Yi-Zhou | MAAL

InvariantCloud: A globally invariant, uniquely indexed point cloud framework for robust 6-DoF tactile pose tracking

Thu, 31 Dec 2026 00:00:00 +0000

Ye, P., Ma, Y., Zhou, Y., Chen, W., Dong, W., Duan, M.*, 2026, “InvariantCloud: A globally invariant, uniquely indexed point cloud framework for robust 6-DoF tactile pose tracking,” IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria.

Sensorless contact forces estimation for robotic manipulators using dual-stage temporal-residual neural network compensation

Thu, 31 Dec 2026 00:00:00 +0000

Zhou, Y., Cheung, Y.H., Liu, S., Law, F.C., Shi, Y., Han, L., Duan, M.*, 2026, “Sensorless contact forces estimation for robotic manipulators using dual-stage temporal-residual neural network compensation,” Control Engineering Practice, 176, 107140.

Computation-Efficient Path Planning Using Evolving Artificial Repulsive Force over Expanding Obstacles for Robotic Manipulator

Wed, 30 Dec 2026 00:00:00 +0000

Zhou, Y., Huang, B., Cheung, Y.H., Ye, P., Duan, M.*, 2026, “Computation-Efficient Path Planning Using Evolving Artificial Repulsive Force over Expanding Obstacles for Robotic Manipulator,” ISA Transactions.

Design and multi-axis additive manufacturing of lightweight and skin-compatible mesh splints using continuous basalt fiber for rehabilitation

Wed, 30 Dec 2026 00:00:00 +0000

Li, F., Gao, F., Yang, Y., Zhou, Y., Duan, M.*, 2026, “Design and multi-axis additive manufacturing of lightweight and skin-compatible mesh splints using continuous basalt fiber for rehabilitation,” ASME Manufacturing Science and Engineering Conference (MSEC), State College, US.

Gaussian-process-based sensor placement and uncertainty quantification for dynamic response reconstruction in flexible aeroelastic structures

Tue, 29 Dec 2026 00:00:00 +0000

Dong, B., Mei, Y., Lu, X., Zhou, Y., Zhang, S., Wang, W., Duan, M.*, 2026, “Gaussian-process-based sensor placement and uncertainty quantification for dynamic response reconstruction in flexible aeroelastic structures,” Mechanical Systems and Signal Processing, 257, 114426.

Sensorless contact wrench estimation for industrial robots

Tue, 11 Aug 2026 00:00:00 +0000

Robots used for polishing, assembly, and manipulation need reliable contact-force feedback. A six-axis wrist force/torque sensor provides direct measurements, but adds cost, wiring, payload, and integration constraints. This project estimates the same six-dimensional contact wrench from signals already available on the robot: joint motion and motor current.

Dual-stage estimation

The estimator combines a physics-based robot model with two learned residual corrections:

Free-space dynamics compensation. An LSTM learns joint-torque errors caused by friction, backlash, hysteresis, parameter mismatch, and torque-conversion bias using contact-free trajectories.
Contact wrench compensation. A temporal encoder and residual network correct the remaining task-space error during contact and predict an input-dependent uncertainty for each wrench axis.

Separating these responsibilities keeps the estimate anchored to robot mechanics while allowing each learning stage to focus on a distinct error source.

Experimental validation

The method was evaluated on a six-axis industrial manipulator. A cable-and-pulley rig applied loads of 0.5, 1.0, and 1.5 kg from multiple directions. A wrist load cell sampled at 1 kHz supplied training labels and evaluation ground truth, but was not used as an input during sensorless inference.

Stage I reduced the Joint 1 residual-torque RMSE from 4.2649 to 0.8591 Nm and the Joint 2 RMSE from 3.1453 to 1.0069 Nm. Across the final six-axis wrench evaluation, the dual-stage method achieved the lowest reported RMSE, maximum error, and relative error on every force and moment axis.

Metric	Fx	Fy	Fz	Mx	My	Mz
RMSE	1.5959 N	0.7067 N	1.9678 N	0.1367 Nm	0.1141 Nm	0.0538 Nm
Maximum error	5.9546 N	4.4262 N	5.3414 N	0.7739 Nm	0.4898 Nm	0.4104 Nm
Relative error	13.8%	5.8%	13.4%	17.6%	22.2%	8.3%

Why it matters

The main contribution is not simply a deeper network, but a physically meaningful decomposition of the estimation problem. The intermediate output makes each correction inspectable, while the probabilistic second stage provides a condition-dependent confidence signal. This creates a practical path toward lower-cost force-aware robots and future closed-loop force control without a permanently installed wrist sensor.

A computation-efficient path planning method for robotic manipulators using evolving artificial repulsive force over expanding obstacles

Thu, 01 Jan 2026 00:00:00 +0000

Duan, M., Zhou, Y., and Cheung, Y.H., IP.PA.12873, “A computation-efficient path planning method for robotic manipulators using evolving artificial repulsive force over expanding obstacles,” US Provisional Application 64/041,762 (filed Apr 2026); CN Application (approved for filing).

Sensorless contact forces estimation method for robotic manipulators using dual-stage temporal-residual neural network compensation

Thu, 01 Jan 2026 00:00:00 +0000

Duan, M., Zhou, Y., and Cheung, Y.H., IP.PA.12872, “Sensorless contact forces estimation method for robotic manipulators using dual-stage temporal-residual neural network compensation,” US Provisional Application 64/041,767 (filed Apr 2026); CN Application 202611125274.2 (filed Jul 2026).

Contact-force-based closed-loop control of multi-axis additive manufacturing With continuous-fiber-reinforced polymer

Wed, 31 Dec 2025 00:00:00 +0000

Yang, Y., Zhou, Y., Duan, M.*, 2025, “Contact-force-based closed-loop control of multi-axis additive manufacturing With continuous-fiber-reinforced polymer,” ASME International Manufacturing Science and Engineering Conference, Greenville.

Dynamic load alleviation of input-redundant flexible aircraft via nonlinear control allocation over invariant manifold

Sat, 27 Dec 2025 00:00:00 +0000

Dong, B., Zhou, Y., Duan, M.*, 2025, “Dynamic load alleviation of input-redundant flexible aircraft via nonlinear control allocation over invariant manifold,” Aerospace Science and Technology, 162, pp. 110119.

Dynamic robotic bricklaying force-position control considering mortar dynamics for enhanced consistency

Thu, 25 Dec 2025 00:00:00 +0000

Zhou, Y., Huang, B., Dong, B., Wen, Y., Duan, M.*, 2025, “Dynamic robotic bricklaying force-position control considering mortar dynamics for enhanced consistency,” Automation in Construction, 174, pp. 106090.

A force-position control system for robot bricklaying considering mortar dynamics

Wed, 01 Jan 2025 00:00:00 +0000

Duan, M., and Zhou, Y., IP.PA.12763, “A force-position control system for robot bricklaying considering mortar dynamics,” US Provisional Application 63/915,650 (filed Nov 2025); CN Application (approved for filing).

Vibration compensation of an Extendable Variable-Stiffness Boom-Lift-Mounted Robot

Mon, 30 Dec 2024 00:00:00 +0000

Zhou, Y., Duan, M.*, 2024, “Vibration compensation of an Extendable Variable-Stiffness Boom-Lift-Mounted Robot,” IEEE/ASME Transactions on Mechatronics, 29, 4, pp. 2812-2820.

Contact-force-based closed-loop control of shell structure additive manufacturing with continuous-fiber-reinforced polymer composites

Sun, 29 Dec 2024 00:00:00 +0000

Yang, Y., Zhou, Y., Duan, M.*, 2024, “Contact-force-based closed-loop control of shell structure additive manufacturing with continuous-fiber-reinforced polymer composites,” Journal of Materials Processing Technology, 331, pp. 118501.

Extendable variable-stiffness boom-lift-mounted robot with vibration compensation

Sun, 01 Jan 2023 00:00:00 +0000

Duan, M., and Zhou, Y., IP.PA.02024, “Extendable variable-stiffness boom-lift-mounted robot with vibration compensation,” US Provisional Application 63/615,786 (filed Dec 2023); US Patent 12,654,313 (issued Jun 2026); CN Application 202411946171.3 (filed Dec 2024, published); HK Application 42025111199.3 (filed Aug 2025, published).