This book constitutes the refereed proceedings of the 6th China Intelligent Robotics Annual Conference on Intelligent Robotics, CIRAC 2025, held in Nantong, China, during September 2022, 2025.

The 12 full papers and 3 short papers presented in this volume were carefully reviewed and selected from 26 submissions.

They are grouped into the following topics: UAV Technology; Robot Mechanism & Control; SLAM & Visual Navigation; Medical Robotics & Perception; Robotic Radar Perception.

Inhalt

.- UAV Technology.

.- Learning Attitude and Airspeed Control for Minimum-Time Flight of Fixed-Wing UAVs.

.- Robust UAV Multi-Object Tracking via Enhanced BoT-SORT with Altitude-Modulated Association and Occlusion Recovery.

.- Robot Mechanism & Control.

.- Bioinspired Design and Analysis of a Spherical Parallel Mechanism.

.- Design and flexibility analysis of puncture guide mechanism based on flexible hinge.

.- A Screw Theory Based Semi-Analytical Method for Elastodynamics Modeling of the 2-Limb 4-DOF High-Speed Parallel Robot.

.- Adaptive asymptotic tracking control for flexible-joint robots with random noises and dead-zone output.

.- SLAM & Visual Navigation.

.- Visual Navigation of Nonholonomic Mobile Robots under Low-Light Environments by Novel Integrated YOLightner Architecture.

.- FlexiSLAM: Semantic-Geometric Collaborative Filtering for Dynamic Object Rejection.

.- DynaGaussian-SLAM: Lightweight Dynamic Visual SLAM with 3D Gaussian Splatting.

.- Medical Robotics & Perception.

.- Video Segmentation of Deformable Instruments in Ultrasound-guided Interventional Surgeries for Structural Heart Diseases.

.- A Structured Representation Learning Framework for Medical Assistant Robotics via Heterogeneous Graph Transformers.

.- Diffusion-Aware Multi-View Hypergraph Representation Learning Model for Intelligent Medical Robotics.

.- Smart Insole Plantar Pressure Measurement Based on CNNBiLSTMAttention Network for Walking-Aid Robots.

.- Robotic Radar Perception.

.- CFFANet: A Frequency-Enhanced and Context-Aware Network for Robust Robot Perception Using mmWave Radar.

.- GAU-Net: A Feature Enhancement Network for Hand Gesture Recognition Using Millimeter-Wave Radar Point Clouds.