Canjun Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Canjun Yang has a total of 237 co-authors. Here are the top co-authors by number of shared publications:
- Yanhu Chen
State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China
14 shared publications - Dejun Li
State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, China
10 shared publications - Shijun Wu
State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, China
10 shared publications - Wei Yang
State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou, China
10 shared publications - Mingwei Lin
State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, China
7 shared publications Yanhu Chen
7 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (22) , 2143
A Rigid-Compliant AUV Capture System with Hydraulic- Buffered Guidance and Endoskeleton-Reinforced Locking
Autonomous underwater vehicle (AUV) capture requires a mechanism to accommodate initial impact and then secure the hull through compliant contact. This study implements a rigid-compliant system that combines a hydraulic-buffered guidance dock with an endoskeleton-reinforced compliant locking mechanism. Building on an earlier numerical study of the guidance dock, the present work adds the locking mechanism, comparative component tests, and integrated water-tank experiments. Adams–AMESim co-simulation evaluates guidance and impact response, while Abaqus analysis and component tests assess the reinforcement effect. At 600 kPa, reinforcement increased the measured underwater vertical clamping force from 260 to 410 N, or 57.7%. Nine of ten tank trials established bow–dock contact at measured speeds of 0.76–0.85 m/s and completed guided buffering, pose adjustment, and locking; one trial missed the guidance region. The baseline simulation predicted a 94.8% reduction in peak contact force relative to a constrained unbuffered dock. The results demonstrate a staged capture system in which separate mechanisms accommodate initial impact and develop compliant clamping force, under fixed-platform, operator-supervised conditions.
- 11 November 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (22) , 2143
Open AccessA Rigid-Compliant AUV Capture System with Hydraulic- Buffered Guidance and Endoskeleton-Reinforced Locking
Autonomous underwater vehicle (AUV) capture requires a mechanism to accommodate initial impact and then secure the hull through compliant contact. This study implements a rigid-compliant system that combines a hydraulic-buffered guidance dock with an endoskeleton-reinforced compliant locking mechanism. Building on an earlier numerical study of the guidance dock, the present work adds the locking mechanism, comparative component tests, and integrated water-tank experiments. Adams–AMESim co-simulation evaluates guidance and impact response, while Abaqus analysis and component tests assess the reinforcement effect. At 600 kPa, reinforcement increased the measured underwater vertical clamping force from 260 to 410 N, or 57.7%. Nine of ten tank trials established bow–dock contact at measured speeds of 0.76–0.85 m/s and completed guided buffering, pose adjustment, and locking; one trial missed the guidance region. The baseline simulation predicted a 94.8% reduction in peak contact force relative to a constrained unbuffered dock. The results demonstrate a staged capture system in which separate mechanisms accommodate initial impact and develop compliant clamping force, under fixed-platform, operator-supervised conditions.
- 5 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 368
Online health monitoring framework of deep-sea UUVs via multi-sensor fusion and Koopman operator-based residual inference
- 5 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 368
Online health monitoring framework of deep-sea UUVs via multi-sensor fusion and Koopman operator-based residual inference
- 24 July 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37 (5) , 119
LLM-augmented semantic reasoning for robust AUV docking under uncertain environments
- 24 July 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37 (5) , 119
LLM-augmented semantic reasoning for robust AUV docking under uncertain environments
- 15 July 2026
- Published by Wiley in Journal of Field Robotics
Underwater Grippers for Dexterous Manipulation: A Review on Design and Enabling Technologies
With the advancement of deep‐sea resource exploration and scientific research, underwater operations are evolving from rough manipulation to precise and intelligent tasks, imposing higher demands on the dexterity and environmental adaptability of underwater grippers. However, existing reviews often focus on superficial classifications based on actuation modes or application scenarios, there by lacking in‐depth analysis grounded in robotic grasping theory and system‐level integration. This paper presents a comprehensive review of underwater dexterous grippers, proposing a novel classification framework based on the integration of force/form closure theory and energy input methods. Under this framework, we systematically analyze the structural designs and mechanisms of grippers ranging from Fully Passive to Fully Active configurations. Furthermore, the review delves into kinematic and dynamic modeling methodologies for rigid, continuum, and rigid‐continuum coupled structures, alongside the challenges and solutions for underwater tactile and deformation perception systems. We also examine control strategies, progressing from low‐level open‐loop control to model‐based intelligent approaches, including the dynamic coupling within vehicle‐manipulator‐gripper systems (UVMS). To address the lack of standardized benchmarking, this study establishes a unified evaluation system incorporating quantitative metrics (e.g., Load‐to‐Weight Ratio, Normalized Durability Index) and benchmark protocols, providing a multi‐dimensional comparative analysis of existing technologies. Finally, the paper identifies emerging trends, suggesting that bio‐inspired rigid‐soft hybrid designs, multimodal perception fusion, and hybrid modeling approaches combining Physics‐Informed Neural Networks with Computational Fluid Dynamics (PINN‐CFD) represent critical directions for achieving highly reliable and dexterous underwater manipulation.
- 15 July 2026
- Published by Wiley in Journal of Field Robotics
Underwater Grippers for Dexterous Manipulation: A Review on Design and Enabling Technologies
With the advancement of deep‐sea resource exploration and scientific research, underwater operations are evolving from rough manipulation to precise and intelligent tasks, imposing higher demands on the dexterity and environmental adaptability of underwater grippers. However, existing reviews often focus on superficial classifications based on actuation modes or application scenarios, there by lacking in‐depth analysis grounded in robotic grasping theory and system‐level integration. This paper presents a comprehensive review of underwater dexterous grippers, proposing a novel classification framework based on the integration of force/form closure theory and energy input methods. Under this framework, we systematically analyze the structural designs and mechanisms of grippers ranging from Fully Passive to Fully Active configurations. Furthermore, the review delves into kinematic and dynamic modeling methodologies for rigid, continuum, and rigid‐continuum coupled structures, alongside the challenges and solutions for underwater tactile and deformation perception systems. We also examine control strategies, progressing from low‐level open‐loop control to model‐based intelligent approaches, including the dynamic coupling within vehicle‐manipulator‐gripper systems (UVMS). To address the lack of standardized benchmarking, this study establishes a unified evaluation system incorporating quantitative metrics (e.g., Load‐to‐Weight Ratio, Normalized Durability Index) and benchmark protocols, providing a multi‐dimensional comparative analysis of existing technologies. Finally, the paper identifies emerging trends, suggesting that bio‐inspired rigid‐soft hybrid designs, multimodal perception fusion, and hybrid modeling approaches combining Physics‐Informed Neural Networks with Computational Fluid Dynamics (PINN‐CFD) represent critical directions for achieving highly reliable and dexterous underwater manipulation.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 10428-10437
Autonomous Target Tracking With Vision and Infrared Sensing Fusion in Rat Robots
Bio-robots, integrating brain-machine interface and living organisms, have demonstrated significant potential in post-disaster search and rescue missions due to their adaptability and sustained energy efficiency. Nevertheless, the acquisition and utilization of environmental information remain insufficient, and the level of operation automation in unknown environment still needs improvement. The reason for the lack of environmental sensing and automation primarily arises from the challenges associated with developing a multi-sensor-equipped electrical backpack and achieving stable autonomous navigation using the sensor data. To address this issue, we proposed a novel method for bio-robots to acquire image and infrared information, recognize and track targets autonomously in environment beyond visual range. A series of experiments were conducted to verify this method. This research enhances the environmental sensing capabilities of bio-robots and contributes to their practical application in search and rescue missions.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 10428-10437
Autonomous Target Tracking With Vision and Infrared Sensing Fusion in Rat Robots
Bio-robots, integrating brain-machine interface and living organisms, have demonstrated significant potential in post-disaster search and rescue missions due to their adaptability and sustained energy efficiency. Nevertheless, the acquisition and utilization of environmental information remain insufficient, and the level of operation automation in unknown environment still needs improvement. The reason for the lack of environmental sensing and automation primarily arises from the challenges associated with developing a multi-sensor-equipped electrical backpack and achieving stable autonomous navigation using the sensor data. To address this issue, we proposed a novel method for bio-robots to acquire image and infrared information, recognize and track targets autonomously in environment beyond visual range. A series of experiments were conducted to verify this method. This research enhances the environmental sensing capabilities of bio-robots and contributes to their practical application in search and rescue missions.
- 8 May 2026
- Published by Elsevier in Ocean Engineering
- Vol. 358
Multi-sensor fusion for autonomous vertical docking in kilometer-scale deep-sea environments
- 8 May 2026
- Published by Elsevier in Ocean Engineering
- Vol. 358
Multi-sensor fusion for autonomous vertical docking in kilometer-scale deep-sea environments
- 25 April 2026
- Published by Elsevier in Ocean Engineering
- Vol. 358
VVFGO: a robust IMU/AHRS/USBL integrated navigation framework with adaptive virtual velocity factor correction for deep-sea docking
- 25 April 2026
- Published by Elsevier in Ocean Engineering
- Vol. 358
VVFGO: a robust IMU/AHRS/USBL integrated navigation framework with adaptive virtual velocity factor correction for deep-sea docking
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7692-7699
Multi-Sensor Fusion and Multi-Agent Control for Autonomous Environmental Exploration With Rat Robots
This letter presents a bio-robotic multi-agent framework that integrates multi-sensor fusion with multi-agent control strategies for rat robots. The sensors equipped with rat robots, including laser-ranging sensor, camera and infrared sensor. We develop two multi-agent control strategies: a leader-follower strategy, in which one rat robot is designated as leader and utilizes lateral laser ranging sensor to navigate along boundaries, while others follow in formation; and a distributed strategy that enables all rat robots to perform decentralized decision-making exploration. The experimental platform consists of four rat robots operating in a confined indoor environment. Results demonstrate that multi-modal sensing significantly enhances environmental perception, particularly in confined and complex conditions; and both strategies provide stable and predictable cooperative motions and improves the efficiency and robustness of rat robot exploration. This work contributes an integrated bio-robotic multi-agent architecture that leverages multi-sensor perception and multi-agent control, offering a foundation for future applications in biological intelligence research, micro-scale environmental exploration and autonomous animal-machine systems.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7692-7699
Multi-Sensor Fusion and Multi-Agent Control for Autonomous Environmental Exploration With Rat Robots
This letter presents a bio-robotic multi-agent framework that integrates multi-sensor fusion with multi-agent control strategies for rat robots. The sensors equipped with rat robots, including laser-ranging sensor, camera and infrared sensor. We develop two multi-agent control strategies: a leader-follower strategy, in which one rat robot is designated as leader and utilizes lateral laser ranging sensor to navigate along boundaries, while others follow in formation; and a distributed strategy that enables all rat robots to perform decentralized decision-making exploration. The experimental platform consists of four rat robots operating in a confined indoor environment. Results demonstrate that multi-modal sensing significantly enhances environmental perception, particularly in confined and complex conditions; and both strategies provide stable and predictable cooperative motions and improves the efficiency and robustness of rat robot exploration. This work contributes an integrated bio-robotic multi-agent architecture that leverages multi-sensor perception and multi-agent control, offering a foundation for future applications in biological intelligence research, micro-scale environmental exploration and autonomous animal-machine systems.
- 30 March 2026
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 10 (2) , 764-778
Physics-informed compact world models for predictive control in AUV terminal docking under communication constraints
- 30 March 2026
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 10 (2) , 764-778
Physics-informed compact world models for predictive control in AUV terminal docking under communication constraints
- Open Access
- 27 March 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (7) , 622
Neural Network-Enhanced Robust Navigation for Vertical Docking of an Autonomous Underwater Shuttle Under USBL Outages
Vertical docking of the autonomous underwater shuttle (AUS) for deep-sea data relay relies heavily on ultra-short baseline (USBL) acoustic positioning, whose measurements can be intermittently unavailable and contaminated by outliers in complex underwater environments. This paper proposes a neural network-enhanced robust navigation framework to improve AUS navigation reliability during acoustically guided vertical docking under USBL outages. First, a model-aided batch maximum a posteriori trajectory estimation method (MA-BMAP) is developed to generate learning quality supervision under sensor-limited conditions. Based on the estimated trajectories, a long short-term memory (LSTM)-based horizontal velocity predictor is integrated into a robust fusion filter with online ocean current estimation, enabling stable state estimation during USBL outages and robust rejection of abnormal USBL measurements. The proposed framework is validated through simulations and field trials in lake and sea environments. In sea trials, during two representative 200 s USBL outage intervals, the end-of-window horizontal position errors are 7.86 m and 4.14 m, respectively, corresponding to AUS-to-docking station distances of 244 m and 51 m. In addition, the introduced USBL outliers are successfully detected and rejected. The results indicate that the proposed method enables accurate and stable navigation during USBL unavailability and rapid recovery once USBL measurements resume, demonstrating its practicality for vertical docking missions.
- 27 March 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (7) , 622
Open AccessNeural Network-Enhanced Robust Navigation for Vertical Docking of an Autonomous Underwater Shuttle Under USBL Outages
Vertical docking of the autonomous underwater shuttle (AUS) for deep-sea data relay relies heavily on ultra-short baseline (USBL) acoustic positioning, whose measurements can be intermittently unavailable and contaminated by outliers in complex underwater environments. This paper proposes a neural network-enhanced robust navigation framework to improve AUS navigation reliability during acoustically guided vertical docking under USBL outages. First, a model-aided batch maximum a posteriori trajectory estimation method (MA-BMAP) is developed to generate learning quality supervision under sensor-limited conditions. Based on the estimated trajectories, a long short-term memory (LSTM)-based horizontal velocity predictor is integrated into a robust fusion filter with online ocean current estimation, enabling stable state estimation during USBL outages and robust rejection of abnormal USBL measurements. The proposed framework is validated through simulations and field trials in lake and sea environments. In sea trials, during two representative 200 s USBL outage intervals, the end-of-window horizontal position errors are 7.86 m and 4.14 m, respectively, corresponding to AUS-to-docking station distances of 244 m and 51 m. In addition, the introduced USBL outliers are successfully detected and rejected. The results indicate that the proposed method enables accurate and stable navigation during USBL unavailability and rapid recovery once USBL measurements resume, demonstrating its practicality for vertical docking missions.