Chaoyang Song
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
Research Interests
Chaoyang Song has a total of 226 co-authors. Here are the top co-authors by number of shared publications:
- Fang Wan
School of Design, Southern University of Science and Technology, Shenzhen, China
32 shared publications Fang Wan
Southern University of Science and Technology
15 shared publications- Jia Pan
The University of Hong Kong
12 shared publications - Xudong Han
School of Design, Southern University of Science and Technology, Shenzhen, China
12 shared publications - Ning Guo
SUSTech Institute of Robotics Southern University of Science and Technology Shenzhen China
8 shared publications - Jian Lin
State Key Laboratory of Tropical Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou, China
7 shared publications
Latest Publications
- Open Access
- 16 October 2026
- Published by Springer Nature in Nature Machine Intelligence
- p. 1-12
Large-scale iontronic skins with neural-hierarchical processing architecture
The human skin gathers and encodes signals from over 200,000 mechanoreceptors, enabling high-spatiotemporal-resolution tactile perception and instant injury prevention. Existing skin-like sensor arrays often have limited sensor count and density, and they use a serial readout architecture that suffers from readout latency, signal crosstalk and bandwidth consumption as element density increases. Here we report a high-density (1,110 units cm ‒2 ) and large-scale (>10,000 units) neural-hierarchical iontronic skin that mimics the hierarchical processing architecture of the human sensory system, which transmits interactive information in layers via signal encoding, convergence and cognitive modelling. Frequency-based position encoding of iontronic sensors enables parallel signal transmission with suppressed crosstalk and a rate of 100 frames per second, while backend convergent compression decreases bandwidth consumption by hundreds of times. We demonstrate that humanoid robots equipped with neural-hierarchical iontronic skins can perform challenging tasks, including fine tactile interactions that can resolve surface features of 300 µm, and the perception of nociceptive stimuli for self-protective responses. This technology provides a large-scale tactile system with high spatiotemporal resolution, paving the way for humanoid robots to approach human-level perception and manipulation.
- 16 October 2026
- Published by Springer Nature in Nature Machine Intelligence
- p. 1-12
Open AccessLarge-scale iontronic skins with neural-hierarchical processing architecture
The human skin gathers and encodes signals from over 200,000 mechanoreceptors, enabling high-spatiotemporal-resolution tactile perception and instant injury prevention. Existing skin-like sensor arrays often have limited sensor count and density, and they use a serial readout architecture that suffers from readout latency, signal crosstalk and bandwidth consumption as element density increases. Here we report a high-density (1,110 units cm ‒2 ) and large-scale (>10,000 units) neural-hierarchical iontronic skin that mimics the hierarchical processing architecture of the human sensory system, which transmits interactive information in layers via signal encoding, convergence and cognitive modelling. Frequency-based position encoding of iontronic sensors enables parallel signal transmission with suppressed crosstalk and a rate of 100 frames per second, while backend convergent compression decreases bandwidth consumption by hundreds of times. We demonstrate that humanoid robots equipped with neural-hierarchical iontronic skins can perform challenging tasks, including fine tactile interactions that can resolve surface features of 300 µm, and the perception of nociceptive stimuli for self-protective responses. This technology provides a large-scale tactile system with high spatiotemporal resolution, paving the way for humanoid robots to approach human-level perception and manipulation.
- Open Access
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7015-7022
Topology-Optimized, Dual-Phase Gripper With Force Estimation for Underwater Operation
Addressing the critical trade-off between compliance and grasping force in underwater manipulation, this letter presents a novel topology optimization framework to automate the design of soft, variable-stiffness fingers from a single material. By employing multiple load cases within the optimization objective, our framework automatically synthesizes a finger structure that preserves the adaptive Fin Ray effect while exhibiting programmed, multi-stage stiffness. We utilize this method to realize a dual-phase finger, characterized by low initial stiffness for compliant contact with a compliant object and high subsequent stiffness for secure grasping. Quantitative comparisons validate this achievement with the optimized design yielding a grasping force 3.6 times higher than that of a Fin Ray finger with comparable softness, while simultaneously achieving an adaptation 2.8 times higher than that of a high-force Fin Ray variant. To enable damage-aware teleoperation, a flex sensor is embedded within the finger structure. We establish a mapping to grasping force via a piecewise-regressed model, whose structure directly reflects the finger's dual-phase mechanical behavior. The gripper is validated through a series of underwater experiments ranging from controlled laboratory tests to a nearshore field trial. This work establishes a new pathway for designing automated, single-material soft grippers with direct applications in complex underwater environments.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7015-7022
Open AccessTopology-Optimized, Dual-Phase Gripper With Force Estimation for Underwater Operation
Addressing the critical trade-off between compliance and grasping force in underwater manipulation, this letter presents a novel topology optimization framework to automate the design of soft, variable-stiffness fingers from a single material. By employing multiple load cases within the optimization objective, our framework automatically synthesizes a finger structure that preserves the adaptive Fin Ray effect while exhibiting programmed, multi-stage stiffness. We utilize this method to realize a dual-phase finger, characterized by low initial stiffness for compliant contact with a compliant object and high subsequent stiffness for secure grasping. Quantitative comparisons validate this achievement with the optimized design yielding a grasping force 3.6 times higher than that of a Fin Ray finger with comparable softness, while simultaneously achieving an adaptation 2.8 times higher than that of a high-force Fin Ray variant. To enable damage-aware teleoperation, a flex sensor is embedded within the finger structure. We establish a mapping to grasping force via a piecewise-regressed model, whose structure directly reflects the finger's dual-phase mechanical behavior. The gripper is validated through a series of underwater experiments ranging from controlled laboratory tests to a nearshore field trial. This work establishes a new pathway for designing automated, single-material soft grippers with direct applications in complex underwater environments.
- Open Access
- 1 March 2026
- Published by KEAI Publishing in Biomimetic Intelligence and Robotics
Multi-modal vision-based deformable perception for in-finger manipulation with soft active surfaces
- 1 March 2026
- Published by KEAI Publishing in Biomimetic Intelligence and Robotics
Open AccessMulti-modal vision-based deformable perception for in-finger manipulation with soft active surfaces
- 28 January 2026
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (12) , 1801-1819
A dataset and benchmark for robotic cloth unfolding grasp selection: The ICRA 2024 Cloth Competition
Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a benchmark and organized the ICRA 2024 Cloth Competition, a unique head-to-head evaluation focused on grasp pose selection for in-air robotic cloth unfolding. Eleven teams participated in the competition, utilizing the publicly released dataset of 500 real-world robotic grasp attempts for cloth unfolding and employing diverse approaches to generate in-air unfolding grasps. Analysis of the competition results revealed insights about the trade-off between grasp success and coverage, the surprisingly strong achievements of hand-engineered methods and a significant discrepancy between competition performance and prior work, underscoring the importance of independent, out-of-the-lab evaluation in robotic cloth manipulation. We also expanded the dataset with 176 competition evaluation trials, resulting in a dataset of 679 unfolding demonstrations across 34 garments. This dataset is a valuable resource for developing and evaluating grasp selection methods, particularly for learning-based approaches. We hope that the benchmark, dataset, and competition results can serve as a foundation for future benchmarks and drive further progress in data-driven robotic cloth manipulation.
- 28 January 2026
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (12) , 1801-1819
A dataset and benchmark for robotic cloth unfolding grasp selection: The ICRA 2024 Cloth Competition
Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a benchmark and organized the ICRA 2024 Cloth Competition, a unique head-to-head evaluation focused on grasp pose selection for in-air robotic cloth unfolding. Eleven teams participated in the competition, utilizing the publicly released dataset of 500 real-world robotic grasp attempts for cloth unfolding and employing diverse approaches to generate in-air unfolding grasps. Analysis of the competition results revealed insights about the trade-off between grasp success and coverage, the surprisingly strong achievements of hand-engineered methods and a significant discrepancy between competition performance and prior work, underscoring the importance of independent, out-of-the-lab evaluation in robotic cloth manipulation. We also expanded the dataset with 176 competition evaluation trials, resulting in a dataset of 679 unfolding demonstrations across 34 garments. This dataset is a valuable resource for developing and evaluating grasp selection methods, particularly for learning-based approaches. We hope that the benchmark, dataset, and competition results can serve as a foundation for future benchmarks and drive further progress in data-driven robotic cloth manipulation.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Practice
- Vol. 1, 18-22
Lessons Learned From the euROBIN Manipulation Skill Versatility Challenge At IROS 2024
Robotic automation in high-mix, low-volume settings often relies on structured workcells where fixtures, workpieces, and procedures are well defined, but tasks must be reconfigured quickly across variants. This paper presents the Design and Learning Research Group's solution to the euROBIN Manipulation Skill Versatility Challenge (MSVC) at IROS 2024, in which a standardized electronic task board is operated through a fixed sequence of subtasks. We deliberately adopt a simple, industry-style implementation: each subtask is taught by recording an open-loop Tool Center Point (TCP) and gripper trajectory in the task-board frame, a wrist-mounted depth camera is used once per run to localize the board and a few key features, and a web dashboard exposes the resulting motion primitives as reusable code blocks that can be reordered and reparameterized. With this pipeline, our system completes the benchmark in 28.2 s in the lab (37.2 s on-site), compared to a human baseline of 16.3 s and an average of 83.5 s for previous teams, closing a large part of the performance gap without advanced learning or feedback control. We further demonstrate limited skill transfer by retargeting the same subtask library to a smoke-detector battery replacement scenario required by the competition. Finally, we release our implementation as open source and discuss how competition design and benchmark structure influence the balance between simple engineered solutions and richer sensing and learning.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Practice
- Vol. 1, 18-22
Lessons Learned From the euROBIN Manipulation Skill Versatility Challenge At IROS 2024
Robotic automation in high-mix, low-volume settings often relies on structured workcells where fixtures, workpieces, and procedures are well defined, but tasks must be reconfigured quickly across variants. This paper presents the Design and Learning Research Group's solution to the euROBIN Manipulation Skill Versatility Challenge (MSVC) at IROS 2024, in which a standardized electronic task board is operated through a fixed sequence of subtasks. We deliberately adopt a simple, industry-style implementation: each subtask is taught by recording an open-loop Tool Center Point (TCP) and gripper trajectory in the task-board frame, a wrist-mounted depth camera is used once per run to localize the board and a few key features, and a web dashboard exposes the resulting motion primitives as reusable code blocks that can be reordered and reparameterized. With this pipeline, our system completes the benchmark in 28.2 s in the lab (37.2 s on-site), compared to a human baseline of 16.3 s and an average of 83.5 s for previous teams, closing a large part of the performance gap without advanced learning or feedback control. We further demonstrate limited skill transfer by retargeting the same subtask library to a smoke-detector battery replacement scenario required by the competition. Finally, we release our implementation as open source and discuss how competition design and benchmark structure influence the balance between simple engineered solutions and richer sensing and learning.
- 9 December 2025
- Published by Elsevier in Ocean Engineering
- Vol. 346
Bio-inspired rigid-Soft interaction for robust picking underwater
- 9 December 2025
- Published by Elsevier in Ocean Engineering
- Vol. 346
Bio-inspired rigid-Soft interaction for robust picking underwater
- Open Access
- 1 October 2025
- Published by KEAI Publishing in Fundamental Research
One-DoF robotic design of overconstrained limbs with energy-efficient, self-collision-free motion
- 1 October 2025
- Published by KEAI Publishing in Fundamental Research
Open AccessOne-DoF robotic design of overconstrained limbs with energy-efficient, self-collision-free motion
- Open Access
One-DoF Robotic Design of Overconstrained Limbs with Energy-Efficient, Self-Collision-Free Motion
While it is expected to build robotic limbs with multiple degrees of freedom (DoF) inspired by nature, a single DoF design remains fundamental, providing benefits that include, but are not limited to, simplicity, robustness, cost-effectiveness, and efficiency. Mechanisms, especially those with multiple links and revolute joints connected in closed loops, play an enabling factor in introducing motion diversity for 1-DoF systems, which are usually constrained by self-collision during a full-cycle range of motion. This study presents a novel computational approach to designing one-degree-of-freedom (1-DoF) overconstrained robotic limbs for a desired spatial trajectory, while achieving energy-efficient, self-collision-free motion in full-cycle rotations. Firstly, we present the geometric optimization problem of linkage-based robotic limbs in a generalized formulation for self-collision-free design. Next, we formulate the spatial trajectory generation problem with the overconstrained linkages by optimizing the similarity and dynamic-related metrics. We further optimize the geometric shape of the overconstrained linkage to ensure smooth and collision-free motion driven by a single actuator. We validated our proposed method through various experiments, including personalized automata and bio-inspired hexapod robots. The resulting hexapod robot, featuring overconstrained robotic limbs, demonstrated outstanding energy efficiency during forward walking.
Open AccessOne-DoF Robotic Design of Overconstrained Limbs with Energy-Efficient, Self-Collision-Free Motion
While it is expected to build robotic limbs with multiple degrees of freedom (DoF) inspired by nature, a single DoF design remains fundamental, providing benefits that include, but are not limited to, simplicity, robustness, cost-effectiveness, and efficiency. Mechanisms, especially those with multiple links and revolute joints connected in closed loops, play an enabling factor in introducing motion diversity for 1-DoF systems, which are usually constrained by self-collision during a full-cycle range of motion. This study presents a novel computational approach to designing one-degree-of-freedom (1-DoF) overconstrained robotic limbs for a desired spatial trajectory, while achieving energy-efficient, self-collision-free motion in full-cycle rotations. Firstly, we present the geometric optimization problem of linkage-based robotic limbs in a generalized formulation for self-collision-free design. Next, we formulate the spatial trajectory generation problem with the overconstrained linkages by optimizing the similarity and dynamic-related metrics. We further optimize the geometric shape of the overconstrained linkage to ensure smooth and collision-free motion driven by a single actuator. We validated our proposed method through various experiments, including personalized automata and bio-inspired hexapod robots. The resulting hexapod robot, featuring overconstrained robotic limbs, demonstrated outstanding energy efficiency during forward walking.
- Open Access
A Biomimetic Vertebraic Soft Robotic Tail for High-Speed, High-Force Dynamic Maneuvering
Robotic tails can enhance the stability and maneuverability of mobile robots, but current designs face a trade-off between the power of rigid systems and the safety of soft ones. Rigid tails generate large inertial effects but pose risks in unstructured environments, while soft tails lack sufficient speed and force. We present a Biomimetic Vertebraic Soft Robotic (BVSR) tail that resolves this challenge through a compliant pneumatic body reinforced by a passively jointed vertebral column inspired by musculoskeletal structures. This hybrid design decouples load-bearing and actuation, enabling high-pressure actuation (up to 6 bar) for superior dynamics while preserving compliance. A dedicated kinematic and dynamic model incorporating vertebral constraints is developed and validated experimentally. The BVSR tail achieves angular velocities above 670°/s and generates inertial forces and torques up to 5.58 N and 1.21 Nm, indicating over 200% improvement compared to non-vertebraic designs. Demonstrations on rapid cart stabilization, obstacle negotiation, high-speed steering, and quadruped integration confirm its versatility and practical utility for agile robotic platforms.
Open AccessA Biomimetic Vertebraic Soft Robotic Tail for High-Speed, High-Force Dynamic Maneuvering
Robotic tails can enhance the stability and maneuverability of mobile robots, but current designs face a trade-off between the power of rigid systems and the safety of soft ones. Rigid tails generate large inertial effects but pose risks in unstructured environments, while soft tails lack sufficient speed and force. We present a Biomimetic Vertebraic Soft Robotic (BVSR) tail that resolves this challenge through a compliant pneumatic body reinforced by a passively jointed vertebral column inspired by musculoskeletal structures. This hybrid design decouples load-bearing and actuation, enabling high-pressure actuation (up to 6 bar) for superior dynamics while preserving compliance. A dedicated kinematic and dynamic model incorporating vertebral constraints is developed and validated experimentally. The BVSR tail achieves angular velocities above 670°/s and generates inertial forces and torques up to 5.58 N and 1.21 Nm, indicating over 200% improvement compared to non-vertebraic designs. Demonstrations on rapid cart stabilization, obstacle negotiation, high-speed steering, and quadruped integration confirm its versatility and practical utility for agile robotic platforms.
- Open Access
MagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap
The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a "domain gap" in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this gap. MagiClaw functions interchangeably as both a handheld tool for intuitive data collection and a robotic end-effector for policy deployment, ensuring hardware consistency and reliability. Each finger incorporates a Soft Polyhedral Network (SPN) with an embedded camera, enabling vision-based estimation of 6-DoF forces and contact deformation. This proprioceptive data is fused with exteroceptive environmental sensing from an integrated iPhone, which provides 6D pose, RGB video, and LiDAR-based depth maps. Through a custom iOS application, MagiClaw streams synchronized, multi-modal data for real-time teleoperation, offline policy learning, and immersive control via mixed-reality interfaces. We demonstrate how this unified system architecture lowers the barrier to collecting high-fidelity, contact-rich datasets and accelerates the development of generalizable manipulation policies. Please refer to the iOS app at https://apps.apple.com/cn/app/magiclaw/id6661033548 for further details.
Open AccessMagiClaw: A Dual-Use, Vision-Based Soft Gripper for Bridging the Human Demonstration to Robotic Deployment Gap
The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a "domain gap" in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this gap. MagiClaw functions interchangeably as both a handheld tool for intuitive data collection and a robotic end-effector for policy deployment, ensuring hardware consistency and reliability. Each finger incorporates a Soft Polyhedral Network (SPN) with an embedded camera, enabling vision-based estimation of 6-DoF forces and contact deformation. This proprioceptive data is fused with exteroceptive environmental sensing from an integrated iPhone, which provides 6D pose, RGB video, and LiDAR-based depth maps. Through a custom iOS application, MagiClaw streams synchronized, multi-modal data for real-time teleoperation, offline policy learning, and immersive control via mixed-reality interfaces. We demonstrate how this unified system architecture lowers the barrier to collecting high-fidelity, contact-rich datasets and accelerates the development of generalizable manipulation policies. Please refer to the iOS app at https://apps.apple.com/cn/app/magiclaw/id6661033548 for further details.