Zhibin Li

Shenzhen Polytechnic

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Nikos G. Tsagarakis

Italian Institute of Technology

Darwin G. Caldwell

Italian Institute of Technology

Kai Yuan

Air Force Engineering University

Christopher McGreavy

European Organization for Nuclear Research

Eleftherios Triantafyllidis

University of Edinburgh

Chengxu Zhou

University College London

Chuanyu Yang

University of Edinburgh

Carlo Tiseo

University of Sussex

Mohammadreza Kasaei

University of Edinburgh

Quentin Rouxel

Université de Lorraine

Cooperative Institutions

Chinese Academy of Sciences

University of Edinburgh

Harbin Institute of Technology

University of Chinese Academy of Sciences

Tsinghua University

East China Normal University

Shanghai Jiao Tong University

Italian Institute of Technology

Northwest Institute of Eco-Environment and Resources

University College London

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Perceptive Locomotion with Controllable Pace and Natural Gait Transitions Over Uneven Terrains

arXiv (Cornell University) (2023)

Daniel Chee Hian Tan Jenny Zhang Michael Chuah Zhibin Li

This work developed a learning framework for perceptive legged locomotion that combines visual feedback, proprioceptive information, and active gait regulation of foot-ground contacts. The perception requires only one forward-facing camera to obtain the heightmap, and the active regulation of gait paces and traveling velocity are realized through our formulation of CPG-based high-level imitation of foot-ground contacts. Through this framework, an end-user has the ability to command task-level inputs to control different walking speeds and gait frequencies according to the traversal of different terrains, which enables more reliable negotiation with encountered obstacles. The results demonstrated that the learned perceptive locomotion policy followed task-level control inputs with intended behaviors, and was robust in presence of unseen terrains and external force perturbations. A video demonstration can be found at https://youtu.be/OTzlWzDfAe8, and the codebase at https://github.com/jennyzzt/perceptual-locomotion.

Codebase

Kinesthetic learning

10.48550/arxiv.2301.10894

Cite

Citations (0)

Accessibility-Based Clustering for Efficient Learning of Robot Fall Recovery.

arXiv (Cornell University) (2021)

Chong Zhang Wanming Yu Zhibin Li

For the model-free deep reinforcement learning of quadruped fall recovery, the initialization of robot configurations is crucial to the data efficiency and robustness. This work focuses on algorithmic improvements of data efficiency and robustness simultaneously through automatic discovery of initial states, which is achieved by our proposed K-Access algorithm based on accessibility metrics. Specifically, we formulated accessibility metrics to measure the difficulty of transitions between two arbitrary states, and proposed a novel K-Access algorithm for state-space clustering that automatically discovers the centroids of the static-pose clusters based on the accessibility metrics. By using the discovered centroidal static poses as initial states, we improve the data efficiency by reducing the redundant exploration, and enhance the robustness by easy explorations from the centroids to sampled static poses. We studied extensive validation using an 8-DOF quadrupedal robot Bittle. Compared to random initialization, the learning curve of our proposed method converges much faster, requiring only around 60% of training episodes. With our method, the robot can successfully recover standing poses in 99.4% of tests within 3 seconds.

Robustness

Initialization

Centroid

Source

Cite

Citations (0)

On New Invariant Solutions of Generalized Fokker-Planck Equation

Communications in Theoretical Physics (2004)

Ruoxia Yao Zhibin Li

The generalized one-dimensional Fokker–Planck equation is analyzed via potential symmetry method and the invariant solutions under potential symmetries are obtained. Among those solutions, some are new and first reported.

10.1088/0253-6102/41/5/665

Cite

Citations (2)

Optimal ankle compliance regulation for humanoid balancing control

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (2013)

Mohamad Mosadeghzad Zhibin Li Nikos G. Tsagarakis Gustavo A. Medrano‐Cerda Houman Dallali

Keeping balance is the main concern for humanoids in standing and walking tasks. This paper endeavors to acquire optimal ankle stabilization methods for humanoids with passive and active compliance and explain ankle balancing strategy from the compliance regulation perspective. Unlike classical stiff humanoids, the compliant ones can control both impedance and position during task operation. Optimal compliance regulation is resolved to maximize the stability of the humanoids. The linearized model is proposed to obtain the optimal ankle impedance for stabilizing against impacts. The nonlinear model is proposed as well and compared with the linear one. The proposed methods are validated by experiments on an intrinsically compliant humanoid using passivity based admittance and impedance controllers both in joint and Cartesian space.

Impedance Control

Admittance

Passivity

10.1109/iros.2013.6696946

Cite

Citations (10)

Variational-based speckle noise removal of SAR imagery

Chaomin Shen Ling Pi Yaxin Peng Zhibin Li

In this paper we present a variational method for synthetic aperture radar (SAR) speckle removal. Variational method is a newly developed technique for the removal of SAR's multiplicative noise. For an image, we could define an energy functional. The energy evolves as the original image changes, and the minimum energy corresponds to the speckle reduced result. Partial differential equation (PDE) technique is used to get the minimal solution. Our energy functional makes use of the statistical information of the multiplicative noise since it follows a Gamma law with mean mu = 1 and variance sigma ² = 1/M for M-look SAR. Our energy is a regularization term with two constraints. The regularization term is the integral for the norm of image gradient; two constraints are the mean of noise should be 1 and the variance of noise should be 1/M. We use the method of Lagrange multipliers, Euler-Lagrange equation and heat flow method to obtain the minimizer of the energy. ERS Precision Image (PRI) data are to demonstrate our algorithm. Numerical result shows that the speckle reduced image preserves edges and point targets while smoothes homogenous regions in the original image. The algorithm is computationally efficient and easy to implement.

Regularization

Multiplicative noise

Speckle noise

Energy functional

10.1109/igarss.2007.4422848

Cite

Citations (2)

Decoding Motor Skills of Artificial Intelligence and Human Policies: A Study on Humanoid and Human Balance Control

IEEE Robotics & Automation Magazine (2020)

Kai Yuan Christopher McGreavy Chuanyu Yang Wouter Wolfslag Zhibin Li

From the advancement in computers, computeraided design has emerged for mechanical and electronic engineering, architecture, and many other engineering fields. Foreseeing a similar development curve and technology wave, we forecast a new emerging discipline in the near future that uses learning-aided approaches to catalyze control development, alongside other similar applications such as medicine discovery. In this article, we propose a new paradigm for using machine learning to facilitate quicker, more efficient, and more effective control development, as an alternative way of leveraging the power of machine learning in addition to other options that intend to use learning directly in real-world applications.

10.1109/mra.2020.2980547

Cite

Citations (10)

A novel 3D-printing repair of surface cracks for improving the mechanical strength

2022 IEEE/SICE International Symposium on System Integration (SII) (2017)

Yuanfei Zhang Shaowei Fan Zhibin Li Hong Liu

A novel 3D-printing repair is proposed based on Fused Deposition Modeling (FDM) for improving the mechanical strength of the objects with surface cracks. Compared to the traditional FDM-based technique, the novelty of our proposed approach is that the extruding and moving directions of the printing nozzle are controllable and thus variable, eliminating any restriction of orthogonal alignment. This permits essential physical contact between the nozzle and the cracked area that allows the nozzle to remove surface material that might be covered by dust, as well as the heat transfer that preheats the inner material before being combined with the extruding one. Hence, the proposed approach can strengthen the bonding strength of materials to a great extent, particularly when the environmental temperature is not in a suitable range. Experimental results show that the mechanical strength of the objects with surface cracks is significantly improved by our proposed approach of 3D-printing repair compared to that produced by the traditional one.

Mechanical strength

Fused Deposition Modeling

3d printed

Deposition

10.1109/sii.2017.8279207

Cite

Citations (0)

Accessibility-Based Clustering for Efficient Learning of Locomotion Skills

2022 International Conference on Robotics and Automation (ICRA) (2022)

Chong Zhang Wanming Yu Zhibin Li

For model-free deep reinforcement learning of quadruped locomotion, the initialization of robot configurations is crucial for data efficiency and robustness. This work focuses on algorithmic improvements of data efficiency and robustness simultaneously through automatic discovery of initial states, which is achieved by our proposed K-Access algorithm based on accessibility metrics. Specifically, we formulated accessibility metrics to measure the difficulty of transitions between two arbitrary states, and proposed a novel K-Access algorithm for state-space clustering that automatically discovers the centroids of the static-pose clusters based on the accessibility metrics. By using the discovered centroidal static poses as the initial states, we can improve data efficiency by reducing redundant explorations, and enhance the robustness by more effective explorations from the centroids to sampled poses. Focusing on fall recovery as a very hard set of locomotion skills, we validated our method extensively using an 8-DoF quadrupedal robot Bittle. Compared to the baselines, the learning curve of our method converges much faster, requiring only 60% of training episodes. With our method, the robot can successfully recover to standing poses within 3 seconds in 99.4% of the test cases. Moreover, the method can generalize to other difficult skills successfully, such as backflipping.

Robustness

Initialization

Centroid

10.1109/icra46639.2022.9812113

Cite

Citations (4)

Contact-Implicit Trajectory Optimization Using an Analytically Solvable Contact Model for Locomotion on Variable Ground

IEEE Robotics and Automation Letters (2020)

Iordanis Chatzinikolaidis Yangwei You Zhibin Li

This paper presents a novel contact-implicit trajectory optimization method using an analytically solvable contact model to enable planning of interactions with hard, soft, and slippery environments. Specifically, we propose a novel contact model that can be computed in closed-form, satisfies friction cone constraints and can be embedded into direct trajectory optimization frameworks without complementarity constraints. The closed-form solution decouples the computation of the contact forces from other actuation forces and this property is used to formulate a minimal direct optimization problem expressed with configuration variables only. Our simulation study demonstrates the advantages over the rigid contact model and a trajectory optimization approach based on complementarity constraints. The proposed model enables physics-based optimization for a wide range of interactions with hard, slippery, and soft grounds in a unified manner expressed by two parameters only. By computing trotting and jumping motions for a quadruped robot, the proposed optimization demonstrates the versatility for multi-contact motion planning on surfaces with different physical properties.

Trajectory Optimization

Complementarity (molecular biology)

Linear complementarity problem

10.1109/lra.2020.3010754

Cite

Citations (14)

Instance-wise Grasp Synthesis for Robotic Grasping

Yucheng Xu Mohammadreza Kasaei Hamidreza Kasaei Zhibin Li

Generating high-quality instance-wise grasp con-figurations provides critical information of how to grasp specific objects in a multi-object environment and is of high importance for robot manipulation tasks. This work proposed a novel Single-Stage Grasp (SSG) synthesis network, which performs high-quality instance-wise grasp synthesis in a single stage: instance mask and grasp configurations are generated for each object simultaneously. Our method outperforms state-of-the-art on robotic grasp prediction based on the OCID-Grasp dataset, and performs competitively on the JACQUARD dataset. The benchmarking results showed significant improvements compared to the baseline on the accuracy of generated grasp configurations. The performance of the proposed method has been validated through both extensive simulations and real robot experiments for three tasks including single object pick-and-place, grasp synthesis in cluttered environments and table cleaning task.

Table (database)

Benchmarking

10.1109/icra48891.2023.10161149

Cite

Citations (1)