior in complex environments. In this paper, we introduce a novel formation control system for an indoor blimp swarm using a specialized leader-follower approach e…
View article: SLABIM: A SLAM-BIM Coupled Dataset in HKUST Main Building
SLABIM: A SLAM-BIM Coupled Dataset in HKUST Main Building Open
Existing indoor SLAM datasets primarily focus on robot sensing, often lacking building architectures. To address this gap, we design and construct the first dataset to couple the SLAM and BIM, named SLABIM. This dataset provides BIM and SL…
View article: Neural Network-based Stability Guarantee for Dissensus Opinion Behaviors on the Sphere
Neural Network-based Stability Guarantee for Dissensus Opinion Behaviors on the Sphere Open
In this paper, we develop a neural network-based method to study opinion behaviors under a covariance-based dissensus algorithm. Driven by this dissensus algorithm, the opinions are updated based on relative interactions and gradually conv…
View article: Opinion-Based Task Allocation for Distributed Mobile Robot Swarms under Minimum Robot Requirements
Opinion-Based Task Allocation for Distributed Mobile Robot Swarms under Minimum Robot Requirements Open
We introduce an opinion dynamics-based approach to Multi-Robot Task Allocation (MRTA), modeling task assignment as a convergence process of continuously evolving opinions. Our method integrates special task requirements, ensuring that each…
View article: Mori-zwanzig approach for belief abstraction with application to belief space planning
Mori-zwanzig approach for belief abstraction with application to belief space planning Open
We propose a learning-based method to extract symbolic representations of the belief state and its dynamics in order to solve planning problems in a continuous-state partially observable Markov decision processes (POMDP) problem. While exi…
View article: Analysis of Huanglongbing transmission model with vector preferences and heterogeneous environments
Analysis of Huanglongbing transmission model with vector preferences and heterogeneous environments Open
The world citrus industry is confronting an unprecedented challenge from citrus Huanglongbing (HLB). With no resistant commercial citrus varieties or curable chemicals currently available, HLB remains the top threat to the world citrus ind…
View article: R&D of a Micro-Sized AUV for Quasi-Real-Time In-Situ Monitoring of Coral Reefs
R&D of a Micro-Sized AUV for Quasi-Real-Time In-Situ Monitoring of Coral Reefs Open
Coral reefs, as one of the most valuable ecosystems on Earth, are facing unprecedented threats. This paper introduces the R&D of a micro-sized autonomous underwater vehicle (AUV) specifically designed for coral reef monitoring, CoralBuddy-…
View article: Dynamic event-triggered integrated task and motion planning for process-aware source seeking
Dynamic event-triggered integrated task and motion planning for process-aware source seeking Open
The process-aware source seeking (PASS) problem in flow fields aims to find an informative trajectory to reach an unknown source location while taking the energy consumption in the flow fields into consideration. Taking advantage of the dy…
View article: A Hybrid Controller Design for Human-Assistive Piloting of an Underactuated Blimp
A Hybrid Controller Design for Human-Assistive Piloting of an Underactuated Blimp Open
This paper introduces a novel solution to the manual control challenge for indoor blimps. The problem's complexity arises from the conflicting demands of executing human commands while maintaining stability through automatic control for un…
View article: Distributed field mapping for mobile sensor teams using a derivative‐free optimisation algorithm
Distributed field mapping for mobile sensor teams using a derivative‐free optimisation algorithm Open
The authors propose a distributed field mapping algorithm that drives a team of robots to explore and learn an unknown scalar field using a Gaussian Process (GP). The authors’ strategy arises by balancing exploration objectives between are…
View article: OceanPlan: Hierarchical Planning and Replanning for Natural Language AUV Piloting in Large-scale Unexplored Ocean Environments
OceanPlan: Hierarchical Planning and Replanning for Natural Language AUV Piloting in Large-scale Unexplored Ocean Environments Open
We develop a hierarchical LLM-task-motion planning and replanning framework to efficiently ground an abstracted human command into tangible Autonomous Underwater Vehicle (AUV) control through enhanced representations of the world. We also …
View article: High-speed data transmission based on mode-locked optical frequency comb
High-speed data transmission based on mode-locked optical frequency comb Open
With the rapid development of emerging technologies such as multimedia services, live broadcasting, video conferencing, and high-definition television, traditional radio frequency communication is unable to meet people 's growing demand fo…
View article: Trust-Preserved Human-Robot Shared Autonomy enabled by Bayesian Relational Event Modeling
Trust-Preserved Human-Robot Shared Autonomy enabled by Bayesian Relational Event Modeling Open
Shared autonomy functions as a flexible framework that empowers robots to operate across a spectrum of autonomy levels, allowing for efficient task execution with minimal human oversight. However, humans might be intimidated by the autonom…
View article: OceanChat: Piloting Autonomous Underwater Vehicles in Natural Language
OceanChat: Piloting Autonomous Underwater Vehicles in Natural Language Open
In the trending research of fusing Large Language Models (LLMs) and robotics, we aim to pave the way for innovative development of AI systems that can enable Autonomous Underwater Vehicles (AUVs) to seamlessly interact with humans in an in…