Submitted successfully

Special Session

 

 

  Special Session Ⅰ: Embodied Intelligence-Driven Marine Remote Sensing and Underwater Visual Perception

 

Session Chairs:  Jieyu Yuan, Nankai University, China

                                   Chongyi Li, Nankai University, China

 

Keywords: Underwater Vision, Underwater Vision, Multimodal Perception, 3D Reconstruction, Visual Navigation, Dataset and Benchmarking

 

Information: 

This special topic focuses on embodied intelligence-driven perception and modeling for marine remote sensing and underwater visual observation. It addresses key challenges in complex marine environments, including imaging degradation, multi-scale target perception, scene understanding, and 3D environmental modeling. The scope covers marine and underwater imaging modeling, multimodal data fusion, object detection and semantic understanding, 3D reconstruction and real-time rendering, underwater visual navigation and localization, as well as dataset construction, simulation systems, and benchmarking. The goal is to promote the development and real-world deployment of AI-driven marine and underwater visual perception technologies.

 

Topics of interest include but are not limited to:

 

  • Degradation Modeling, Denoising, Enhancement, and Optical Correction for Marine Remote Sensing and Underwater Imaging

  • Marine Imaging Technologies and Multimodal Perception and Fusion Methods

  • Marine and Underwater Object Detection, Recognition, and Classification

  • Underwater Scene Understanding and Semantic/Instance Segmentation

  • 3D Reconstruction, Modeling, and Real-Time Rendering of Marine Environments

  • Underwater Visual Navigation, Localization, and Environmental Mapping

  • Lightweight and Real-Time Algorithms for Marine Visual Perception

  • Large Language Models and Foundation Models for Marine Visual Perception, Understanding, and Cross-Modal Analysis

  • Marine and Underwater Vision Datasets, Simulation Systems, and Benchmarking

  • Quality Assessment and Evaluation of Marine Environment Understanding and Underwater Visual Perception

 

  Special Session Ⅱ: Brain-Inspired Robot Visual Detection and Spatial Perception

 

Session Chairs:  Mingliang Zhou, Chongqing University, China

                                   Xuekai Wei, Chongqing University, China

 

Keywords: Robot Vision, Object Detection, Spatial Perception, Brain-Inspired Computing, Visual Processing, Spatial Memory

 

Information: 

This session focuses on leveraging insights from neural mechanisms of the human brain to overcome key challenges in robot visual detection and spatial perception. It explores how brain-inspired principles such as visual processing pathways, spatial memory formation, and attentional modulation can be incorporated into the design of robotic visual detection and spatial perception models. The session emphasizes the potential of brain-inspired approaches to improve object detection accuracy, 3D spatial understanding in complex environments, robust navigation, and dexterous manipulation, thereby enabling a shift from passive sensing to active perception and intelligent decision-making, and fostering more natural and efficient human-robot collaboration.

 

Topics of interest include but are not limited to:

 

  • Brain-Inspired Object Detection Methods for Robots

  • Bio-Inspired Robot Perception and Environmental Understanding

  • Robot Spatial Reasoning and Autonomous Navigation

  • Scene Understanding by Integrating Visual and Spatial Relations

  • Active Visual Detection and Perception

  • Neuromorphic Vision Sensors Applications

  • Spiking Neural Networks for Visual Reasoning

  • Object Detection and Planning in Dynamic Environments

 

  Special Session Ⅲ: Machine Learning in the Era of Foundation Models: Toward Robotics and Beyond

 

Session Chairs:  Wenhui Wu, Shenzhen University, China

                                    Yuheng Jia, Southeast University, China

                                    Hu Liang, Qilu University of Technology, China

 

Keywords: Foundation Model, Machine Learning, Weakly-Supervised Learning, Supervised Learning, Representation Learning

 

Information: 

In recent years, the emergence of foundation models (FMs) has provided powerful new tools for machine learning, reshaping our research paradigms. This session aims to comprehensively cover the field of machine learning for robotics and beyond, spanning from the development of novel classical algorithms to the transformative impact of modern foundation models. We welcome submissions that advance both the theory and practice of traditional machine learning approaches, as well as those investigating how large-scale pre-training can lead to more robust and generalizable representations. We will pay particular attention to how these representations can revolutionize classical tasks such as clustering and classification, while also seeking new paradigms for tasks like anomaly detection and segmentation. Topics of interest include but are not limited to: theoretical foundations of machine learning, novel clustering and classification algorithms, weakly supervised representation learning, self-supervised methods for pre-training, and research applying foundation models to enhance machine learning tasks, particularly in scenarios such as robotic perception, learning, and control. This session aims to provide a dissemination platform for cutting-edge research that pushes the boundaries of machine learning development across various domains.

 

Topics of interest include but are not limited to:

 

  • Theoretical Foundations of Machine Learning

  • Novel Clustering and Classification Algorithms

  • Innovations in Classical Machine Learning Tasks

  • Weakly Supervised Representation Learning

  • Machine Learning Algorithms for Foundation Models

  • Applied Research in Machine Learning

  • Machine Learning for Complex Data

  • Trustworthy Machine Learning

  • Machine Learning for Robotics

 

Special Session Ⅳ: Reinforcement Learning for Control and Decision-Making in Autonomous Robots

 

Session Chairs:  Shan Xue, Hainan University, China

                                    Lu Dong, Southeast University, China

 

Keywords: Reinforcement Learning, Control and Decision-Making, Autonomous Robots, Adaptive Dynamic Programming, Multi-Agent Systems

 

Information: 

This special session, "Reinforcement Learning for Control and Decision-Making in Autonomous Robots," focuses on theoretical methods and practical applications of reinforcement learning in autonomous robotic systems. As robots operate in increasingly complex and dynamic environments, achieving efficient and robust control and decision-making becomes a central challenge. Reinforcement learning, as an interaction-based learning framework, provides essential tools for autonomous control and policy optimization, while multi-agent collaboration, distributed learning, and data-driven approaches offer solutions for decision-making in complex scenarios.
The session aims to bring together the latest advances in reinforcement learning, control theory, and decision-making, covering robotic control, planning, cooperation, multi-agent systems, and real-time decision-making in dynamic and complex environments. It provides a platform for academic and industrial exchange to promote intelligent control and decision-making technologies for autonomous robots.

 

Topics of interest include but are not limited to:

 

  • Reinforcement Learning for Control and Decision-Making

  • Adaptive Dynamic Programming

  • 3Multi-Agent Reinforcement Learning

  • Robotic Control and Planning

  • Safe Reinforcement Learning and Robust Control

  • Data-Driven Reinforcement Learning

 

  Special Session Ⅴ: Environmental Perception, Navigation, and Intelligent Operation for Underwater Robotics

 

Session Chairs:  Rongxin Zhang, Xiamen University, China

                                   Tiesong Zhao, Fuzhou University, China

                                    Ying Fang, Fuzhou University, China

 

Keywords: Underwater Robotics, Underwater Vision, Sonar Image Processing, Underwater Image Enhancement, Underwater Object Detection

 

Information: 

Underwater robotics is a vital branch of service robots, playing irreplaceable roles in ocean exploration, environmental monitoring, infrastructure maintenance, and rescue operations. However, the complex underwater environment, characterized by optical scattering, absorption, and acoustic propagation challenges, severely impedes the "eyes" of robots—their visual and sonar perception systems. This special session aims to gather the latest research advances in this field, focusing on environmental perception and understanding technologies crucial for underwater robots. Key topics include enhancement, restoration, quality assessment, object detection, and scene understanding for underwater optical and sonar imagery, extending to robust perception-based underwater SLAM, path planning, and intelligent manipulation. We invite researchers to contribute and discuss how to advance the perceptual and operational capabilities of underwater robots in complex real-world scenarios.

 

Topics of interest include but are not limited to:

 

  • Underwater Optical Image Enhancement and Restoration

  • Underwater Acoustic (Sonar) Image Processing and Interpretation

  • Underwater Image Quality Assessment and Benchmarks

  • Underwater Object Detection, Recognition, and Tracking

  • Underwater SLAM (Simultaneous Localization and Mapping)

 

  Special Session Ⅵ: Bio-inspired Design, Perception, Learning and Control to Improve Robotic Dexterity

 

Session Chairs:  Longhui Qin, Southeast University, China

                                   Chao Ma, Xi'an Jiaotong University, China

 

Keywords: Dexterous Hand, Sensors or Actuators, Bio-inspired Design, Machine Learning Algorithms, Learning from Demonstration, Soft Robotics

 

Information: 

To endow robots with human-level dexterity, bio-inspired design of various arms, end-effectors, sensors and actuators, and robotic systems are usually indispensable, which also motivates the emergence of abundant novel mechanisms, methods, and models in robotic perception, learning and control. In this session, we welcome multidisciplinary insights that try to address the challenges in the field of robotic manipulation. From the perspective of novel designs, it not only focuses on innovative designs of robotic components, e.g., fingers, grippers, hands and legs, but also involves multifarious sensors and actuators based on different principles, such as tactile, olfactory, visual and temperature sensors, and electrical, pneumatic, hydraulic and thermal actuators. Meanwhile, a mass of efforts is being increasingly devoted to the development of perception methods and control models in combination of state-of-the-art machine learning algorithms. In addition, investigations on how to learn from human demonstrations effectively also receive intense attentions. All relevant researchers are sincerely welcome to join us in this session to advance the theories and techniques of robotic dexterity. 

 

Topics of interest include but are not limited to:

 

  • Novel Design of Robotic Components as well as Their Kinematic and Dynamic Modeling

  • Soft Robotics, Bio-inspired Robotic Designs, and Advanced Actuators

  • Sensor Design, Sensor Network Construction, Perception Methods, and Data Fusion Algorithms

  • Wearable Electronics, Haptic Glove, Motion Capture System or Other Designs for Human Motion Measurement or Tracking

  • Learning Methods from Demonstration

  • Human-robot Interaction or Collaboration

  • Learning Algorithms Related to Robotic Manipulation or Locomotion

  • Control Models for Robotic Manipulation, Locomotion, Jumping and so on

  • Applications Related to Home Service Robots, Agricultural Robots, Medical robots, and Robotic Assembly, etc.

  • Embodied-intelligence Techniques Related to Robotic Dexterity

 

  Special Session Ⅶ: Human-Robot Collaboration in Intelligent Manufacturing

 

Session Chairs:  Jin Yi, Chongqing University, China

                                   Chao Lu, China University of Geosciences, China

 

Keywords: Human-Robot Collaboration, Intelligent Manufacturing, Task Assignment and Scheduling, Ergonomics, Embodied Intelligence

 

Information: 

The integration of advanced robotics into intelligent manufacturing is driving a profound transition from rigid, isolated automation to highly flexible, human-centric production systems. In this context, the boundary between traditional industrial automation and service robotics is rapidly blurring. Service robots equipped with embodied perception, such as mobile manipulators and interactive assembly assistants, are increasingly deployed on factory floors to collaborate directly with human operators. This paradigm of Human-Robot Collaboration (HRC) has the potential to significantly enhance productivity, address the challenges of high-mix low-volume production, and ensure occupational safety.

However, realizing fluid and efficient HRC presents complex theoretical and engineering challenges. Collaborative systems must evolve beyond simple collision avoidance to achieve deep cognitive understanding, ergonomics-aware task planning, and adaptive execution. This special session aims to gather cutting-edge research at the intersection of robotics, operational scheduling, and human factors. We invite researchers and engineers to contribute their latest findings on how to advance the perceptual, operational, and collaborative capabilities of robots to realize true human-machine symbiosis in complex manufacturing scenarios.

 

Topics of interest include but are not limited to:

 

  • Human Action Intent Recognition and Cognitive State Prediction

  • Task Allocation and Multi-Objective Scheduling in HRC Workcells

  • Ergonomics-Aware Constraint Modeling and Evaluation for Collaborative Assembly

  • Intelligent Optimization Algorithms (e.g., RL, Swarm Intelligence) for Manufacturing Workflows

  • Embodied Intelligence and Dexterous Manipulation in Contact-Rich Tasks

  • Multi-Fidelity Surrogate Modeling and Digital Twins for Human-Robot Environments

 

  Special Session Ⅷ: Target Detection, Tracking, and Public Opinion Analysis

 

Session Chairs:  Xuzhen Zhu, Beijing University of Posts and Telecommunications, China

                                   Zengping Zhang, Inner Mongolia University of Finance and Economics, China

                                   Tieliang Gao, Xinxiang University, China

                                   Yajuan Cui, Zhengzhou University of Light Industry, China

 

Keywords: Machine Vision, Target Detection, Multimodal, Target Tracking, Target Localization, Temporal Synchronization, Public Opinion Analysis, Space-Air-Ground Integrated

 

Information: 

This special topic, "Machine Vision, Object Detection & Tracking, and Public Opinion Analysis," focuses on cutting-edge interdisciplinary research in computer vision, social computing, and spatial information technology. It systematically explores the core advances, key challenges, and innovative applications of three independent technical directions: "Machine Vision," "Public Opinion Analysis," and "Integrated Space-Air-Ground."
The Machine Vision direction delves into the fundamental theories and key technologies of machine vision, primarily encompassing object detection, object tracking, and object localization tasks. It emphasizes research on breakthrough methods to enhance algorithm robustness, real-time performance, and accuracy under complex scenarios. Core topics include: efficient fusion strategies for multi-modal sensing (visible light, infrared, radar, depth, etc.) data and their application in vision tasks; the critical role of time synchronization technology in continuous frame processing and multi-source sensor data fusion, ensuring spatiotemporal consistency of perception results. Typical applications involve intelligent surveillance, autonomous driving, robot navigation, human-computer interaction, and smart cities.
The Public Opinion Analysis direction is dedicated to the theoretical, methodological, and systemic research of public opinion analysis. Its core lies in accurately perceiving, deeply understanding, and predicting the evolutionary trends of social sentiment from massive, multi-source, heterogeneous network data (text, images, videos, social relationships, etc.). Key research focuses on core technologies including public opinion information extraction, sentiment analysis, opinion mining, propagation modeling, influence assessment, event evolution analysis, and false information detection. The research integrates big data analytics, natural language processing, social network analysis, and machine learning to provide intelligent support for insights into public sentiment, social hotspots, brand reputation, and policy feedback. Application scenarios primarily include social governance, brand management, market research, crisis warning, and public service optimization.
The Integrated Space-Air-Ground direction concentrates on the construction challenges and applications of integrated space-air-ground networks and systems. Core research investigates how to collaboratively integrate the sensing, communication, and computing resources of space-based (satellites), air-based (UAVs, etc.), and ground-based platforms to achieve collaborative intelligence over wide areas. Key topics include: novel object detection, tracking, and localization methods for space-air-ground collaborative environments; fusion processing and analysis techniques for multi-source, multi-modal (optical, SAR, hyperspectral, signals, etc.) data from space, air, and ground; high-precision time synchronization and spatial registration technologies under wide-area distributed systems. Typical applications encompass large-scale environmental and disaster monitoring, wide-area object search and tracking, smart city three-dimensional sensing, and national security domains.

 

Topics of interest include but are not limited to:

 

  • Object Detection Algorithm Optimization

  • Multimodal Data Fusion

  • Real-Time Object Tracking Techniques

  • Multiple Object Perception and Tracking

  • Multi-Sensor Temporal Synchronization and Calibration

  • Multi-Source Heterogeneous Public Opinion Data Fusion and Representation Learning

  • Social Media Sentiment Analysis and Opinion Mining

  • Public Opinion Propagation Modeling and Influence Assessment

  • Cross-Modal Retrieval

  • Communication of SAGIN（Space-Air-Ground Integrated Network）

 

 Special Session Ⅸ: Intelligent Control and Decision Planning for Robots in Unstructured Environments

 

Session Chairs:  Yifan Liu, South China University of Technology, China

                                   Changxin Huang, Shenzhen University, China

 

Keywords: Intelligent Robotics, Unstructured Environments, Autonomous Navigation, Machine Learning, Embodied Intelligence, Intelligent Control, Decision Planning

 

Information: 

In recent years, service robots have achieved remarkable progress in structured environments. However,  robot motion control and decision planning in unstructured environments, such as outdoor and field scenarios, encounter challenges due to the dynamic environmental changes, complex and diverse scenes, limited prior information, and high uncertainty. To address these challenges, this special session, titled "Intelligent Control and Decision Planning for Robots in Unstructured Environments," aims to bring together the latest research advances in this field, including robot motion control, robot planning and decision-making, autonomous navigation, adaptive control, and machine learning. In addition, we will place particular emphasis on the application of emerging technologies, such as embodied intelligence, in unstructured environments. We sincerely welcome researchers from related fields to contribute and jointly explore approaches to enhancing the control and planning capabilities of robots operating in unstructured environments.

 

Topics of interest include but are not limited to:

 

  • Field Robotics

  • Robust/Adaptive Control in Uncertain Environments

  • Reinforcement Learning-based Control, Planning & Decision-Making

  • Autonomous Robot Navigation

  • Sim-to-Real Policy Transfer

  • Embodied Intelligence

  • Imitation Learning / Self-Supervised Learning

  • Autonomous Robotic Manipulation and Compliant Control

 

More conference sessions to be updated soon.